We introduce X-Dyna, a novel zero-shot, diffusion-based pipeline for animating a single human image using facial expressions and body movements derived from a driving video, that generates realistic, context-aware dynamics for both the subject and the surrounding environment. Building on prior approaches centered on human pose control, X-Dyna addresses key shortcomings causing the loss of dynamic details, enhancing the lifelike qualities of human video animations. At the core of our approach is the Dynamics-Adapter, a lightweight module that effectively integrates reference appearance context into the spatial attentions of the diffusion backbone while preserving the capacity of motion modules in synthesizing fluid and intricate dynamic details. Beyond body pose control, we connect a local control module with our model to capture identity-disentangled facial expressions, facilitating accurate expression transfer for enhanced realism in animated scenes. Together, these components form a unified framework capable of learning physical human motion and natural scene dynamics from a diverse blend of human and scene videos. Comprehensive qualitative and quantitative evaluations demonstrate that X-Dyna outperforms state-of- the-art methods, creating highly lifelike and expressive animations. The code is available at https://github.com/bytedance/X-Dyna

Training large-scale neural networks in vision, and multimodal domains demands substantial memory resources, primarily due to the storage of optimizer states. While LoRA, a popular parameter-efficient method, reduces memory usage, it often suffers from suboptimal performance due to the constraints of low-rank updates. Low-rank gradient projection methods (e.g., GaLore, Flora) reduce optimizer memory by projecting gradients and moment estimates into low-rank spaces via singular value decomposition or random projection. However, they fail to account for inter-projection correlation, causing performance degradation, and their projection strategies often incur high computational costs. In this paper, we present COAP (COrrelation-Aware Gradient Projection), a memory-efficient method that minimizes computational overhead while maintaining training performance. Evaluated across various vision, language, and multimodal tasks, COAP outperforms existing methods in both training speed and model performance. For LLaMA-1B, it reduces optimizer memory by 61% with only 2% additional time cost, achieving the same PPL as AdamW. With 8-bit quantization, COAP cuts optimizer memory by 81% and achieves 4x speedup over GaLore for LLaVA-v1.5-7B fine-tuning, while delivering higher accuracy. https://byteaigc.github.io/coap/

The ability to synthesize personalized group photos and specify the positions of each identity offers immense creative potential. While such imagery can be visually appealing, it presents significant challenges for existing technologies. A persistent issue is identity (ID) leakage, where injected facial features interfere with one another, resulting in low face resemblance, incorrect positioning, and visual artifacts. Existing methods suffer from limitations such as the reliance on segmentation models, increased runtime, or a high probability of ID leakage. To address these challenges, we propose ID-Patch, a novel method that provides robust association between identities and 2D positions. Our approach generates an ID patch and ID embeddings from the same facial features: the ID patch is positioned on the conditional image for precise spatial control, while the ID embeddings integrate with text embeddings to ensure high resemblance. Experimental results demonstrate that ID-Patch surpasses baseline methods across metrics, such as face ID resemblance, ID-position association accuracy, and generation efficiency. Project Page is: https://byteaigc.github.io/ID-Patch/

We present X-Dancer, a novel zero-shot music-driven image animation pipeline that creates diverse and long-range lifelike human dance videos from a single static image. As its core, we introduce a unified transformer-diffusion framework, featuring an autoregressive transformer model that synthesize extended and music-synchronized token sequences for 2D body, head and hands poses, which then guide a diffusion model to produce coherent and realistic dance video frames. Unlike traditional methods that primarily generate human motion in 3D, X-Dancer addresses data limitations and enhances scalability by modeling a wide spectrum of 2D dance motions, capturing their nuanced alignment with musical beats through readily available monocular videos. To achieve this, we first build a spatially compositional token representation from 2D human pose labels associated with keypoint confidences, encoding both large articulated body movements (e.g., upper and lower body) and fine-grained motions (e.g., head and hands). We then design a music-to-motion transformer model that autoregressively generates music-aligned dance pose token sequences, incorporating global attention to both musical style and prior motion context. Finally we leverage a diffusion backbone to animate the reference image with these synthesized pose tokens through AdaIN, forming a fully differentiable end-to-end framework. Experimental results demonstrate that X-Dancer is able to produce both diverse and characterized dance videos, substantially outperforming state-of-the-art methods in term of diversity, expressiveness and realism. Code and model will be available for research purposes.

We propose X-NeMo, a novel zero-shot diffusion-based portrait animation pipeline that animates a static portrait using facial movements from a driving video of a different individual. Our work first identifies the root causes of the limitations in prior approaches, such as identity leakage and difficulty in capturing subtle and extreme expressions. To address these challenges, we introduce a fully end-to-end training framework that distills a 1D identity-agnostic latent motion descriptor from driving image, effectively controlling motion through cross-attention during image generation. Our implicit motion descriptor captures expressive facial motion in fine detail, learned end-to-end from a diverse video dataset without reliance on any pre-trained motion detectors. We further disentangle motion latents from identity cues with enhanced expressiveness by supervising their learning with a dual GAN decoder, alongside spatial and color augmentations. By embedding the driving motion into a 1D latent vector and controlling motion via cross-attention instead of additive spatial guidance, our design effectively eliminates the transmission of spatial-aligned structural clues from the driving condition to the diffusion backbone, substantially mitigating identity leakage. Extensive experiments demonstrate that X-NeMo surpasses state-of-the-art baselines, producing highly expressive animations with superior identity resemblance. Our code and models will be available for research.

We present X-UniMotion, a unified and expressive implicit latent representation for whole-body human motion, encompassing facial expressions, body poses, and hand gestures. Unlike prior motion transfer methods that rely on explicit skeletal poses and heuristic cross-identity adjustments, our approach encodes multi-granular human motion directly from a single image into a compact set of four disentangled latent tokens—one each for facial expression and body pose, and one per hand. These motion latents are both highly expressive and identity-agnostic, enabling high-fidelity, detailed cross-identity motion transfer across subjects with distinct identities, poses and spatial configurations. To achieve this, we introduce a self-supervised, end-to-end training framework that jointly learns the motion encoder and latent representation alongside a DiT-based video generative model, trained on large-scale video datasets spanning diverse human motions. Motion-identity disentanglement is enforced via 2D spatial and color augmentations, as well as synthetic 3D renderings of cross-identity subject pairs under shared poses. We further guide the learning of motion tokens using auxiliary decoders to promote fine-grained, semantically aligned, and normal-aware motion embeddings. Extensive experiments demonstrate that X-UniMotion outperforms state-of-the-art methods, producing highly expressive animations with superior motion expressiveness and identity preservation. Please refer to https://byteaigc.github.io/X-Unimotion/ for more information.

We present X-Actor, a novel audio-driven portrait animation framework that generates lifelike, emotionally expressive talking head videos from a single reference image and an input audio clip. Unlike prior methods that emphasize lip synchronization and short-range visual fidelity in constrained speaking scenarios, X-Actor enables actor-quality, long-form portrait performance—capturing nuanced, dynamically evolving emotions that flow coherently with the rhythm and content of speech. Central to our approach is a two-stage decoupled generation pipeline: an audio-conditioned autoregressive diffusion model that predicts expressive yet identity-agnostic facial motion latent tokens within a long temporal context window, followed by a diffusion-based video synthesis module that translates these motions into high-fidelity video animations. By operating in a compact facial motion latent space decoupled from visual and identity cues, our autoregressive diffusion model effectively captures long-range correlations between audio and facial dynamics through a diffusion-forcing training paradigm, enabling infinite-length emotionally-rich motion prediction without error accumulation. Extensive experiments demonstrate that X-Actor produces compelling, cinematic-style performances that go beyond standard talking head animations and achieves state-of-the-art results in long-range, audio-driven emotional portrait acting. Please refer to https://byteaigc.github.io/X-Actor/ for more results.

Generating emotional talking faces from a single portrait image remains a significant challenge. The simultaneous achievement of expressive emotional talking and accurate lip-sync is particularly difficult, as expressiveness is often compromised for lip-sync accuracy. Prevailing generative works usually struggle to juggle to generate subtle variations of emotional expression and lip-synchronized talking. To address these challenges, we suggest modeling the implicit and explicit correlations between audio and emotional talking faces with a unified framework. As human emotional expressions usually present subtle and implicit relations with speech audio, we propose incorporating audio and emotional style embeddings into the diffusion-based generation process, for realistic generation while concentrating on emotional expressions. We then propose lip-based explicit correlation learning to construct a strong mapping of audio to lip motions, assuring lip-audio synchronization. Furthermore, we deploy a video-to-video rendering module to transfer expressions and lip motions from a proxy 3D avatar to an arbitrary portrait. Both quantitatively and qualitatively, MagicTalk outperforms state-of-the-art methods in terms of expressiveness, lip-sync, and perceptual quality.

We present DiffPortrait3D, a conditional diffusion model that is capable of synthesizing 3D-consistent photo-realistic novel views from as few as a single in-the-wild portrait. Specifically, given a single RGB input, we aim to synthesize plausible but consistent facial details rendered from novel camera views with retained both identity and facial expression. In lieu of time-consuming optimization and fine-tuning, our zero-shot method generalizes well to arbitrary face portraits with unposed camera views, extreme facial expressions, and diverse artistic depictions. At its core, we leverage the generative prior of 2D diffusion models pre-trained on large-scale image datasets as our rendering backbone, while the denoising is guided with disentangled attentive control of appearance and camera pose. To achieve this, we first inject the appearance context from the reference image into the self-attention layers of the frozen UNets. The rendering view is then manipulated with a novel conditional control module that interprets the camera pose by watching a condition image of a crossed subject from the same view. Furthermore, we insert a trainable cross-view attention module to enhance view consistency, which is further strengthened with a novel 3D-aware noise generation process during inference. We demonstrate state-of-the-art results both qualitatively and quantitatively on our challenging in-the-wild and multi-view benchmarks.

Automatic detection of facial Action Units (AUs) allows for objective facial expression analysis. Due to the high cost of AU labeling and the limited size of existing benchmarks, previous AU detection methods tend to overfit the dataset, resulting in a significant performance loss when evaluated across corpora. To address this problem, we propose FG-Net for generalizable facial action unit detection. Specifically, FG-Net extracts feature maps from a Style-GAN2 model pre-trained on a large and diverse face image dataset. Then, these features are used to detect AUs with a Pyramid CNN Interpreter, making the training efficient and capturing essential local features. The proposed FG-Net achieves a strong generalization ability for heatmap-based AU detection thanks to the generalizable and semantic-rich features extracted from the pre-trained generative model. Extensive experiments are conducted to evaluate within- and cross-corpus AU detection with the widely-used DISFA and BP4D datasets. Compared with the state-of-the-art, the proposed method achieves superior cross-domain performance while maintaining competitive within-domain performance. In addition, FG-Net is dataefficient and achieves competitive performance even when trained on 1000 samples. Our code will be released at https://github.com/ihp-lab/FG-Net

Although substantial progress has been made in audiodriven talking video synthesis, there still remain two major difficulties: existing works 1) need a long sequence of training dataset (>1h) to synthesize co-speech gestures, which causes a significant limitation on their applicability; 2) usually fail to generate long sequences, or can only generate long sequences without enough diversity. To solve these challenges, we propose a Disentangled Recurrent Representation Learning framework to synthesize long diversified gesture sequences with a short training video of around 2 minutes. In our framework, we first make a disentangled latent space assumption to encourage unpaired audio and pose combinations, which results in diverse "one-to-many" mappings in pose generation. Next, we apply a recurrent inference module to feed back the last generation as initial guidance to the next phase, enhancing the long-term video generation of full continuity and diversity. Comprehensive experimental results verify that our model can generate realistic synchronized full-body talking videos with training data efficiency.

We introduce PICFormer, a novel framework for Pluralistic Image Completion using a transFormer based architecture, that achieves both high quality and diversity at a much faster inference speed. Our key contribution is to introduce a code-shared codebook learning using a restrictive CNN on small and non-overlapping receptive fields (RFs) for the local visible token representation. This results in a compact yet expressive discrete representation, facilitating efficient modeling of global visible context relations by the transformer. Unlike the prevailing autoregressive approaches, we proposed to sample all tokens simultaneously, leading to more than 100× faster inference speed. To enhance appearance consistency between visible and generated regions, we further propose a novel attention-aware layer (AAL), designed to better exploit distantly related high-frequency features. Through extensive experiments, we demonstrate that the PICFormer efficiently learns semantically-rich discrete codes, resulting in significantly improved image quality. Moreover, our diverse image completion framework surpasses State-of-the-Art methods on multiple image completion datasets.

Recent neural rendering methods have made great progress in generating photorealistic human avatars. However, these methods are generally conditioned only on low-dimensional driving signals (e.g., body poses), which are insufficient to encode the complete appearance of a clothed human. Hence they fail to generate faithful details. To address this problem, we exploit driving view images (e.g., in telepresence systems) as additional inputs. We propose a novel neural rendering pipeline, Hybrid Volumetric-Textural Rendering (HVTR++), which synthesizes 3D human avatars from arbitrary driving poses and views while staying faithful to appearance details efficiently and at high quality. First, we learn to encode the driving signals of pose and view image on a dense UV manifold of the human body surface and extract UV-aligned features, preserving the structure of a skeleton-based parametric model. To handle complicated motions (e.g., self-occlusions), we then leverage the UV-aligned features to construct a 3D volumetric representation based on a dynamic neural radiance field. While this allows us to represent 3D geometry with changing topology, volumetric rendering is computationally heavy. Hence we employ only a rough volumetric representation using a pose- and image-conditioned downsampled neural radiance field (PID-NeRF), which we can render efficiently at low resolutions. In addition, we learn 2D textural features that are fused with rendered volumetric features in image space. The key advantage of our approach is that we can then convert the fused features into a high-resolution, high-quality avatar by a fast GAN-based textural renderer. We demonstrate that hybrid rendering enables HVTR++ to handle complicated motions, render high-quality avatars under user-controlled poses/shapes, and most importantly, be efficient at inference time. Our experimental results also demonstrate state-of-the-art quantitative results.

Synthesis and reconstruction of 3D human head has gained increasing interests in computer vision and computer graphics recently. Existing state-of-the-art 3D generative adversarial networks (GANs) for 3D human head synthesis are either limited to near-frontal views or hard to preserve 3D consistency in large view angles. We propose PanoHead, the first 3D-aware generative model that enables high-quality view-consistent image synthesis of full heads in 360° with diverse appearance and detailed geometry using only in-the-wild unstructured images for training. At its core, we lift up the representation power of recent 3D GANs and bridge the data alignment gap when training from in-the-wild images with widely distributed views. Specifically, we propose a novel two-stage self-adaptive image alignment for robust 3D GAN training. We further introduce a tri-grid neural volume representation that effectively addresses front-face and back-head feature entanglement rooted in the widely-adopted tri-plane formulation. Our method instills prior knowledge of 2D image segmentation in adversarial learning of 3D neural scene structures, enabling compositable head synthesis in diverse backgrounds. Benefiting from these designs, our method significantly outperforms previous 3D GANs, generating high-quality 3D heads with accurate geometry and diverse appearances, even with long wavy and afro hairstyles, renderable from arbitrary poses. Furthermore, we show that our system can reconstruct full 3D heads from single input images for personalized realistic 3D avatars.

We present OmniAvatar, a novel geometry-guided 3D head synthesis model trained from in-the-wild unstructured images that is capable of synthesizing diverse identity-preserved 3D heads with compelling dynamic details under full disentangled control over camera poses, facial expressions, head shapes, articulated neck and jaw poses. To achieve such high level of disentangled control, we first explicitly define a novel semantic signed distance function (SDF) around a head geometry (FLAME) conditioned on the control parameters. This semantic SDF allows us to build a differentiable volumetric correspondence map from the observation space to a disentangled canonical space from all the control parameters. We then leverage the 3D-aware GAN framework (EG3D) to synthesize detailed shape and appearance of 3D full heads in the canonical space, followed by a volume rendering step guided by the volumetric correspondence map to output into the observation space. To ensure the control accuracy on the synthesized head shapes and expressions, we introduce a geometry prior loss to conform to head SDF and a control loss to conform to the expression code. Further, we enhance the temporal realism with dynamic details conditioned upon varying expressions and joint poses. Our model can synthesize more preferable identity-preserved 3D heads with compelling dynamic details compared to the state-of-the-art methods both qualitatively and quantitatively. We also provide an ablation study to justify many of our system design choices.

Stylized 3D avatars have become increasingly prominent in our modern life. Creating these avatars manually usually involves laborious selection and adjustment of continuous and discrete parameters and is time-consuming for average users. Self-supervised approaches to automatically create 3D avatars from user selfies promise high quality with little annotation cost but fall short in application to stylized avatars due to a large style domain gap. We propose a novel self-supervised learning framework to create high-quality stylized 3D avatars with a mix of continuous and discrete parameters. Our cascaded domain bridging framework first leverages a modified portrait stylization approach to translate input selfies into stylized avatar renderings as the targets for desired 3D avatars. Next, we find the best parameters of the avatars to match the stylized avatar renderings through a differentiable imitator we train to mimic the avatar graphics engine. To ensure we can effectively optimize the discrete parameters, we adopt a cascaded relaxation-and-search pipeline. We use a human preference study to evaluate how well our method preserves user identity compared to previous work as well as manual creation. Our results achieve much higher preference scores than previous work and close to those of manual creation. We also provide an ablation study to justify the design choices in our pipeline.

Portraiture as an art form has evolved from realistic depiction into a plethora of creative styles. While substantial progress has been made in automated stylization, generating high quality stylistic portraits is still a challenge, and even the recent popular Toonify suffers from several artifacts when used on real input images. Such StyleGAN-based methods have focused on finding the best latent inversion mapping for reconstructing input images; however, our key insight is that this does not lead to good generalization to different portrait styles. Hence we propose AgileGAN, a framework that can generate high quality stylistic portraits via inversion-consistent transfer learning. We introduce a novel hierarchical variational autoencoder to ensure the inverse mapped distribution conforms to the original latent Gaussian distribution, while augmenting the original space to a multi-resolution latent space so as to better encode different levels of detail. To better capture attribute-dependent stylization of facial features, we also present an attribute-aware generator and adopt an early stopping strategy to avoid overfitting small training datasets. Our approach provides greater agility in creating high quality and high resolution (1024×1024) portrait stylization models, requiring only a limited number of style exemplars (~100) and short training time (~1 hour). We collected several style datasets for evaluation including 3D cartoons, comics, oil paintings and celebrities. We show that we can achieve superior portrait stylization quality to previous state-of-the-art methods, with comparisons done qualitatively, quantitatively and through a perceptual user study. We also demonstrate two applications of our method, image editing and motion retargeting.

We present a deep generative scene modeling technique for indoor environments. Our goal is to train a generative model using a feed-forward neural network that maps a prior distribution (e.g., a normal distribution) to the distribution of primary objects in indoor scenes. We introduce a 3D object arrangement representation that models the locations and orientations of objects, based on their size and shape attributes. Moreover, our scene representation is applicable for 3D objects with different multiplicities (repetition counts), selected from a database. We show a principled way to train this model by combining discriminative losses for both a 3D object arrangement representation and a 2D image-based representation. We demonstrate the effectiveness of our scene representation and the network training method on benchmark datasets. We also show the applications of this generative model in scene interpolation and scene completion.

Estimating the relative rigid pose between two RGB-D scans of the same underlying environment is a fundamental problem in computer vision, robotics, and computer graphics. Most existing approaches allow only limited maximum relative pose changes since they require considerable overlap between the input scans. We introduce a novel approach that extends the scope to extreme relative poses, with little or even no overlap between the input scans. The key idea is to infer more complete scene information about the underlying environment and match on the completed scans. In particular, instead of only performing scene completion from each individual scan, our approach alternates between relative pose estimation and scene completion. This allows us to perform scene completion by utilizing information from both input scans at late iterations, resulting in better results for both scene completion and relative pose estimation. Experimental results on benchmark datasets show that our approach leads to considerable improvements over state-of-the-art approaches for relative pose estimation. In particular, our approach provides encouraging relative pose estimates even between non-overlapping scans.

Existing video-based human pose estimation methods extensively apply large networks onto every frame in the video to localize body joints, which suffer high computational cost and hardly meet the low-latency requirement in realistic applications. To address this issue, we propose a novel Dynamic Kernel Distillation (DKD) model to facilitate small networks for estimating human poses in videos, thus significantly lifting the efficiency. In particular, DKD introduces a light-weight distillator to online distill pose kernels via leveraging temporal cues from the previous frame in a one-shot feed-forward manner. Then, DKD simplifies body joint localization into a matching procedure between the pose kernels and the current frame, which can be efficiently computed via simple convolution. In this way, DKD fast transfers pose knowledge from one frame to provide compact guidance for body joint localization in the following frame, which enables utilization of small networks in video-based pose estimation. To facilitate the training process, DKD exploits a temporally adversarial training strategy that introduces a temporal discriminator to help generate temporally coherent pose kernels and pose estimation results within a long range. Experiments on Penn Action and Sub-JHMDB benchmarks demonstrate outperforming efficiency of DKD, specifically, 10x flops reduction and 2x speedup over previous best model, and its state-of-the-art accuracy.

We propose a novel approach to performing fine-grained 3D manipulation of image content via a convolutional neural network, which we call the Transformable Bottleneck Network (TBN). It applies given spatial transformations directly to a volumetric bottleneck within our encoder-bottleneck-decoder architecture. Multi-view supervision encourages the network to learn to spatially disentangle the feature space within the bottleneck. The resulting spatial structure can be manipulated with arbitrary spatial transformations. We demonstrate the efficacy of TBNs for novel view synthesis, achieving state-of-the-art results on a challenging benchmark. We demonstrate that the bottlenecks produced by networks trained for this task contain meaningful spatial structure that allows us to intuitively perform a variety of image manipulations in 3D, well beyond the rigid transformations seen during training. These manipulations include non-uniform scaling, non-rigid warping, and combining content from different images. Finally, we extract explicit 3D structure from the bottleneck, performing impressive 3D reconstruction from a single input image.

Despite the popularity of real-time monocular face tracking systems in many successful applications, one overlooked problem with these systems is rigid instability. It occurs when the input facial motion can be explained by either head pose change or facial expression change, creating ambiguities that often lead to jittery and unstable rigid head poses under large expressions. Existing rigid stabilization methods either employ a heavy anatomically-motivated approach that are unsuitable for real-time applications, or utilize heuristic-based rules that can be problematic under certain expressions. We propose the first rigid stabilization method for real-time monocular face tracking using a dynamic rigidity prior learned from realistic datasets. The prior is defined on a region-based face model and provides dynamic region-based adaptivity for rigid pose optimization during real-time performance. We introduce an effective offline training scheme to learn the dynamic rigidity prior by optimizing the convergence of the rigid pose optimization to the ground-truth poses in the training data. Our real-time face tracking system is an optimization framework that alternates between rigid pose optimization and expression optimization. To ensure tracking accuracy, we combine both robust, drift-free facial landmarks and dense optical flow into the optimization objectives. We evaluate our system extensively against state-of-the-art monocular face tracking systems and achieve significant improvement in tracking accuracy on the high-quality face tracking benchmark. Our system can improve facial-performance-based applications such as facial animation retargeting and virtual face makeup with accurate expression and stable pose. We further validate the dynamic rigidity prior by comparing it against other variants on the tracking accuracy.

Recent advances in single-view 3D hair digitization have made the creation of high-quality CG characters scalable and accessible to end-users, enabling new forms of personalized VR and gaming experiences. To handle the complexity and variety of hair structures, most cutting-edge techniques rely on the successful retrieval of a particular hair model from a comprehensive hair database. Not only are the aforementioned data-driven methods storage intensive, but they are also prone to failure for highly unconstrained input images, complicated hairstyles, and failed face detection. Instead of using a large collection of 3D hair models directly, we propose to represent the manifold of 3D hairstyles implicitly through a compact latent space of a volumetric variational autoencoder (VAE). This deep neural network is trained with volumetric orientation field representations of 3D hair models and can synthesize new hairstyles from a compressed code. To enable end-to-end 3D hair inference, we train an additional embedding network to predict the code in the VAE latent space from any input image. Strand-level hairstyles can then be generated from the predicted volumetric representation. Our fully automatic framework does not require any ad-hoc face fitting, intermediate classification and segmentation, or hairstyle database retrieval. Our hair synthesis approach is significantly more robust and can handle a much wider variation of hairstyles than state-of-the-art data-driven hair modeling techniques with challenging inputs, including photos that are low-resolution, overexposured, or contain extreme head poses. The storage requirements are minimal and a 3D hair model can be produced from an image in a second. Our evaluations also show that successful reconstructions are possible from highly stylized cartoon images, non-human subjects, and pictures taken from behind a person. Our approach is particularly well suited for continuous and plausible hair interpolation between very different hairstyles.

Performance-driven character animation enables users to create expressive results by performing the desired motion of the character with their face and/or body. However, for cutout animations where continuous motion is combined with discrete artwork replacements, supporting a performance-driven workflow has some unique requirements. To trigger the appropriate artwork replacements, the system must reliably detect a wide range of customized facial expressions that are challenging for existing recognition methods, which focus on a few canonical expressions (e.g., angry, disgusted, scared, happy, sad and surprised). Also, real usage scenarios require the system to work in realtime with minimal training. In this paper, we propose a novel customized expression recognition technique that meets all of these requirements. We first use a set of handcrafted features combining geometric features derived from facial landmarks and patch-based appearance features through group sparsity-based facial component learning. To improve discrimination and generalization, these handcrafted features are integrated into a custom-designed Deep Convolutional Neural Network (CNN) structure trained from publicly available facial expression datasets. The combined features are fed to an online ensemble of SVMs designed for the few training sample problem and performs in realtime. To improve temporal coherence, we also apply a Hidden Markov Model (HMM) to smooth the recognition results. Our system achieves state-of-the-art performance on canonical expression datasets and promising results on our collected dataset of customized expressions.

We propose a novel system to reconstruct a high-quality hair depth map from a single portrait photo with minimal user input. We achieve this by combining depth cues such as occlusions, silhouettes, and shading, with a novel 3D helical structural prior for hair reconstruction. We fit a parametric morphable face model to the input photo and construct a base shape in the face, hair and body regions using occlusion and silhouette constraints. We then estimate the normals in the hair region via a Shape-from-Shading-based optimization that uses the lighting inferred from the face model and enforces an adaptive albedo prior that models the typical color and occlusion variations of hair. We introduce a 3D helical hair prior that captures the geometric structure of hair, and show that it can be robustly recovered from the input photo in an automatic manner. Our system combines the base shape, the normals estimated by Shape from Shading, and the 3D helical hair prior to reconstruct high-quality 3D hair models. Our single-image reconstruction closely matches the results of a state-of-the-art multi-view stereo applied on a multi-view stereo dataset. Our technique can reconstruct a wide variety of hairstyles ranging from short to long and from straight to messy, and we demonstrate the use of our 3D hair models for high-quality portrait relighting, novel view synthesis and 3D-printed portrait reliefs.

Human hair presents highly convoluted structures and spans an extraordinarily wide range of hairstyles, which is essential for the digitization of compelling virtual avatars but also one of the most challenging to create. Cutting-edge hair modeling techniques typically rely on expensive capture devices and significant manual labor. We introduce a novel data-driven framework that can digitize complete and highly complex 3D hairstyles from a single-view photograph. We first construct a large database of manually crafted hair models from several online repositories. Given a reference photo of the target hairstyle and a few user strokes as guidance, we automatically search for multiple best matching examples from the database and combine them consistently into a single hairstyle to form the large-scale structure of the hair model. We then synthesize the final hair strands by jointly optimizing for the projected 2D similarity to the reference photo, the physical plausibility of each strand, as well as the local orientation coherency between neighboring strands. We demonstrate the effectiveness and robustness of our method on a variety of hairstyles and challenging images, and compare our system with state-of-the-art hair modeling algorithms.

As the 3D printing technology starts to revolutionize our daily life and the manufacturing industries, a critical problem is about to e-merge: how can we find an automatic way to divide a 3D model into multiple printable pieces, so as to save the space, to reduce the printing time, or to make a large model printable by small printers. In this paper, we present a systematic study on the partitioning and packing of 3D models under the multi-phase level set framework. We first construct analysis tools to evaluate the qualities of a partitioning using six metrics: stress load, surface details, interface area, packed size, printability, and assembling. Based on this analysis, we then formulate level set methods to improve the qualities of the partitioning according to the metrics. These methods are integrated into an automatic system, which repetitively and locally optimizes the partitioning. Given the optimized partitioning result, we further provide a container structure modeling algorithm to facilitate the packing process of the printed pieces. Our experiment shows that the system can generate quality partitioning of various 3D models for space saving and fast production purposes.

We introduce a data-driven hair capture framework based on example strands generated through hair simulation. Our method can robustly reconstruct faithful 3D hair models from unprocessed input point clouds with large amounts of outliers. Current state-of-the-art techniques use geometrically-inspired heuristics to derive global hair strand structures, which can yield implausible hair strands for hairstyles involving large occlusions, multiple layers, or wisps of varying lengths. We address this problem using a voting-based fitting algorithm to discover structurally plausible configurations among the locally grown hair segments from a database of simulated examples. To generate these examples, we exhaustively sample the simulation configurations within the feasible parameter space constrained by the current input hairstyle. The number of necessary simulations can be further reduced by leveraging symmetry and constrained initial conditions. The final hairstyle can then be structurally represented by a limited number of examples. To handle constrained hairstyles such as a ponytail of which realistic simulations are more difficult, we allow the user to sketch a few strokes to generate strand examples through an intuitive interface. Our approach focuses on robustness and generality. Since our method is structurally plausible by construction, we ensure an improved control during hair digitization and avoid implausible hair synthesis for a wide range of hairstyles.

From fishtail to princess braids, these intricately woven structures define an important and popular class of hairstyle, frequently used for digital characters in computer graphics. In addition to the challenges created by the infinite range of styles, existing modeling and capture techniques are particularly constrained by the geometric and topological complexities. We propose a data-driven method to automatically reconstruct braided hairstyles from input data obtained from a single consumer RGB-D camera. Our approach covers the large variation of repetitive braid structures using a family of compact procedural braid models. From these models, we produce a database of braid patches and use a robust random sampling approach for data fitting. We then recover the input braid structures using a multi-label optimization algorithm and synthesize the intertwining hair strands of the braids. We demonstrate that a minimal capture equipment is sufficient to effectively capture a wide range of complex braids with distinct shapes and structures.

We propose a novel algorithm to reconstruct the 3D geometry of human hairs in wide-baseline setups using strand-based refinement. The hair strands are first extracted in each 2D view, and projected onto the 3D visual hull for initialization. The 3D positions of these strands are then refined by optimizing an objective function that takes into account cross-view hair orientation consistency, the visual hull constraint and smoothness constraints defined at the strand, wisp and global levels. Based on the refined strands, the algorithm can reconstruct an approximate hair surface: experiments with synthetic hair models achieve an accuracy of ~3mm. We also show real-world examples to demonstrate the capability to capture full-head hair styles as well as hair in motion with as few as 8 cameras.

We develop an automatic pipeline that allows ordinary users to capture complete and fully textured 3D models of themselves in minutes, using only a single Kinect sensor, in the uncontrolled lighting environment of their own home. Our method requires neither a turntable nor a second operator, and is robust to the small deformations and changes of pose that inevitably arise during scanning. After the users rotate themselves with the same pose for a few scans from different views, our system stitches together the captured scans using multi-view non-rigid registration, and produces watertight final models. To ensure consistent texturing, we recover the underlying albedo from each scanned texture and generate seamless global textures using Poisson blending. Despite the minimal requirements we place on the hardware and users, our method is suitable for full body capture of challenging scenes that cannot be handled well using previous methods, such as those involving loose clothing, complex poses, and props.

Existing hair capture systems fail to produce strands that reflect the structures of real-world hairstyles. We introduce a system that reconstructs coherent and plausible wisps aware of the underlying hair structures from a set of still images without any special lighting. Our system first discovers locally coherent wisp structures in the reconstructed point cloud and the 3D orientation field, and then uses a novel graph data structure to reason about both the connectivity and directions of the local wisp structures in a global optimization. The wisps are then completed and used to synthesize hair strands which are robust against occlusion and missing data and plausible for animation and simulation. We show reconstruction results for a variety of complex hairstyles including curly, wispy, and messy hair.

Reconstructing realistic 3D hair geometry is challenging due to omnipresent occlusions, complex discontinuities and specular appearance. To address these challenges, we propose a multi-view hair reconstruction algorithm based on orientation fields with structure-aware aggregation. Our key insight is that while hair's color appearance is view-dependent, the response to oriented filters that captures the local hair orientation is more stable. We apply the structure-aware aggregation to the MRF matching energy to enforce the structural continuities implied from the local hair orientations. Multiple depth maps from the MRF optimization are then fused into a globally consistent hair geometry with a template refinement procedure. Compared to the state-of-the-art color-based methods, our method faithfully reconstructs detailed hair structures. We demonstrate the results for a number of hair styles, ranging from straight to curly, and show that our framework is suitable for capturing hair in motion.

We present a novel shape completion technique for creating temporally coherent watertight surfaces from real-time captured dynamic performances. Because of occlusions and low surface albedo, scanned mesh sequences typically exhibit large holes that persist over extended periods of time. Most conventional dynamic shape reconstruction techniques rely on template models or assume slow deformations in the input data. Our framework sidesteps these requirements and directly initializes shape completion with topology derived from the visual hull. To seal the holes with patches that are consistent with the subject's motion, we first minimize surface bending energies in each frame to ensure smooth transitions across hole boundaries. Temporally coherent dynamics of surface patches are obtained by unwarping all frames within a time window using accurate interframe correspondences. Aggregated surface samples are then filtered with a temporal visibility kernel that maximizes the use of nonoccluded surfaces. A key benefit of our shape completion strategy is that it does not rely on long-range correspondences or a template model. Consequently, our method does not suffer error accumulation typically introduced by noise, large deformations, and drastic topological changes. We illustrate the effectiveness of our method on several high-resolution scans of human performances captured with a state-of-the-art multiview 3D acquisition system.

3D printing technology is rapidly maturing and becoming ubiquitous. One of the remaining obstacles to wide-scale adoption is that the object to be printed must fit into the working volume of the 3D printer. We propose a framework, called Chopper, to decompose a large 3D object into smaller parts so that each part fits into the printing volume. These parts can then be assembled to form the original object. We formulate a number of desirable criteria for the partition, including assemblability, having few components, unobtrusiveness of the seams, and structural soundness. Chopper optimizes these criteria and generates a partition either automatically or with user guidance. Our prototype outputs the final decomposed parts with customized connectors on the interfaces. We demonstrate the effectiveness of Chopper on a variety of non-trivial real-world objects.

Abstract We present a novel approach for computing and solving the Poisson equation over the surface of a mesh. As in previous approaches, we define the Laplace‐Beltrami operator by considering the derivatives of functions defined on the mesh. However, in this work, we explore a choice of functions that is decoupled from the tessellation. Specifically, we use basis functions (second‐order tensor‐product B‐splines) defined over 3D space, and then restrict them to the surface. We show that in addition to being invariant to mesh topology, this definition of the Laplace‐Beltrami operator allows a natural multiresolution structure on the function space that is independent of the mesh structure, enabling the use of a simple multigrid implementation for solving the Poisson equation.