Evolutionary algorithms (EAs) are optimization algorithms that simulate natural selection and genetic mechanisms. Despite advancements, existing EAs have two main issues: (1) they rarely update next-generation individuals based on global correlations, thus limiting comprehensive learning; (2) it is challenging to balance exploration and exploitation, excessive exploitation leads to premature convergence to local optima, while excessive exploration results in an excessively slow search. Existing EAs heavily rely on manual parameter settings, inappropriate parameters might disrupt the exploration-exploitation balance, further impairing model performance. To address these challenges, we propose a novel evolutionary algorithm framework called Graph Neural Evolution (GNE). Unlike traditional EAs, GNE represents the population as a graph, where nodes correspond to individuals, and edges capture their relationships, thus effectively leveraging global information. Meanwhile, GNE utilizes spectral graph neural networks (GNNs) to decompose evolutionary signals into their frequency components and designs a filtering function to fuse these components. High-frequency components capture diverse global information, while low-frequency components capture more consistent information. This explicit frequency filtering strategy directly controls global-scale features through frequency components, overcoming the limitations of manual parameter settings and making the exploration-exploitation control more interpretable and effective. Extensive evaluations on nine benchmark functions (e.g., Sphere, Rastrigin, and Rosenbrock) demonstrate that GNE consistently outperforms both classical algorithms (GA, DE, CMA-ES) and advanced algorithms (SDAES, RL-SHADE) under various conditions, including original, noise-corrupted, and optimal solution deviation scenarios. GNE achieves solution quality several orders of magnitude better than other algorithms (e.g., 3.07e-20 mean on Sphere vs. 1.51e-07).

We introduce RealmDreamer, a technique for generating forward-facing 3D scenes from text descriptions. Our method optimizes a 3D Gaussian Splatting representation to match complex text prompts using pretrained diffusion models. Our key insight is to leverage 2D inpainting diffusion models conditioned on an initial scene estimate to provide low variance and high-fidelity estimates of unknown regions during 3D distillation. In conjunction, we imbue correct geometry with geometric distillation from a depth diffusion model, conditioned on samples from the inpainting model. We find that the initialization of the optimization is crucial, and provide a principled methodology for doing so. Notably, our technique doesn't require video or multi-view data and can synthesize various high-quality 3D scenes in different styles with complex layouts. Further, the generality of our method allows 3D synthesis from a single image. As measured by a comprehensive user study, our method outperforms all existing approaches, preferred by 88-95%. Project page: realmdreamer.github.io

This work focuses on tracking and understanding human motion using consumer wearable devices, such as VR/AR headsets, smart glasses, cellphones, and smartwatches. These devices provide diverse, multi-modal sensor inputs, including egocentric images, and 1-3 sparse IMU sensors in varied combinations. Motion descriptions can also accompany these signals. The diverse input modalities and their intermittent availability pose challenges for consistent motion capture and understanding. In this work, we present Ego4o (o for omni), a new framework for simultaneous human motion capture and understanding from multi-modal egocentric inputs. This method maintains performance with partial inputs while achieving better results when multiple modalities are combined. First, the IMU sensor inputs, the optional egocentric image, and text description of human motion are encoded into the latent space of a motion VQ-VAE. Next, the latent vectors are sent to the VQ-VAE decoder and optimized to track human motion. When motion descriptions are unavailable, the latent vectors can be input into a multi-modal LLM to generate human motion descriptions, which can further enhance motion capture accuracy. Quantitative and qualitative evaluations demonstrate the effectiveness of our method in predicting accurate human motion and high-quality motion descriptions. Project page: https://jianwang-mpi.github.io/ego4o.

Faithfully reconstructing textured shapes and physical properties from videos presents an intriguing yet challenging problem. Significant efforts have been dedicated to advancing such a system identification problem in this area. Previous methods often rely on heavy optimization pipelines with a differentiable simulator and renderer to estimate physical parameters. However, these approaches frequently necessitate extensive hyperparameter tuning for each scene and involve a costly optimization process, which limits both their practicality and generalizability. In this work, we propose a novel framework, Vid2Sim, a generalizable video-based approach for recovering geometry and physical properties through a mesh-free reduced simulation based on Linear Blend Skinning (LBS), offering high computational efficiency and versatile representation capability. Specifically, Vid2Sim first reconstructs the observed configuration of the physical system from video using a feed-forward neural network trained to capture physical world knowledge. A lightweight optimization pipeline then refines the estimated appearance, geometry, and physical properties to closely align with video observations within just a few minutes. Additionally, after the reconstruction, Vid2Sim enables high-quality, mesh-free simulation with high efficiency. Extensive experiments demonstrate that our method achieves superior accuracy and efficiency in reconstructing geometry and physical properties from video data.

Photorealistic simulators are essential for the training and evaluation of vision-centric autonomous vehicles (AVs). At their core is Novel View Synthesis (NVS), a crucial capability that generates diverse unseen viewpoints to accommodate the broad and continuous pose distribution of AVs. Recent advances in radiance fields, such as 3D Gaussian Splatting, achieve photorealistic rendering at real-time speeds and have been widely used in modeling large-scale driving scenes. However, their performance is commonly evaluated using an interpolated setup with highly correlated training and test views. In contrast, extrapolation, where test views largely deviate from training views, remains underexplored, limiting progress in generalizable simulation technology. To address this gap, we leverage publicly available AV datasets with multiple traversals, multiple vehicles, and multiple cameras to build the first Extrapolated Urban View Synthesis (EUVS) benchmark. Meanwhile, we conduct both quantitative and qualitative evaluations of state-of-the-art NVS methods across different evaluation settings. Our results show that current NVS methods are prone to overfitting to training views. Besides, incorporating diffusion priors and improving geometry cannot fundamentally improve NVS under large view changes, highlighting the need for more robust approaches and large-scale training. We will release the data to help advance self-driving and urban robotics simulation technology.

Human motion is highly diverse and dynamic, posing challenges for imitation learning algorithms that aim to generalize motor skills for controlling simulated characters. Previous methods typically rely on a universal full-body controller for tracking reference motion (tracking-based model) or a unified full-body skill embedding space (skill embedding). However, these approaches often struggle to generalize and scale to larger motion datasets. In this work, we introduce a novel skill learning framework, ModSkill, that decouples complex full-body skills into compositional, modular skills for independent body parts. Our framework features a skill modularization attention layer that processes policy observations into modular skill embeddings that guide low-level controllers for each body part. We also propose an Active Skill Learning approach with Generative Adaptive Sampling, using large motion generation models to adaptively enhance policy learning in challenging tracking scenarios. Our results show that this modularized skill learning framework, enhanced by generative sampling, outperforms existing methods in precise full-body motion tracking and enables reusable skill embeddings for diverse goal-driven tasks.

Reconstructing 3D hand-face interactions with deformations from a single image is a challenging yet crucial task with broad applications in AR, VR, and gaming. The challenges stem from self-occlusions during single-view hand-face interactions, diverse spatial relationships between hands and face, complex deformations, and the ambiguity of the single-view setting. The previous state-of-the-art, Decaf, employs a global fitting optimization guided by contact and deformation estimation networks trained on studio-collected data with 3D annotations. However, Decaf suffers from a time-consuming optimization process and limited generalization capability due to its reliance on 3D annotations of hand-face interaction data. To address these issues, we present DICE, the first end-to-end method for Deformation-aware hand-face Interaction reCovEry from a single image. DICE estimates the poses of hands and faces, contacts, and deformations simultaneously using a Transformer-based architecture. It features disentangling the regression of local deformation fields and global mesh vertex locations into two network branches, enhancing deformation and contact estimation for precise and robust hand-face mesh recovery. To improve generalizability, we propose a weakly-supervised training approach that augments the training set using in-the-wild images without 3D ground-truth annotations, employing the depths of 2D keypoints estimated by off-the-shelf models and adversarial priors of poses for supervision. Our experiments demonstrate that DICE achieves state-of-the-art performance on a standard benchmark and in-the- wild data in terms of accuracy and physical plausibility. Additionally, our method operates at an interactive rate (20 fps) on an Nvidia 4090 GPU, whereas Decaf requires more than 15 seconds for a single image. The code will be available at: https://github.com/Qingxuan-Wu/DICE.

Existing video generation models excel at producing photo-realistic videos from text or images, but often lack physical plausibility and 3D controllability. To overcome these limitations, we introduce PhysCtrl, a novel framework for physics-grounded image-to-video generation with physical parameters and force control. At its core is a generative physics network that learns the distribution of physical dynamics across four materials (elastic, sand, plasticine, and rigid) via a diffusion model conditioned on physics parameters and applied forces. We represent physical dynamics as 3D point trajectories and train on a large-scale synthetic dataset of 550K animations generated by physics simulators. We enhance the diffusion model with a novel spatiotemporal attention block that emulates particle interactions and incorporates physics-based constraints during training to enforce physical plausibility. Experiments show that PhysCtrl generates realistic, physics-grounded motion trajectories which, when used to drive image-to-video models, yield high-fidelity, controllable videos that outperform existing methods in both visual quality and physical plausibility. Our code, model and data will be made publicly available upon publication.

Reconstructing physically plausible human motion from monocular videos remains a challenging problem in computer vision and graphics. Existing methods primarily focus on kinematics-based pose estimation, often leading to unrealistic results due to the lack of physical constraints. To address such artifacts, prior methods have typically relied on physics-based post-processing following the initial kinematics-based motion estimation. However, this two-stage design introduces error accumulation, ultimately limiting the overall reconstruction quality. In this paper, we present PhysHMR, a unified framework that directly learns a visual-to-action policy for humanoid control in a physics-based simulator, enabling motion reconstruction that is both physically grounded and visually aligned with the input video. A key component of our approach is the pixel-as-ray strategy, which lifts 2D keypoints into 3D spatial rays and transforms them into global space. These rays are incorporated as policy inputs, providing robust global pose guidance without depending on noisy 3D root predictions. This soft global grounding, combined with local visual features from a pretrained encoder, allows the policy to reason over both detailed pose and global positioning. To overcome the sample inefficiency of reinforcement learning, we further introduce a distillation scheme that transfers motion knowledge from a mocap-trained expert to the vision-conditioned policy, which is then refined using physically motivated reinforcement learning rewards. Extensive experiments demonstrate that PhysHMR produces high-fidelity, physically plausible motion across diverse scenarios, outperforming prior approaches in both visual accuracy and physical realism.

ABSTRACT Shilling attack detection is a method to identify and defend against malicious users in recommender systems, and it mainly detects shilling attackers by analyzing user behavior or item content anomalies. Items in the system subject to shilling attack often present abnormal scoring time‐series information and relationship networks, but time‐series data has the characteristics of large and unstable data volume, which makes it difficult to directly use raw data for detection, while detection from user relationship networks can often only solve a specific attack problem, and it is difficult to detect coordinated attack behaviors. To address the above issues, we propose a detection method called ITRN, which makes full use of item timing information and relational networks, dividing the time series of item ratings based on important points, constructing cubes for similarity measure using the second‐order difference method to obtain the anomalous time intervals and the set of suspicious users, constructing a suspicious user‐item bipartite graph, aggregating the higher‐order neighboring information of the suspicious users using LightGCN, and then inputting these higher‐order embedded inputs into the linear layer that are mapped into a scalar, and finally these scalars are input into the Sigmoid function to obtain the probability of the user being suspicious. Experiments were conducted on three datasets of varying sizes from Movielens, and the results showed that our method improved precision by approximately 0.02 and F1‐measure by approximately 0.01 compared to the optimal baseline model.

Humans possess the ability to master a wide range of motor skills, enabling them to quickly and flexibly adapt to the surrounding environment. Despite recent progress in replicating such versatile human motor skills, existing research often oversimplifies or inadequately captures the complex interplay between human body movements and highly dynamic environments, such as interactions with fluids. In this paper, we present a world model for Character-Fluid Coupling (CFC) for simulating human-fluid interactions via two-way coupling. We introduce a two-level world model which consists of a Physics-Informed Neural Network (PINN)-based model for fluid dynamics and a character world model capturing body dynamics under various external forces. This two-level world model adeptly predicts the dynamics of fluid and its influence on rigid bodies via force prediction, sidestepping the computational burden of fluid simulation and providing policy gradients for efficient policy training. Once trained, our system can control characters to complete high-level tasks while adaptively responding to environmental changes. We also present that the fluid initiates emergent behaviors of the characters, enhancing motion diversity and interactivity. Extensive experiments underscore the effectiveness of CFC, demonstrating its ability to produce high-quality, realistic human-fluid interaction animations.

Recent advancements in single-image 3D generation have produced two main categories of methods: reconstruction-based and generative methods. Reconstruction-based methods are efficient but lack uncertainty handling, leading to blurry artifacts in unseen regions. Generative approaches that based on score distillation (Poole et al. 2023), (Wang et al. 2024) are slow due to scene-specific optimization. Other methods, like InstantMesh (Xu et al. 2024), use a two-stage process - generating multi-view images with a diffusion model and then reconstructing 3D - which is inefficient due to multiple denoising steps of the diffusion model. To overcome these limitations, we introduce GECO, a feed-forward method for fast and high-quality single-image-to-3D generation within one second on a single GPU. Our approach resolves uncertainty and inefficiency issues through a two-stage distillation process. In the first stage, we distill a multi-step diffusion model (Shi et al. 2023) into a one-step model using score distillation for single-image-to-multi-view synthesis. To mitigate the synthesis quality degradation caused by the one-step model, we introduce a second distillation stage to learn to predict high-quality 3D from imperfect multi-view generated images by performing distillation directly on 3D representations. Experiments demonstrate that GECO offers significant speed improvements and comparable reconstruction quality compared to prior two-stage methods.

Diffusion models have recently become the de-facto approach for generative modeling in the 2D domain. However, extending diffusion models to 3D is challenging, due to the difficulties in acquiring 3D ground truth data for training. On the other hand, 3D GANs that integrate implicit 3D representations into GANs have shown remarkable 3D-aware generation when trained only on single-view image datasets. However, 3D GANs do not provide straightforward ways to precisely control image synthesis. To address these challenges, We present Control3Diff, a 3D diffusion model that combines the strengths of diffusion models and 3D GANs for versatile controllable 3D-aware image synthesis for single-view datasets. Control3Diff explicitly models the underlying latent distribution (optionally conditioned on external inputs), thus enabling direct control during the diffusion process. Moreover, our approach is general and applicable to any types of controlling inputs, allowing us to train it with the same diffusion objective without any auxiliary supervision. We validate the efficacy of Control3Diff on standard image generation benchmarks including FFHQ, AFHQ, and ShapeNet, using various conditioning inputs such as images, sketches, and text prompts.

Neural Radiance Field (NeRF) has been widely recognized for its excellence in novel view synthesis and 3D scene reconstruction. However, their effectiveness is in-herently tied to the assumption of static scenes, rendering them susceptible to undesirable artifacts when confronted with transient distractors such as moving objects or shad-ows. In this work, we propose a novel paradigm, namely “Heuristics-Guided Segmentation” (HuGS), which signifi-cantly enhances the separation of static scenes from tran-sient distractors by harmoniously combining the strengths of hand-crafted heuristics and state-of-the-art segmentation models, thus significantly transcending the limitations of previous solutions. Furthermore, we delve into the metic-ulous design of heuristics, introducing a seamless fusion of Structure-from-Motion (SfM)-based heuristics and color residual heuristics, catering to a diverse range of texture profiles. Extensive experiments demonstrate the superiority and robustness of our method in mitigating transient dis-tractors for NeRFs trained in non-static scenes. Project page: https://cnhaox.github.io/NeRF-HuGS/

We introduce Gaussian Articulated Template Model (GART), an explicit, efficient, and expressive representation for non-rigid articulated subject capturing and rendering from monocular videos. GART utilizes a mixture of moving 3D Gaussians to explicitly approximate a deformable subject's geometry and appearance. It takes advantage of a categorical template model prior (SMPL, SMAL, etc.) with learnable forward skinning while further generalizing to more complex non-rigid deformations with novel latent bones. GART can be reconstructed via differentiable rendering from monocular videos in seconds or minutes and rendered in novel poses faster than 150fps.

In this work, we introduce Wonder3D, a novel method for efficiently generating high-fidelity textured meshes from single-view images. Recent methods based on Score Distillation Sampling (SDS) have shown the potential to recover 3D geometry from 2D diffusion priors, but they typically suffer from time-consuming per-shape optimization and inconsistent geometry. In contrast, certain works di-rectly produce 3D information via fast network inferences, but their results are often of low quality and lack geometric details. To holistically improve the quality, consistency, and efficiency of single-view reconstruction tasks, we pro-pose a cross-domain diffusion model that generates multi-view normal maps and the corresponding color images. To ensure the consistency of generation, we employ a multi-view cross-domain attention mechanism that facilitates information exchange across views and modalities. Lastly, we introduce a geometry-aware normal fusion algorithm that extracts high-quality surfaces from the multi-view 2D representations in only 2 r-;» 3 minutes. Our extensive evaluations demonstrate that our method achieves high-quality reconstruction results, robust generalization, and good efficiency compared to prior works.

In this work, we explore egocentric whole-body motion capture using a single fisheye camera, which simultane-ously estimates human body and hand motion. This task presents significant challenges due to three factors: the lack of high-quality datasets, fisheye camera distortion, and hu-man body self-occlusion. To address these challenges, we propose a novel approach that leverages Fisheye ViT to ex-tract fisheye image features, which are subsequently con-verted into pixel-aligned 3D heatmap representations for 3D human body pose prediction. For hand tracking, we incorporate dedicated hand detection and hand pose esti-mation networks for regressing 3D hand poses. Finally, we develop a diffusion-based whole-body motion prior model to refine the estimated whole-body motion while accounting for joint uncertainties. To train these networks, we col-lect a large synthetic dataset, Ego WholeBody, comprising 840,000 high-quality egocentric images captured across a diverse range of whole-body motion sequences. Quantitative and qualitative evaluations demonstrate the effective-ness of our method in producing high-quality whole-body motion estimates from a single egocentric camera.

3D simulated environments play a critical role in Embodied AI, but their creation requires expertise and extensive manual effort, restricting their diversity and scope. To miti-gate this limitation, we present Holodeck, a system that generates 3D environments to match a user-supplied prompt fullyautomatedly. Holodeck can generate diverse scenes, e.g., arcades, spas, and museums, adjust the designs for styles, and can capture the semantics of complex queries such as “apartment for a researcher with a cat” and “office of a professor who is a fan of Star Wars”. Holodeck leverages a large language model (i.e., GPT-4) for common sense knowledge about what the scene might look like and uses a large collection of 3D assets from Objaverse to populate the scene with diverse objects. To address the challenge of positioning objects correctly, we prompt GPT-4 to generate spatial relational constraints between objects and then optimize the layout to satisfy those constraints. Our large-scale human evaluation shows that annotators prefer Holodeck over manually designed procedural baselines in residential scenes and that Holodeck can produce high-quality outputs for diverse scene types. We also demonstrate an exciting application of Holodeck in Embodied AI, training agents to navigate in novel scenes like music rooms and daycares without human-constructed data, which is a significant step forward in developing general-purpose embodied agents.

In this paper, we present a novel diffusion model called SyncDreamer that generates multiview-consistent images from a single-view image. Using pretrained large-scale 2D diffusion models, recent work Zero123 demonstrates the ability to generate plausible novel views from a single-view image of an object. However, maintaining consistency in geometry and colors for the generated images remains a challenge. To address this issue, we propose a synchronized multiview diffusion model that models the joint probability distribution of multiview images, enabling the generation of multiview-consistent images in a single reverse process. SyncDreamer synchronizes the intermediate states of all the generated images at every step of the reverse process through a 3D-aware feature attention mechanism that correlates the corresponding features across different views. Experiments show that SyncDreamer generates images with high consistency across different views, thus making it well-suited for various 3D generation tasks such as novel-view-synthesis, text-to-3D, and image-to-3D. Project page: https://liuyuan-pal.github.io/SyncDreamer/.

Weight initialization plays an important role in neural network training. Widely used initialization methods are proposed and evaluated for networks that are trained from scratch. However, the growing number of pretrained models now offers new opportunities for tackling this classical problem of weight initialization. In this work, we introduce weight selection, a method for initializing smaller models by selecting a subset of weights from a pretrained larger model. This enables the transfer of knowledge from pretrained weights to smaller models. Our experiments demonstrate that weight selection can significantly enhance the performance of small models and reduce their training time. Notably, it can also be used together with knowledge distillation. Weight selection offers a new approach to leverage the power of pretrained models in resource-constrained settings, and we hope it can be a useful tool for training small models in the large-model era.

Diffusion models have demonstrated great potential for generating diverse images. However, their performance often suffers from slow generation due to iterative denoising. Knowledge distillation has been recently proposed as a remedy which can reduce the number of inference steps to one or a few, without significant quality degradation. However, existing distillation methods either require significant amounts of offline computation for generating synthetic training data from the teacher model, or need to perform expensive online learning with the help of real data. In this work, we present a novel technique called BOOT, that overcomes these limitations with an efficient data-free distillation algorithm. The core idea is to learn a time-conditioned model that predicts the output of a pre-trained diffusion model teacher given any time-step. Such a model can be efficiently trained based on bootstrapping from two consecutive sampled steps. Furthermore, our method can be easily adapted to large-scale text-to-image diffusion models, which are challenging for previous methods given the fact that the training sets are often large and difficult to access. We demonstrate the effectiveness of our approach on several benchmark datasets in the DDIM setting, achieving comparable generation quality while being orders of magnitude faster than the diffusion teacher. The text-to-image results show that the proposed approach is able to handle highly complex distributions, shedding light on more efficient generative modeling.

Abstract The field of visual computing is rapidly advancing due to the emergence of generative artificial intelligence (AI), which unlocks unprecedented capabilities for the generation, editing, and reconstruction of images, videos, and 3D scenes. In these domains, diffusion models are the generative AI architecture of choice. Within the last year alone, the literature on diffusion‐based tools and applications has seen exponential growth and relevant papers are published across the computer graphics, computer vision, and AI communities with new works appearing daily on arXiv. This rapid growth of the field makes it difficult to keep up with all recent developments. The goal of this state‐of‐the‐art report (STAR) is to introduce the basic mathematical concepts of diffusion models, implementation details and design choices of the popular Stable Diffusion model, as well as overview important aspects of these generative AI tools, including personalization, conditioning, inversion, among others. Moreover, we give a comprehensive overview of the rapidly growing literature on diffusion‐based generation and editing, categorized by the type of generated medium, including 2D images, videos, 3D objects, locomotion, and 4D scenes. Finally, we discuss available datasets, metrics, open challenges, and social implications. This STAR provides an intuitive starting point to explore this exciting topic for researchers, artists, and practitioners alike.

We introduce a novel approach to learn geometries such as depth and surface normal from images while incorporating geometric context. The difficulty of reliably capturing geometric context in existing methods impedes their ability to accurately enforce the consistency between the different geometric properties, thereby leading to a bottleneck of geometric estimation quality. We therefore propose the Adaptive Surface Normal (ASN) constraint, a simple yet efficient method. Our approach extracts geometric context that encodes the geometric variations present in the input image and correlates depth estimation with geometric constraints. By dynamically determining reliable local geometry from randomly sampled candidates, we establish a surface normal constraint, where the validity of these candidates is evaluated using the geometric context. Furthermore, our normal estimation leverages the geometric context to prioritize regions that exhibit significant geometric variations, which makes the predicted normals accurately capture intricate and detailed geometric information. Through the integration of geometric context, our method unifies depth and surface normal estimations within a cohesive framework, which enables the generation of high-quality 3D geometry from images. We validate the superiority of our approach over state-of-the-art methods through extensive evaluations and comparisons on diverse indoor and outdoor datasets, showcasing its efficiency and robustness.

Apparel's significant role in human appearance underscores the importance of garment digitalization for digital human creation. Recent advances in 3D content creation are pivotal for digital human creation. Nonetheless, garment generation from text guidance is still nascent. We introduce a text-driven 3D garment generation framework, DressCode, which aims to democratize design for novices and offer immense potential in fashion design, virtual try-on, and digital human creation. We first introduce SewingGPT, a GPT-based architecture integrating cross-attention with text-conditioned embedding to generate sewing patterns with text guidance. We then tailor a pre-trained Stable Diffusion to generate tile-based Physically-based Rendering (PBR) textures for the garments. By leveraging a large language model, our framework generates CG-friendly garments through natural language interaction. It also facilitates pattern completion and texture editing, streamlining the design process through user-friendly interaction. This framework fosters innovation by allowing creators to freely experiment with designs and incorporate unique elements into their work. With comprehensive evaluations and comparisons with other state-of-the-art methods, our method showcases superior quality and alignment with input prompts. User studies further validate our high-quality rendering results, highlighting its practical utility and potential in production settings. Our project page is https://IHe-KaiI.github.io/DressCode/.

Reproducing realistic collective behaviors presents a captivating yet formidable challenge. Traditional rule-based methods rely on hand-crafted principles, limiting motion diversity and realism in generated collective behaviors. Recent imitation learning methods learn from data but often require ground-truth motion trajectories and struggle with authenticity, especially in high-density groups with erratic movements. In this paper, we present a scalable approach, Collective Behavior Imitation Learning (CBIL), for learning fish schooling behavior directly from videos , without relying on captured motion trajectories. Our method first leverages Video Representation Learning, in which a Masked Video AutoEncoder (MVAE) extracts implicit states from video inputs in a self-supervised manner. The MVAE effectively maps 2D observations to implicit states that are compact and expressive for following the imitation learning stage. Then, we propose a novel adversarial imitation learning method to effectively capture complex movements of the schools of fish, enabling efficient imitation of the distribution of motion patterns measured in the latent space. It also incorporates bio-inspired rewards alongside priors to regularize and stabilize training. Once trained, CBIL can be used for various animation tasks with the learned collective motion priors. We further show its effectiveness across different species. Finally, we demonstrate the application of our system in detecting abnormal fish behavior from in-the-wild videos.

We propose a new method for learning a generalized animatable neural human representation from a sparse set of multi-view imagery of multiple persons. The learned representation can be used to synthesize novel view images of an arbitrary person and further animate them with the user's pose control. While most existing methods can either generalize to new persons or synthesize animations with user control, none of them can achieve both at the same time. We attribute this accomplishment to the employment of a 3D proxy for a shared multi-person human model, and further the warping of the spaces of different poses to a shared canonical pose space, in which we learn a neural field and predict the person- and pose-dependent deformations, as well as appearance with the features extracted from input images. To cope with the complexity of the large variations in body shapes, poses, and clothing deformations, we design our neural human model with disentangled geometry and appearance. Furthermore, we utilize the image features both at the spatial point and on the surface points of the 3D proxy for predicting person- and pose-dependent properties. Experiments show that our method significantly outperforms the state-of-the-arts on both tasks.

This paper presents a novel grid-based NeRF called F2- NeRF (Fast-Free-NeRF) for novel view synthesis, which enables arbitrary input camera trajectories and only costs a few minutes for training. Existing fast grid-based NeRF training frameworks, like Instant-NGP, Plenoxels, DVGO, or TensoRF, are mainly designed for bounded scenes and rely on space warping to handle unbounded scenes. Existing two widely-used space-warping methods are only designed for the forward-facing trajectory or the 360° object-centric trajectory but cannot process arbitrary trajectories. In this paper, we delve deep into the mechanism of space warping to handle unbounded scenes. Based on our analysis, we further propose a novel space-warping method called perspective warping, which allows us to handle arbitrary trajectories in the grid-based NeRF framework. Extensive experiments demonstrate that F2-NeRF is able to use the same perspective warping to render high-quality images on two standard datasets and a new free trajectory dataset collected by us. Project page: totoro97.github.io/projects/f2-nerf.

We present a novel method, called NeuralUDF, for reconstructing surfaces with arbitrary topologies from 2D images via volume rendering. Recent advances in neural rendering based reconstruction have achieved compelling results. However, these methods are limited to objects with closed surfaces since they adopt Signed Distance Function (SDF) as surface representation which requires the target shape to be divided into inside and outside. In this paper, we propose to represent surfaces as the Unsigned Distance Function (UDF) and develop a new volume rendering scheme to learn the neural UDF representation. Specifically, a new density function that correlates the property of UDF with the volume rendering scheme is introduced for robust optimization of the UDF fields. Experiments on the DTU and DeepFashion3D datasets show that our method not only enables high-quality reconstruction of non-closed shapes with complex typologies, but also achieves comparable performance to the SDF based methods on the reconstruction of closed surfaces. Visit our project page at https://www.xxlong.site/NeuralUDF.

Egocentric 3D human pose estimation with a single head-mounted fisheye camera has recently attracted attention due to its numerous applications in virtual and augmented reality. Existing methods still struggle in challenging poses where the human body is highly occluded or is closely interacting with the scene. To address this issue, we propose a scene-aware egocentric pose estimation method that guides the prediction of the egocentric pose with scene constraints. To this end, we propose an egocentric depth estimation network to predict the scene depth map from a wide-view egocentric fisheye camera while mitigating the occlusion of the human body with a depth-inpainting network. Next, we propose a scene-aware pose estimation network that projects the 2D image features and estimated depth map of the scene into a voxel space and regresses the 3D pose with a V2V network. The voxel-based feature representation provides the direct geometric connection between 2D image features and scene geometry, and further facilitates the V2V network to constrain the predicted pose based on the estimated scene geometry. To enable the training of the aforementioned networks, we also generated a synthetic dataset, called EgoGTA, and an in-the-wild dataset based on EgoPW, called EgoPW-Scene. The experimental results of our new evaluation sequences show that the predicted 3D egocentric poses are accurate and physically plausible in terms of human-scene interaction, demonstrating that our method outperforms the state-of-the-art methods both quantitatively and qualitatively.

3D-aware image synthesis encompasses a variety of tasks, such as scene generation and novel view synthesis from images. Despite numerous task-specific methods, developing a comprehensive model remains challenging. In this paper, we present SSDNeRF, a unified approach that employs an expressive diffusion model to learn a generalizable prior of neural radiance fields (NeRF) from multi-view images of diverse objects. Previous studies have used two-stage approaches that rely on pretrained NeRFs as real data to train diffusion models. In contrast, we propose a new single-stage training paradigm with an end-to-end objective that jointly optimizes a NeRF auto-decoder and a latent diffusion model, enabling simultaneous 3D reconstruction and prior learning, even from sparsely available views. At test time, we can directly sample the diffusion prior for unconditional generation, or combine it with arbitrary observations of unseen objects for NeRF reconstruction. SSDNeRF demonstrates robust results comparable to or better than leading task-specific methods in unconditional generation and single/sparse-view 3D reconstruction.6

Recent methods for neural surface representation and rendering, for example NeuS [59], have demonstrated the remarkably high-quality reconstruction of static scenes. However, the training of NeuS takes an extremely long time (8 hours), which makes it almost impossible to apply them to dynamic scenes with thousands of frames. We propose a fast neural surface reconstruction approach, called NeuS2, which achieves two orders of magnitude improvement in terms of acceleration without compromising reconstruction quality. To accelerate the training process, we parameterize a neural surface representation by multi-resolution hash encodings and present a novel lightweight calculation of second-order derivatives tailored to our networks to leverage CUDA parallelism, achieving a factor two speed up. To further stabilize and expedite training, a progressive learning strategy is proposed to optimize multi-resolution hash encodings from coarse to fine. We extend our method for fast training of dynamic scenes, with a proposed incremental training strategy and a novel global transformation prediction component, which allow our method to handle challenging long sequences with large movements and deformations. Our experiments on various datasets demonstrate that NeuS2 significantly outperforms the state-of-the-arts in both surface reconstruction accuracy and training speed for both static and dynamic scenes. The code is available at our website: https://vcai.mpi-inf.mpg.de/projects/NeuS2/.

Novel view synthesis from a single image requires inferring occluded regions of objects and scenes whilst simultaneously maintaining semantic and physical consistency with the input. Existing approaches condition neural radiance fields (NeRF) on local image features, projecting points to the input image plane, and aggregating 2D features to perform volume rendering. However, under severe occlusion, this projection fails to resolve uncertainty, resulting in blurry renderings that lack details. In this work, we propose NerfDiff, which addresses this issue by distilling the knowledge of a 3D-aware conditional diffusion model (CDM) into NeRF through synthesizing and refining a set of virtual views at test-time. We further propose a novel NeRF-guided distillation algorithm that simultaneously generates 3D consistent virtual views from the CDM samples, and finetunes the NeRF based on the improved virtual views. Our approach significantly outperforms existing NeRF-based and geometry-free approaches on challenging datasets including ShapeNet, ABO, and Clevr3D.

Generating controllable and photorealistic digital human avatars is a long-standing and important problem in Vision and Graphics. Recent methods have shown great progress in terms of either photorealism or inference speed while the combination of the two desired properties still remains unsolved. To this end, we propose a novel method, called DELIFFAS, which parameterizes the appearance of the human as a surface light field that is attached to a controllable and deforming human mesh model. At the core, we represent the light field around the human with a deformable two-surface parameterization, which enables fast and accurate inference of the human appearance. This allows perceptual supervision on the full image compared to previous approaches that could only supervise individual pixels or small patches due to their slow runtime. Our carefully designed human representation and supervision strategy leads to state-of-the-art synthesis results and inference time. The video results and code are available at https://vcai.mpi-inf.mpg.de/projects/DELIFFAS.

Neural fields have achieved impressive advancements in view synthesis and scene reconstruction. However, editing these neural fields remains challenging due to the implicit encoding of geometry and texture information. In this paper, we propose DreamEditor, a novel framework that enables users to perform controlled editing of neural fields using text prompts. By representing scenes as mesh-based neural fields, DreamEditor allows localized editing within specific regions. DreamEditor utilizes the text encoder of a pretrained text-to-Image diffusion model to automatically identify the regions to be edited based on the semantics of the text prompts. Subsequently, DreamEditor optimizes the editing region and aligns its geometry and texture with the text prompts through score distillation sampling [Poole et al. 2022]. Extensive experiments have demonstrated that DreamEditor can accurately edit neural fields of real-world scenes according to the given text prompts while ensuring consistency in irrelevant areas. DreamEditor generates highly realistic textures and geometry, significantly surpassing previous works in both quantitative and qualitative evaluations.

As information exists in various modalities in real world, effective interaction and fusion among multimodal information plays a key role for the creation and perception of multimodal data in computer vision and deep learning research. With superb power in modeling the interaction among multimodal information, multimodal image synthesis and editing has become a hot research topic in recent years. Instead of providing explicit guidance for network training, multimodal guidance offers intuitive and flexible means for image synthesis and editing. On the other hand, this field is also facing several challenges in alignment of multimodal features, synthesis of high-resolution images, faithful evaluation metrics, etc. In this survey, we comprehensively contextualize the advance of the recent multimodal image synthesis and editing and formulate taxonomies according to data modalities and model types. We start with an introduction to different guidance modalities in image synthesis and editing, and then describe multimodal image synthesis and editing approaches extensively according to their model types. After that, we describe benchmark datasets and evaluation metrics as well as corresponding experimental results. Finally, we provide insights about the current research challenges and possible directions for future research.

We present a neural rendering-based method called NeRO for reconstructing the geometry and the BRDF of reflective objects from multiview images captured in an unknown environment. Multiview reconstruction of reflective objects is extremely challenging because specular reflections are view-dependent and thus violate the multiview consistency, which is the cornerstone for most multiview reconstruction methods. Recent neural rendering techniques can model the interaction between environment lights and the object surfaces to fit the view-dependent reflections, thus making it possible to reconstruct reflective objects from multiview images. However, accurately modeling environment lights in the neural rendering is intractable, especially when the geometry is unknown. Most existing neural rendering methods, which can model environment lights, only consider direct lights and rely on object masks to reconstruct objects with weak specular reflections. Therefore, these methods fail to reconstruct reflective objects, especially when the object mask is not available and the object is illuminated by indirect lights. We propose a two-step approach to tackle this problem. First, by applying the split-sum approximation and the integrated directional encoding to approximate the shading effects of both direct and indirect lights, we are able to accurately reconstruct the geometry of reflective objects without any object masks. Then, with the object geometry fixed, we use more accurate sampling to recover the environment lights and the BRDF of the object. Extensive experiments demonstrate that our method is capable of accurately reconstructing the geometry and the BRDF of reflective objects from only posed RGB images without knowing the environment lights and the object masks. Codes and datasets are available at https://github.com/liuyuan-pal/NeRO.

2D images are observations of the 3D physical world depicted with the geometry, material, and illumination components. Recovering these underlying intrinsic components from 2D images, also known as inverse rendering, usually requires a supervised setting with paired images collected from multiple viewpoints and lighting conditions, which is resource-demanding. In this work, we present GAN2X, a new method for unsupervised inverse rendering that only uses unpaired images for training. Unlike previous Shape-from-GAN approaches that mainly focus on 3D shapes, we take the first attempt to also recover non-Lambertian material properties by exploiting the pseudo paired data generated by a GAN. To achieve precise inverse rendering, we devise a specularity-aware neural surface representation that continuously models the geometry and material properties. A shading-based refinement technique is adopted to further distill information in the target image and recover more fine details. Experiments demonstrate that GAN2X can accurately decompose 2D images to 3D shape, albedo, and specular properties for different object categories, and achieves state-of-the-art performance for unsupervised single-view 3D face reconstruction. We also show its applications in downstream tasks including real image editing and lifting 2D GANs to decomposed 3D GANs.

We present a new neural representation, called Neural Ray (NeuRay), for the novel view synthesis task. Recent works construct radiance fields from image features of input views to render novel view images, which enables the generalization to new scenes. However, due to occlusions, a 3D point may be invisible to some input views. On such a 3D point, these generalization methods will include inconsistent image features from invisible views, which interfere with the radiance field construction. To solve this problem, we predict the visibility of 3D points to input views within our NeuRay representation. This visibility enables the radiance field construction to focus on visible image features, which significantly improves its rendering quality. Meanwhile, a novel consistency loss is proposed to refine the visibility in NeuRay when finetuning on a specific scene. Experiments demonstrate that our approach achieves state-of-the-art performance on the novel view synthesis task when generalizing to unseen scenes and outperforms perscene optimization methods after finetuning. Project page:https://liuyuan-pal.github.io/NeuRay/

Egocentric 3D human pose estimation with a single fisheye camera has drawn a significant amount of attention recently. However, existing methods struggle with pose estimation from in-the-wild images, because they can only be trained on synthetic data due to the unavailability of large-scale in-the-wild egocentric datasets. Furthermore, these methods easily fail when the body parts are occluded by or interacting with the surrounding scene. To address the shortage of in-the-wild data, we collect a large-scale in-the-wild egocentric dataset called Egocentric Poses in the Wild (EgoPW). This dataset is captured by a head-mounted fisheye camera and an auxiliary external camera, which provides an additional observation of the human body from a third-person perspective during training. We present a new egocentric pose estimation method, which can be trained on the new dataset with weak external supervision. Specifically, we first generate pseudo labels for the EgoPW dataset with a spatio-temporal optimization method by incorporating the external-view supervision. The pseudo labels are then used to train an egocentric pose estimation network. To facilitate the network training, we propose a novel learning strategy to supervise the egocentric features with the high-quality features extracted by a pretrained external-view pose estimation model. The experiments show that our method predicts accurate 3D poses from a single in-the-wild egocentric image and outperforms the state-of-the-art methods both quantitatively and qualitatively.

Detecting 3D landmarks on cone-beam computed tomography (CBCT) is crucial to assessing and quantifying the anatomical abnormalities in 3D cephalometric analysis. However, the current methods are time-consuming and suffer from large biases in landmark localization, leading to unreliable diagnosis results. In this work, we propose a novel Structure-Aware Long Short-Term Memory framework (SA-LSTM) for efficient and accurate 3D landmark detection. To reduce the computational burden, SA-LSTM is designed in two stages. It first locates the coarse landmarks via heatmap regression on a down-sampled CBCT volume and then progressively refines landmarks by attentive offset regression using multi-resolution cropped patches. To boost accuracy, SA-LSTM captures global-local dependence among the cropping patches via self-attention. Specifically, a novel graph attention module implicitly encodes the landmark's global structure to rationalize the predicted position. Moreover, a novel attention-gated module recursively filters irrelevant local features and maintains high-confident local predictions for aggregating the final result. Experiments conducted on an in-house dataset and a public dataset show that our method outperforms state-of-the-art methods, achieving 1.64 mm and 2.37 mm average errors, respectively. Furthermore, our method is very efficient, taking only 0.5 seconds for inferring the whole CBCT volume of resolution 768×768×576 .

High-fidelity reconstruction of dynamic fluids from sparse multiview RGB videos remains a formidable challenge, due to the complexity of the underlying physics as well as the severe occlusion and complex lighting in the captured data. Existing solutions either assume knowledge of obstacles and lighting, or only focus on simple fluid scenes without obstacles or complex lighting, and thus are unsuitable for real-world scenes with unknown lighting conditions or arbitrary obstacles. We present the first method to reconstruct dynamic fluid phenomena by leveraging the governing physics (ie, Navier -Stokes equations) in an end-to-end optimization from a mere set of sparse video frames without taking lighting conditions, geometry information, or boundary conditions as input. Our method provides a continuous spatio-temporal scene representation using neural networks as the ansatz of density and velocity solution functions for fluids as well as the radiance field for static objects. With a hybrid architecture that separates static and dynamic contents apart, fluid interactions with static obstacles are reconstructed for the first time without additional geometry input or human labeling. By augmenting time-varying neural radiance fields with physics-informed deep learning, our method benefits from the supervision of images and physical priors. Our progressively growing model with regularization further disentangles the density-color ambiguity in the radiance field, which allows for a more robust optimization from the given input of sparse views. A pretrained density-to-velocity fluid model is leveraged in addition as the data prior to avoid suboptimal velocity solutions which underestimate vorticity but trivially fulfill physical equations. Our method exhibits high-quality results with relaxed constraints and strong flexibility on a representative set of synthetic and real flow captures. Code and sample tests are at https://people.mpi-inf.mpg.de/~mchu/projects/PI-NeRF/.

Segmenting arbitrary 3D objects into constituent parts that are structurally meaningful is a fundamental problem encountered in a wide range of computer graphics applications. Existing methods for 3D shape segmentation suffer from complex geometry processing and heavy computation caused by using low-level features and fragmented segmentation results due to the lack of global consideration. We present an efficient method, called SEG-MAT, based on the medial axis transform (MAT) of the input shape. Specifically, with the rich geometrical and structural information encoded in the MAT, we are able to develop a simple and principled approach to effectively identify the various types of junctions between different parts of a 3D shape. Extensive evaluations and comparisons show that our method outperforms the state-of-the-art methods in terms of segmentation quality and is also one order of magnitude faster.

We introduce MulayCap, a novel human performance capture method using a monocular video camera without the need for pre-scanning. The method uses "multi-layer" representations for geometry reconstruction and texture rendering, respectively. For geometry reconstruction, we decompose the clothed human into multiple geometry layers, namely a body mesh layer and a garment piece layer. The key technique behind is a Garment-from-Video (GfV) method for optimizing the garment shape and reconstructing the dynamic cloth to fit the input video sequence, based on a cloth simulation model which is effectively solved with gradient descent. For texture rendering, we decompose each input image frame into a shading layer and an albedo layer, and propose a method for fusing a fixed albedo map and solving for detailed garment geometry using the shading layer. Compared with existing single view human performance capture systems, our "multi-layer" approach bypasses the tedious and time consuming scanning step for obtaining a human specific mesh template. Experimental results demonstrate that MulayCap produces realistic rendering of dynamically changing details that has not been achieved in any previous monocular video camera systems. Benefiting from its fully semantic modeling, MulayCap can be applied to various important editing applications, such as cloth editing, re-targeting, relighting, and AR applications.

Dense human pose estimation is the problem of learning dense correspondences between RGB images and the surfaces of human bodies, which finds various applications, such as human body reconstruction, human pose transfer, and human action recognition. Prior dense pose estimation methods are all based on Mask R-CNN framework and operate in a top-down manner of first attempting to identify a bounding box for each person and matching dense correspondences in each bounding box. Consequently, these methods lack robustness due to their critical dependence on the Mask R-CNN detection, and the runtime increases drastically as the number of persons in the image increases. We therefore propose a novel alternative method for solving the dense pose estimation problem, called Direct Dense Pose (DDP). DDP first predicts the instance mask and global IUV representation separately and then combines them together. We also propose a simple yet effective 2D temporal-smoothing scheme to alleviate the temporal jitters when dealing with video data. Experiments demonstrate that DDP overcomes the limitations of previous top-down baseline methods and achieves competitive accuracy. In addition, DDP is computationally more efficient than previous dense pose estimation methods, and it reduces jitters when applied to a video sequence, which is a problem plaguing the previous methods.

Generative adversarial networks achieve great performance in photorealistic image synthesis in various domains, including human images. However, they usually employ latent vectors that encode the sampled outputs globally. This does not allow convenient control of semantically relevant individual parts of the image, and cannot draw samples that only differ in partial aspects, such as clothing style. We address these limitations and present a generative model for images of dressed humans offering control over pose, local body part appearance and garment style. This is the first method to solve various aspects of human image generation, such as global appearance sampling, pose transfer, parts and garment transfer, and part sampling jointly in a unified framework. As our model encodes part-based latent appearance vectors in a normalized pose-independent space and warps them to different poses, it preserves body and clothing appearance under varying posture. Experiments show that our flexible and general generative method outperforms task-specific baselines for pose-conditioned image generation, pose transfer and part sampling in terms of realism and output resolution.

Motion coherence is an important clue for distinguishing true correspondences from false ones. Modeling motion coherence on sparse putative correspondences is challenging due to their sparsity and uneven distributions. Existing works on motion coherence are sensitive to parameter settings and have difficulty in dealing with complex motion patterns. In this paper, we introduce a network called Laplacian Motion Coherence Network (LMCNet) to learn motion coherence property for correspondence pruning. We propose a novel formulation of fitting coherent motions with a smooth function on a graph of correspondences and show that this formulation allows a closed-form solution by graph Laplacian. This closed-form solution enables us to design a differentiable layer in a learning framework to capture global motion coherence from putative correspondences. The global motion coherence is further combined with local coherence extracted by another local layer to robustly detect inlier correspondences. Experiments demonstrate that LMCNet has superior performances to the state of the art in relative camera pose estimation and correspondences pruning of dynamic scenes1.

We present a novel method for multi-view depth estimation from a single video, which is a critical task in various applications, such as perception, reconstruction and robot navigation. Although previous learning-based methods have demonstrated compelling results, most works estimate depth maps of individual video frames independently, without taking into consideration the strong geometric and temporal coherence among the frames. Moreover, current state-of-the-art (SOTA) models mostly adopt a fully 3D convolution network for cost regularization and therefore require high computational cost, thus limiting their deployment in real-world applications. Our method achieves temporally coherent depth estimation results by using a novel Epipolar Spatio-Temporal (EST) transformer to explicitly associate geometric and temporal correlation with multiple estimated depth maps. Furthermore, to reduce the computational cost, inspired by recent Mixture-of-Experts models, we design a compact hybrid network consisting of a 2D context-aware network and a 3D matching network which learn 2D context information and 3D disparity cues separately. Extensive experiments demonstrate that our method achieves higher accuracy in depth estimation and significant speedup than the SOTA methods.

We present a new pose transfer method for synthesizing a human animation from a single image of a person controlled by a sequence of body poses. Existing pose transfer methods exhibit significant visual artifacts when applying to a novel scene, resulting in temporal inconsistency and failures in preserving the identity and textures of the person. To address these limitations, we design a compositional neural network that predicts the silhouette, garment labels, and textures. Each modular network is explicitly dedicated to a subtask that can be learned from the synthetic data. At the inference time, we utilize the trained network to produce a unified representation of appearance and its labels in UV coordinates, which remains constant across poses. The unified representation provides an incomplete yet strong guidance to generating the appearance in response to the pose change. We use the trained network to complete the appearance and render it with the background. With these strategies, we are able to synthesize human animations that can preserve the identity and appearance of the person in a temporally coherent way without any fine-tuning of the network on the testing scene. Experiments show that our method outperforms the state-of-the-arts in terms of synthesis quality, temporal coherence, and generalization ability.

Egocentric 3D human pose estimation using a single fisheye camera has become popular recently as it allows capturing a wide range of daily activities in unconstrained environments, which is difficult for traditional outside-in motion capture with external cameras. However, existing methods have several limitations. A prominent problem is that the estimated poses lie in the local coordinate system of the fisheye camera, rather than in the world coordinate system, which is restrictive for many applications. Furthermore, these methods suffer from limited accuracy and temporal instability due to ambiguities caused by the monocular setup and the severe occlusion in a strongly distorted egocentric perspective. To tackle these limitations, we present a new method for egocentric global 3D body pose estimation using a single head-mounted fish-eye camera. To achieve accurate and temporally stable global poses, a spatio-temporal optimization is performed over a sequence of frames by minimizing heatmap reprojection errors and enforcing local and global body motion priors learned from a mocap dataset. Experimental results show that our approach outperforms state-of-the-art methods both quantitatively and qualitatively.

We present EgoRenderer, a system for rendering full-body neural avatars of a person captured by a wearable, egocentric fisheye camera that is mounted on a cap or a VR headset. Our system renders photorealistic novel views of the actor and her motion from arbitrary virtual camera locations. Rendering full-body avatars from such egocentric images come with unique challenges due to the top-down view and large distortions. We tackle these challenges by decomposing the rendering process into several steps, including texture synthesis, pose construction, and neural image translation. For texture synthesis, we propose Ego-DPNet, a neural network that infers dense correspondences between the input fisheye images and an underlying parametric body model, and to extract textures from egocentric inputs. In addition, to encode dynamic appearances, our approach also learns an implicit texture stack that captures detailed appearance variation across poses and viewpoints. For correct pose generation, we first estimate body pose from the egocentric view using a parametric model. We then synthesize an external free-viewpoint pose image by projecting the parametric model to the user-specified target viewpoint. We next combine the target pose image and the textures into a combined feature image, which is transformed into the output color image using a neural image translation network. Experimental evaluations show that EgoRenderer is capable of generating realistic free-viewpoint avatars of a person wearing an egocentric camera. Comparisons to several baselines demonstrate the advantages of our approach.

We present a novel method for single image depth estimation using surface normal constraints. Existing depth estimation methods either suffer from the lack of geometric constraints, or are limited to the difficulty of reliably capturing geometric context, which leads to a bottleneck of depth estimation quality. We therefore introduce a simple yet effective method, named Adaptive Surface Normal (ASN) constraint, to effectively correlate the depth estimation with geometric consistency. Our key idea is to adaptively determine the reliable local geometry from a set of randomly sampled candidates to derive surface normal constraint, for which we measure the consistency of the geometric contextual features. As a result, our method can faithfully reconstruct the 3D geometry and is robust to local shape variations, such as boundaries, sharp corners and noises. We conduct extensive evaluations and comparisons using public datasets. The experimental results demonstrate our method outperforms the state-of-the-art methods and has superior efficiency and robustness. Codes are available at: https://github.com/xxlong0/ASNDepth

Differentiable rendering has received increasing interest for image-based inverse problems. It can benefit traditional optimization-based solutions to inverse problems, but also allows for self-supervision of learning-based approaches for which training data with ground truth annotation is hard to obtain. However, existing differentiable renderers either do not model visibility of the light sources from the different points in the scene, responsible for shadows in the images, or are very slow which makes it difficult to train deep architectures over thousands of iterations. To this end, we propose an accurate yet efficient approach for differentiable visibility and soft shadow computation. Our approach is based on the spherical harmonics approximations of the scene illumination and visibility, where the occluding surface is approximated with spheres. This allows for a significantly more efficient shadow computation compared to methods based on ray tracing. As our formulation is differentiable, it can be used to solve inverse problems such as texture, illumination, rigid pose, and geometric deformation recovery from images using analysis-by-synthesis optimization.

We propose the first approach to synthesize the synchronous 3D conversational body and hand gestures, as well as 3D face and head animations, of a virtual character from speech input. Our algorithm uses a CNN architecture that leverages the inherent correlation between facial expression and hand gestures. Synthesis of conversational body gestures is a multi-modal problem since many similar gestures can plausibly accompany the same input speech. To synthesize plausible body gestures in this setting, we train a Generative Adversarial Network (GAN) based model that measures the plausibility of the generated sequences of 3D body motion when paired with the input audio features. We also contribute a new corpus that contains more than 33 hours of annotated data from in-the-wild videos of talking people. To this end, we apply state-of-the-art monocular approaches for 3D body and hand pose estimation as well as 3D face performance capture to the video corpus. In this way, we can train on orders of magnitude more data than previous algorithms that resort to complex in-studio motion capture solutions, and thereby train more expressive synthesis algorithms. Our experiments and user study show the state-of-the-art quality of our speech-synthesized full 3D character animations.

We present a novel neural surface reconstruction method, called NeuS, for reconstructing objects and scenes with high fidelity from 2D image inputs. Existing neural surface reconstruction approaches, such as DVR [Niemeyer et al., 2020] and IDR [Yariv et al., 2020], require foreground mask as supervision, easily get trapped in local minima, and therefore struggle with the reconstruction of objects with severe self-occlusion or thin structures. Meanwhile, recent neural methods for novel view synthesis, such as NeRF [Mildenhall et al., 2020] and its variants, use volume rendering to produce a neural scene representation with robustness of optimization, even for highly complex objects. However, extracting high-quality surfaces from this learned implicit representation is difficult because there are not sufficient surface constraints in the representation. In NeuS, we propose to represent a surface as the zero-level set of a signed distance function (SDF) and develop a new volume rendering method to train a neural SDF representation. We observe that the conventional volume rendering method causes inherent geometric errors (i.e. bias) for surface reconstruction, and therefore propose a new formulation that is free of bias in the first order of approximation, thus leading to more accurate surface reconstruction even without the mask supervision. Experiments on the DTU dataset and the BlendedMVS dataset show that NeuS outperforms the state-of-the-arts in high-quality surface reconstruction, especially for objects and scenes with complex structures and self-occlusion.

We propose a deep videorealistic 3D human character model displaying highly realistic shape, motion, and dynamic appearance learned in a new weakly supervised way from multi-view imagery. In contrast to previous work, our controllable 3D character displays dynamics, e.g., the swing of the skirt, dependent on skeletal body motion in an efficient data-driven way, without requiring complex physics simulation. Our character model also features a learned dynamic texture model that accounts for photo-realistic motion-dependent appearance details, as well as view-dependent lighting effects. During training, we do not need to resort to difficult dynamic 3D capture of the human; instead we can train our model entirely from multi-view video in a weakly supervised manner. To this end, we propose a parametric and differentiable character representation which allows us to model coarse and fine dynamic deformations, e.g., garment wrinkles, as explicit spacetime coherent mesh geometry that is augmented with high-quality dynamic textures dependent on motion and view point. As input to the model, only an arbitrary 3D skeleton motion is required, making it directly compatible with the established 3D animation pipeline. We use a novel graph convolutional network architecture to enable motion-dependent deformation learning of body and clothing, including dynamics, and a neural generative dynamic texture model creates corresponding dynamic texture maps. We show that by merely providing new skeletal motions, our model creates motion-dependent surface deformations, physically plausible dynamic clothing deformations, as well as video-realistic surface textures at a much higher level of detail than previous state of the art approaches, and even in real-time.

We propose Neural Actor (NA), a new method for high-quality synthesis of humans from arbitrary viewpoints and under arbitrary controllable poses. Our method is developed upon recent neural scene representation and rendering works which learn representations of geometry and appearance from only 2D images. While existing works demonstrated compelling rendering of static scenes and playback of dynamic scenes, photo-realistic reconstruction and rendering of humans with neural implicit methods, in particular under user-controlled novel poses, is still difficult. To address this problem, we utilize a coarse body model as a proxy to unwarp the surrounding 3D space into a canonical pose. A neural radiance field learns pose-dependent geometric deformations and pose- and view-dependent appearance effects in the canonical space from multi-view video input. To synthesize novel views of high-fidelity dynamic geometry and appearance, NA leverages 2D texture maps defined on the body model as latent variables for predicting residual deformations and the dynamic appearance. Experiments demonstrate that our method achieves better quality than the state-of-the-arts on playback as well as novel pose synthesis, and can even generalize well to new poses that starkly differ from the training poses. Furthermore, our method also supports shape control on the free-view synthesis of human actors.

Synthesizing realistic videos of humans using neural networks has been a popular alternative to the conventional graphics-based rendering pipeline due to its high efficiency. Existing works typically formulate this as an image-to-image translation problem in 2D screen space, which leads to artifacts such as over-smoothing, missing body parts, and temporal instability of fine-scale detail, such as pose-dependent wrinkles in the clothing. In this article, we propose a novel human video synthesis method that approaches these limiting factors by explicitly disentangling the learning of time-coherent fine-scale details from the embedding of the human in 2D screen space. More specifically, our method relies on the combination of two convolutional neural networks (CNNs). Given the pose information, the first CNN predicts a dynamic texture map that contains time-coherent high-frequency details, and the second CNN conditions the generation of the final video on the temporally coherent output of the first CNN. We demonstrate several applications of our approach, such as human reenactment and novel view synthesis from monocular video, where we show significant improvement over the state of the art both qualitatively and quantitatively.

Learning structures of 3D shapes is a fundamental problem in the field of computer graphics and geometry processing. We present a simple yet interpretable unsupervised method for learning a new structural representation in the form of 3D structure points. The 3D structure points produced by our method encode the shape structure intrinsically and exhibit semantic consistency across all the shape instances with similar structures. This is a challenging goal that has not fully been achieved by other methods. Specifically, our method takes a 3D point cloud as input and encodes it as a set of local features. The local features are then passed through a novel point integration module to produce a set of 3D structure points. The chamfer distance is used as reconstruction loss to ensure the structure points lie close to the input point cloud. Extensive experiments have shown that our method outperforms the state-of-the-art on the semantic shape correspondence task and achieves comparable performance with the state-of-the-art on the segmentation label transfer task. Moreover, the PCA based shape embedding built upon consistent structure points demonstrates good performance in preserving the shape structures. Code is available at https://github.com/NolenChen/3DStructurePoints.

Photo-realistic free-viewpoint rendering of real-world scenes using classical computer graphics techniques is challenging, because it requires the difficult step of capturing detailed appearance and geometry models. Recent studies have demonstrated promising results by learning scene representations that implicitly encodes both geometry and appearance without 3D supervision. However, existing approaches in practice often show blurry renderings caused by the limited network capacity or the difficulty in finding accurate intersections of camera rays with the scene geometry. Synthesizing high-resolution imagery from these representations often requires time-consuming optical ray marching. In this work, we introduce Neural Sparse Voxel Fields (NSVF), a new neural scene representation for fast and high-quality free-viewpoint rendering. The NSVF defines a series of voxel-bounded implicit fields organized in a sparse voxel octree to model local properties in each cell. We progressively learn the underlying voxel structures with a differentiable ray-marching operation from only a set of posed RGB images. With the sparse voxel octree structure, rendering novel views at inference time can be accelerated by skipping the voxels without relevant scene content. Our method is over 10 times faster than the state-of-the-art while achieving higher quality results. Furthermore, by utilizing an explicit sparse voxel representation, our method can be easily applied to scene editing and scene composition. we also demonstrate various kinds of challenging tasks, including multi-object learning, free-viewpoint rendering of a moving human, and large-scale scene rendering.

Thin structures, such as wire-frame sculptures, fences, cables, power lines, and tree branches, are common in the real world. It is extremely challenging to acquire their 3D digital models using traditional image-based or depth-based reconstruction methods, because thin structures often lack distinct point features and have severe self-occlusion. We propose the first approach that simultaneously estimates camera motion and reconstructs the geometry of complex 3D thin structures in high quality from a color video captured by a handheld camera. Specifically, we present a new curve-based approach to estimate accurate camera poses by establishing correspondences between featureless thin objects in the foreground in consecutive video frames, without requiring visual texture in the background scene to lock on. Enabled by this effective curve-based camera pose estimation strategy, we develop an iterative optimization method with tailored measures on geometry, topology as well as self-occlusion handling for reconstructing 3D thin structures. Extensive validations on a variety of thin structures show that our method achieves accurate camera pose estimation and faithful reconstruction of 3D thin structures with complex shape and topology at a level that has not been attained by other existing reconstruction methods.

3D deep learning performance depends on object representation and local feature extraction. In this work, we present MAT-Net, a neural network which captures local and global features from the Medial Axis Transform (MAT). Different from K-Nearest-Neighbor method which extracts local features by a fixed number of neighbors, our MAT-Net exploits effective modules Group-MAT and Edge-Net to process topological structure. Experimental results illustrate that MAT-Net demonstrates competitive or better performance on 3D shape recognition than state-of-the-art methods, and prove that MAT representation has excellent capacity in 3D deep learning, even in the case of low resolution.

We propose a method for generating video-realistic animations of real humans under user control. In contrast to conventional human character rendering, we do not require the availability of a production-quality photo-realistic three-dimensional (3D) model of the human but instead rely on a video sequence in conjunction with a (medium-quality) controllable 3D template model of the person. With that, our approach significantly reduces production cost compared to conventional rendering approaches based on production-quality 3D models and can also be used to realistically edit existing videos. Technically, this is achieved by training a neural network that translates simple synthetic images of a human character into realistic imagery. For training our networks, we first track the 3D motion of the person in the video using the template model and subsequently generate a synthetically rendered version of the video. These images are then used to train a conditional generative adversarial network that translates synthetic images of the 3D model into realistic imagery of the human. We evaluate our method for the reenactment of another person that is tracked to obtain the motion data, and show video results generated from artist-designed skeleton motion. Our results outperform the state of the art in learning-based human image synthesis.

We introduce C urve F usion , the first approach for high quality scanning of thin structures at interactive rates using a handheld RGBD camera. Thin filament-like structures are mathematically just 1D curves embedded in R 3 , and integration-based reconstruction works best when depth sequences (from the thin structure parts) are fused using the object's (unknown) curve skeleton. Thus, using the complementary but noisy color and depth channels, C urve F usion first automatically identifies point samples on potential thin structures and groups them into bundles , each being a group of a fixed number of aligned consecutive frames. Then, the algorithm extracts per-bundle skeleton curves using L 1 axes, and aligns and iteratively merges the L 1 segments from all the bundles to form the final complete curve skeleton. Thus, unlike previous methods, reconstruction happens via integration along a data-dependent fusion primitive , i.e., the extracted curve skeleton. We extensively evaluate C urve F usion on a range of challenging examples, different scanner and calibration settings, and present high fidelity thin structure reconstructions previously just not possible from raw RGBD sequences.

A new method is presented for producing photo collages that preserve content correlation of photos. We use deep learning techniques to find correlation among given photos to facilitate their embedding on the canvas, and develop an efficient combinatorial optimization technique to make correlated photos stay close to each other. To make efficient use of canvas space, our method first extracts salient regions of photos and packs only these salient regions. We allow the salient regions to have arbitrary shapes, therefore yielding informative, yet more compact collages than by other similar collage methods based on salient regions. We present extensive experimental results, user study results, and comparisons against the state-of-the-art methods to show the superiority of our method.

Objects created by connecting and bending wires are common in furniture design, metal sculpting, wire jewelry, etc. Reconstructing such objects with traditional depth and image based methods is extremely difficult due to their unique characteristics such as lack of features, thin elements, and severe self-occlusions. We present a novel image-based method that reconstructs a set of continuous 3D wires used to create such an object, where each wire is composed of an ordered set of 3D curve segments. Our method exploits two main observations: simplicity - wire objects are often created using only a small number of wires, and smoothness - each wire is primarily smoothly bent with sharp features appearing only at joints or isolated points. In light of these observations, we tackle the challenging image correspondence problem across featureless wires by first generating multiple candidate 3D curve segments and then solving a global selection problem that balances between image and smoothness cues to identify the correct 3D curves. Next, we recover a decomposition of such curves into a set of distinct and continuous wires by formulating a multiple traveling salesman problem , which finds smooth paths, i.e. , wires, connecting the curves. We demonstrate our method on a wide set of real examples with varying complexity and present high-fidelity results using only 3 images for each object. We provide the source code and data for our work in the project website.