Point cloud salient object detection has attracted the attention of researchers in recent years. Since existing works do not fully utilize the geometry context of 3D objects, blurry boundaries are generated when segmenting objects with complex backgrounds. In this paper, we propose a geometry-aware 3D salient object detection network that explicitly clusters points into superpoints to enhance the geometric boundaries of objects, thereby segmenting complete objects with clear boundaries. Specifically, we first propose a simple yet effective superpoint partition module to cluster points into superpoints. In order to improve the quality of superpoints, we present a point cloud class-agnostic loss to learn discriminative point features for clustering superpoints from the object. After obtaining superpoints, we then propose a geometry enhancement module that utilizes superpoint-point attention to aggregate geometric information into point features for predicting the salient map of the object with clear boundaries. Extensive experiments show that our method achieves new state-of-the-art performance on the PCSOD dataset.

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.

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.

Reasoning stands as a cornerstone of intelligence, enabling the synthesis of existing knowledge to solve complex problems. Despite remarkable progress, existing reasoning benchmarks often fail to rigorously evaluate the nuanced reasoning capabilities required for complex, real-world problemsolving, particularly in multi-disciplinary and multimodal contexts. In this paper, we introduce a graduate-level, multi-disciplinary, EnglishChinese benchmark, dubbed as Reasoning Bench (RBench), for assessing the reasoning capability of both language and multimodal models. RBench spans 1,094 questions across 108 subjects for language model evaluation and 665 questions across 83 subjects for multimodal model testing. These questions are meticulously curated to ensure rigorous difficulty calibration, subject balance, and cross-linguistic alignment, enabling the assessment to be an Olympiad-level multidisciplinary benchmark. We evaluate many models such as o1, GPT-4o, DeepSeek-R1, etc. Experimental results indicate that advanced models perform poorly on complex reasoning, especially multimodal reasoning. Even the top-performing model OpenAI o1 achieves only 53.2% accuracy on our multimodal evaluation. Data and code are made publicly available athttps://evalmodels.github.io/rbench/

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.

Masked autoencoders (MAEs) have recently achieved great success in computer vision. They can automatically extract representations from unlabeled data and improve the performance of various downstream tasks. However, training an MAE model requires substantial resources, which limits their accessibility to many academic institutions: often laboratories in universities lack the necessary resources. This issue significantly hinders the development of this field. In this paper, we propose FastMAE, an efficient MAE approach. Inspired by the idea of offline tokenizers in natural language processing, FastMAE presents a novel way to build an offline vision tokenizer, which can provide high-level semantics in an efficient way. Benefiting from the offline tokenizer, FastMAE becomes an efficient vision learner. Our experiments demonstrate that FastMAE can achieve 83.6% accuracy with ViT-B in only 18.8 h on 8 NVIDIA Tesla-V100 GPUs, which is 31.3× faster than the original MAE, providing a resource friendly baseline for the computer vision community. Moreover, it also achieves comparable performance to state-of-the-art methods. We hope our research will attract more people to engage in MAE-related research and that we can advance its development together.

Denoising diffusion models have demonstrated tremendous success in modeling data distributions and synthesizing high-quality samples. In the 2D image domain, they have become the state-of-the-art and are capable of generating photo-realistic images with high controllability. More recently, researchers have begun to explore how to utilize diffusion models to generate 3D data, as doing so has more potential in real-world applications. This requires careful design choices in two key ways: identifying a suitable 3D representation and determining how to apply the diffusion process. In this survey, we provide the first comprehensive review of diffusion models for manipulating 3D content, including 3D generation, reconstruction, and 3D-aware image synthesis. We classify existing methods into three major categories: 2D space diffusion with pretrained models, 2D space diffusion without pretrained models, and 3D space diffusion. We also summarize popular datasets used for 3D generation with diffusion models. Along with this survey, we maintain a repository https://github.com/cwchenwang/awesome-3d-diffusion to track the latest relevant papers and codebases. Finally, we pose current challenges for diffusion models for 3D generation, and suggest future research directions.

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 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.

Accurately estimating the 3D pose and shape is an essential step towards understanding animal behavior, and can potentially benefit many downstream applications, such as wildlife conservation. However, research in this area is held back by the lack of a comprehensive and diverse dataset with high-quality 3D pose and shape annotations. In this paper, we propose Animal3D, the first comprehensive dataset for mammal animal 3D pose and shape estimation. Animal3D consists of 3379 images collected from 40 mammal species, high-quality annotations of 26 key-points, and importantly the pose and shape parameters of the SMAL [50] model. All annotations were labeled and checked manually in a multi-stage process to ensure highest quality results. Based on the Animal3D dataset, we benchmark representative shape and pose estimation models at: (1) supervised learning from only the Animal3D data, (2) synthetic to real transfer from synthetically generated images, and (3) fine-tuning human pose and shape estimation models. Our experimental results demonstrate that predicting the 3D shape and pose of animals across species remains a very challenging task, despite significant advances in human pose estimation. Our results further demonstrate that synthetic pre-training is a viable strategy to boost the model performance. Overall, Animal3D opens new directions for facilitating future research in animal 3D pose and shape estimation, and is publicly available.

Neural Radiance Fields (NeRFs) have demonstrated impressive performance in vision and graphics tasks, such as novel view synthesis and immersive reality. However, the shape-radiance ambiguity of radiance fields remains a challenge, especially in the sparse viewpoints setting. Recent work resorts to integrating depth priors into outdoor NeRF training to alleviate the issue. However, the criteria for selecting depth priors and the relative merits of different priors have not been thoroughly investigated. Moreover, the relative merits of selecting different approaches to use the depth priors is also an unexplored problem. In this paper, we provide a comprehensive study and evaluation of employing depth priors to outdoor neural radiance fields, covering common depth sensing technologies and most application ways. Specifically, we conduct extensive experiments with two representative NeRF methods equipped with four commonly-used depth priors and different depth usages on two widely used outdoor datasets. Our experimental results reveal several interesting findings that can potentially benefit practitioners and researchers in training their NeRF models with depth priors. Project page: https://cwchenwang.github.io/outdoor-nerf-depth

Achieving an immersive experience enabling users to explore virtual environments with six degrees of freedom (6DoF) is essential for various applications such as virtual reality (VR). Wide-baseline panoramas are commonly used in these applications to reduce network bandwidth and storage requirements. However, synthesizing novel views from these panoramas remains a key challenge. Although existing neural radiance field methods can produce photorealistic views under narrow-baseline and dense image captures, they tend to overfit the training views when dealing with wide-baseline panoramas due to the difficulty in learning accurate geometry from sparse $360^{\circ}$ views. To address this problem, we propose PanoGRF, Generalizable Spherical Radiance Fields for Wide-baseline Panoramas, which construct spherical radiance fields incorporating $360^{\circ}$ scene priors. Unlike generalizable radiance fields trained on perspective images, PanoGRF avoids the information loss from panorama-to-perspective conversion and directly aggregates geometry and appearance features of 3D sample points from each panoramic view based on spherical projection. Moreover, as some regions of the panorama are only visible from one view while invisible from others under wide baseline settings, PanoGRF incorporates $360^{\circ}$ monocular depth priors into spherical depth estimation to improve the geometry features. Experimental results on multiple panoramic datasets demonstrate that PanoGRF significantly outperforms state-of-the-art generalizable view synthesis methods for wide-baseline panoramas (e.g., OmniSyn) and perspective images (e.g., IBRNet, NeuRay).

With the emergence of neural radiance fields (NeRFs), view synthesis quality has reached an unprecedented level. Compared to traditional mesh-based assets, this volumetric representation is more powerful in expressing scene geometry but inevitably suffers from high rendering costs and can hardly be involved in further processes like editing, posing significant difficulties in combination with the existing graphics pipeline. In this paper, we present a hybrid volume-mesh representation, VMesh, which depicts an object with a textured mesh along with an auxiliary sparse volume. VMesh retains the advantages of mesh-based assets, such as efficient rendering and compact storage, while also incorporating the ability to represent subtle geometric structures provided by the volumetric counterpart. VMesh can be obtained from multi-view images of an object and renders at 2K 60FPS on common consumer devices with high fidelity, unleashing new opportunities for real-time immersive applications.

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.

Neural Radiance Fields (NeRF) achieve photo-realistic view synthesis with densely captured input images. However, the geometry of NeRF is extremely under-constrained given sparse views, resulting in significant degradation of novel view synthesis quality. Inspired by self-supervised depth estimation methods, we propose StructNeRF, a solution to novel view synthesis for indoor scenes with sparse inputs. StructNeRF leverages the structural hints naturally embedded in multi-view inputs to handle the unconstrained geometry issue in NeRF. Specifically, it tackles the texture and non-texture regions respectively: a patch-based multi-view consistent photometric loss is proposed to constrain the geometry of textured regions; for non-textured ones, we explicitly restrict them to be 3D consistent planes. Through the dense self-supervised depth constraints, our method improves both the geometry and the view synthesis performance of NeRF without any additional training on external data. Extensive experiments on several real-world datasets demonstrate that StructNeRF shows superior or comparable performance compared to state-of-the-art methods (e.g. NeRF, DSNeRF, RegNeRF, Dense Depth Priors, MonoSDF, etc.) for indoor scenes with sparse inputs both quantitatively and qualitatively.

Automatic generation of fonts can greatly facilitate the font design process, and provide prototypes where designers can draw inspiration from. Existing generation methods are mainly built upon rasterized glyph images to utilize the successful convolutional architecture, but ignore the vector nature of glyph shapes. We present an implicit representation, modeling each glyph as shape primitives enclosed by several quadratic curves. This structured implicit representation is shown to be better suited for glyph modeling, and enables rendering glyph images at arbitrary high resolutions. Our representation gives high-quality glyph reconstruction and interpolation results, and performs well on the challenging one-shot font style transfer task comparing to other alternatives both qualitatively and quantitatively.

Head tracking in head-mounted displays (HMDs) enables users to explore a 360-degree virtual scene with free head movements. However, for seated use of HMDs such as users sitting on a chair or a couch, physically turning around 360-degree is not possible. Redirection techniques decouple tracked physical motion and virtual motion, allowing users to explore virtual environments with more flexibility. In seated situations with only head movements available, the difference of stimulus might cause the detection thresholds of rotation gains to differ from that of redirected walking. Therefore we present an experiment with a two-alternative forced-choice (2AFC) design to compare the thresholds for seated and standing situations. Results indicate that users are unable to discriminate rotation gains between 0.89 and 1.28, a smaller range compared to the standing condition. We further treated head amplification as an interaction technique and found that a gain of 2.5, though not a hard threshold, was near the largest gain that users consider applicable. Overall, our work aims to better understand human perception of rotation gains in seated VR and the results provide guidance for future design choices of its applications.

Learning an empirically effective model with generalization using limited data is a challenging task for deep neural networks. In this paper, we propose a novel learning framework called Purified Learning to exploit task-irrelevant features extracted from task-irrelevant labels when training models on small-scale datasets. Particularly, we purify feature representations by using the expression of task-irrelevant information, thus facilitating the learning process of classification. Our work is built on solid theoretical analysis and extensive experiments, which demonstrate the effectiveness of Purified Learning. According to the theory we proved, Purified Learning is model-agnostic and doesn't have any restrictions on the model needed, so it can be combined with any existing deep neural networks with ease to achieve better performance.

We present NeRF-SR, a solution for high-resolution (HR) novel view synthesis with mostly low-resolution (LR) inputs. Our method is built upon Neural Radiance Fields (NeRF) that predicts per-point density and color with a multi-layer perceptron. While producing images at arbitrary scales, NeRF struggles with resolutions that go beyond observed images. Our key insight is that NeRF benefits from 3D consistency, which means an observed pixel absorbs information from nearby views. We first exploit it by a super-sampling strategy that shoots multiple rays at each image pixel, which further enforces multi-view constraint at a sub-pixel level. Then, we show that NeRF-SR can further boost the performance of super-sampling by a refinement network that leverages the estimated depth at hand to hallucinate details from related patches on only one HR reference image. Experiment results demonstrate that NeRF-SR generates high-quality results for novel view synthesis at HR on both synthetic and real-world datasets without any external information. Project page: https://cwchenwang.github.io/NeRF-SR

We investigated how to incorporate implicit touch pressure, finger pressure applied to a touch surface during typing, to improve text entry performance via statistical decoding. We focused on one-handed touch-typing on indirect interface as an example scenario. We first collected typing data on a pressure-sensitive touchpad, and analyzed users' typing behavior such as touch point distribution, key-to-finger mappings, and pressure images. Our investigation revealed distinct pressure patterns for different keys. Based on the findings, we performed a series of simulations to iteratively optimize the statistical decoding algorithm. Our investigation led to a Markov-Bayesian decoder incorporating pressure image data into decoding. It improved the top-1 accuracy from 53% to 74% over a naive Bayesian decoder. We then implemented PalmBoard, a text entry method that implemented the Markov-Bayesian decoder and effectively supported one-handed touch-typing on indirect interfaces. A user study showed participants achieved an average speed of 32.8 WPM with 0.6% error rate. Expert typists could achieve 40.2 WPM with 30 minutes of practice. Overall, our investigation showed that incorporating implicit touch pressure is effective in improving text entry decoding.