Xun Cao

Xinya Ji, Hang Zhou, Kaisiyuan Wang et al.

Although significant progress has been made to audio-driven talking face generation, existing methods either neglect facial emotion or cannot be applied to arbitrary subjects. In this paper, we propose the Emotion-Aware Motion Model (EAMM) to generate one-shot emotional talking faces by involving an emotion source video. Specifically, we first propose an Audio2Facial-Dynamics module, which renders talking faces from audio-driven unsupervised zero- and first-order key-points motion. Then through exploring the motion model's properties, we further propose an Implicit Emotion Displacement Learner to represent emotion-related facial dynamics as linearly additive displacements to the previously acquired motion representations. Comprehensive experiments demonstrate that by incorporating the results from both modules, our method can generate satisfactory talking face results on arbitrary subjects with realistic emotion patterns.

Kailai Zhou, Yibo Wang, Tao Lv et al.

We endeavor on a rarely explored task named Insubstantial Object Detection (IOD), which aims to localize the object with following characteristics: (1) amorphous shape with indistinct boundary; (2) similarity to surroundings; (3) absence in color. Accordingly, it is far more challenging to distinguish insubstantial objects in a single static frame and the collaborative representation of spatial and temporal information is crucial. Thus, we construct an IOD-Video dataset comprised of 600 videos (141,017 frames) covering various distances, sizes, visibility, and scenes captured by different spectral ranges. In addition, we develop a spatio-temporal aggregation framework for IOD, in which different backbones are deployed and a spatio-temporal aggregation loss (STAloss) is elaborately designed to leverage the consistency along the time axis. Experiments conducted on IOD-Video dataset demonstrate that spatio-temporal aggregation can significantly improve the performance of IOD. We hope our work will attract further researches into this valuable yet challenging task. The code will be available at: \url{https://github.com/CalayZhou/IOD-Video}.

Tencent Hunyuan Team, Ao Liu, Botong Zhou et al. · tencent-ai

As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model. It synergistically combines Mamba's long-sequence processing efficiency with Transformer's superior contextual understanding. Hunyuan-TurboS features an adaptive long-short chain-of-thought (CoT) mechanism, dynamically switching between rapid responses for simple queries and deep "thinking" modes for complex problems, optimizing computational resources. Architecturally, this 56B activated (560B total) parameter model employs 128 layers (Mamba2, Attention, FFN) with an innovative AMF/MF block pattern. Faster Mamba2 ensures linear complexity, Grouped-Query Attention minimizes KV cache, and FFNs use an MoE structure. Pre-trained on 16T high-quality tokens, it supports a 256K context length and is the first industry-deployed large-scale Mamba model. Our comprehensive post-training strategy enhances capabilities via Supervised Fine-Tuning (3M instructions), a novel Adaptive Long-short CoT Fusion method, Multi-round Deliberation Learning for iterative improvement, and a two-stage Large-scale Reinforcement Learning process targeting STEM and general instruction-following. Evaluations show strong performance: overall top 7 rank on LMSYS Chatbot Arena with a score of 1356, outperforming leading models like Gemini-2.0-Flash-001 (1352) and o4-mini-2025-04-16 (1345). TurboS also achieves an average of 77.9% across 23 automated benchmarks. Hunyuan-TurboS balances high performance and efficiency, offering substantial capabilities at lower inference costs than many reasoning models, establishing a new paradigm for efficient large-scale pre-trained models.

Longwei Guo, Hao Zhu, Yuanxun Lu et al.

We propose a robust and accurate non-parametric method for single-view 3D face reconstruction (SVFR). While tremendous efforts have been devoted to parametric SVFR, a visible gap still lies between the result 3D shape and the ground truth. We believe there are two major obstacles: 1) the representation of the parametric model is limited to a certain face database; 2) 2D images and 3D shapes in the fitted datasets are distinctly misaligned. To resolve these issues, a large-scale pseudo 2D\&3D dataset is created by first rendering the detailed 3D faces, then swapping the face in the wild images with the rendered face. These pseudo 2D&3D pairs are created from publicly available datasets which eliminate the gaps between 2D and 3D data while covering diverse appearances, poses, scenes, and illumination. We further propose a non-parametric scheme to learn a well-generalized SVFR model from the created dataset, and the proposed hierarchical signed distance function turns out to be effective in predicting middle-scale and small-scale 3D facial geometry. Our model outperforms previous methods on FaceScape-wild/lab and MICC benchmarks and is well generalized to various appearances, poses, expressions, and in-the-wild environments. The code is released at http://github.com/zhuhao-nju/rafare .

Yuanxun Lu, Jingyang Zhang, Shiwei Li et al.

Recent advances in generative AI have unveiled significant potential for the creation of 3D content. However, current methods either apply a pre-trained 2D diffusion model with the time-consuming score distillation sampling (SDS), or a direct 3D diffusion model trained on limited 3D data losing generation diversity. In this work, we approach the problem by employing a multi-view 2.5D diffusion fine-tuned from a pre-trained 2D diffusion model. The multi-view 2.5D diffusion directly models the structural distribution of 3D data, while still maintaining the strong generalization ability of the original 2D diffusion model, filling the gap between 2D diffusion-based and direct 3D diffusion-based methods for 3D content generation. During inference, multi-view normal maps are generated using the 2.5D diffusion, and a novel differentiable rasterization scheme is introduced to fuse the almost consistent multi-view normal maps into a consistent 3D model. We further design a normal-conditioned multi-view image generation module for fast appearance generation given the 3D geometry. Our method is a one-pass diffusion process and does not require any SDS optimization as post-processing. We demonstrate through extensive experiments that, our direct 2.5D generation with the specially-designed fusion scheme can achieve diverse, mode-seeking-free, and high-fidelity 3D content generation in only 10 seconds. Project page: https://nju-3dv.github.io/projects/direct25.

Hao Zhu, Fengyi Liu, Qi Zhang et al.

The use of Implicit Neural Representation (INR) through a hash-table has demonstrated impressive effectiveness and efficiency in characterizing intricate signals. However, current state-of-the-art methods exhibit insufficient regularization, often yielding unreliable and noisy results during interpolations. We find that this issue stems from broken gradient flow between input coordinates and indexed hash-keys, where the chain rule attempts to model discrete hash-keys, rather than the continuous coordinates. To tackle this concern, we introduce RHINO, in which a continuous analytical function is incorporated to facilitate regularization by connecting the input coordinate and the network additionally without modifying the architecture of current hash-based INRs. This connection ensures a seamless backpropagation of gradients from the network's output back to the input coordinates, thereby enhancing regularization. Our experimental results not only showcase the broadened regularization capability across different hash-based INRs like DINER and Instant NGP, but also across a variety of tasks such as image fitting, representation of signed distance functions, and optimization of 5D static / 6D dynamic neural radiance fields. Notably, RHINO outperforms current state-of-the-art techniques in both quality and speed, affirming its superiority.

Yiyu Zhuang, Qi Zhang, Xuan Wang et al.

Recent advances in implicit neural representation have demonstrated the ability to recover detailed geometry and material from multi-view images. However, the use of simplified lighting models such as environment maps to represent non-distant illumination, or using a network to fit indirect light modeling without a solid basis, can lead to an undesirable decomposition between lighting and material. To address this, we propose a fully differentiable framework named neural ambient illumination (NeAI) that uses Neural Radiance Fields (NeRF) as a lighting model to handle complex lighting in a physically based way. Together with integral lobe encoding for roughness-adaptive specular lobe and leveraging the pre-convoluted background for accurate decomposition, the proposed method represents a significant step towards integrating physically based rendering into the NeRF representation. The experiments demonstrate the superior performance of novel-view rendering compared to previous works, and the capability to re-render objects under arbitrary NeRF-style environments opens up exciting possibilities for bridging the gap between virtual and real-world scenes. The project and supplementary materials are available at https://yiyuzhuang.github.io/NeAI/.

Tao Lv, Hao Ye, Quan Yuan et al.

We demonstrate a compact, cost-effective snapshot spectral imaging system named Aperture Diffraction Imaging Spectrometer (ADIS), which consists only of an imaging lens with an ultra-thin orthogonal aperture mask and a mosaic filter sensor, requiring no additional physical footprint compared to common RGB cameras. Then we introduce a new optical design that each point in the object space is multiplexed to discrete encoding locations on the mosaic filter sensor by diffraction-based spatial-spectral projection engineering generated from the orthogonal mask. The orthogonal projection is uniformly accepted to obtain a weakly calibration-dependent data form to enhance modulation robustness. Meanwhile, the Cascade Shift-Shuffle Spectral Transformer (CSST) with strong perception of the diffraction degeneration is designed to solve a sparsity-constrained inverse problem, realizing the volume reconstruction from 2D measurements with Large amount of aliasing. Our system is evaluated by elaborating the imaging optical theory and reconstruction algorithm with demonstrating the experimental imaging under a single exposure. Ultimately, we achieve the sub-super-pixel spatial resolution and high spectral resolution imaging. The code will be available at: https://github.com/Krito-ex/CSST.

Jian Gao, Chun Gu, Youtian Lin et al.

In this paper, we present a novel differentiable point-based rendering framework to achieve photo-realistic relighting. To make the reconstructed scene relightable, we enhance vanilla 3D Gaussians by associating extra properties, including normal vectors, BRDF parameters, and incident lighting from various directions. From a collection of multi-view images, the 3D scene is optimized through 3D Gaussian Splatting while BRDF and lighting are decomposed by physically based differentiable rendering. To produce plausible shadow effects in photo-realistic relighting, we introduce an innovative point-based ray tracing with the bounding volume hierarchies for efficient visibility pre-computation. Extensive experiments demonstrate our improved BRDF estimation, novel view synthesis and relighting results compared to state-of-the-art approaches. The proposed framework showcases the potential to revolutionize the mesh-based graphics pipeline with a point-based pipeline enabling editing, tracing, and relighting.

Kailai Zhou, Lijing Cai, Yibo Wang et al.

The integration of miniaturized spectrometers into mobile devices offers new avenues for image quality enhancement and facilitates novel downstream tasks. However, the broader application of spectral sensors in mobile photography is hindered by the inherent complexity of spectral images and the constraints of spectral imaging capabilities. To overcome these challenges, we propose a joint RGB-Spectral decomposition model guided enhancement framework, which consists of two steps: joint decomposition and prior-guided enhancement. Firstly, we leverage the complementarity between RGB and Low-resolution Multi-Spectral Images (Lr-MSI) to predict shading, reflectance, and material semantic priors. Subsequently, these priors are seamlessly integrated into the established HDRNet to promote dynamic range enhancement, color mapping, and grid expert learning, respectively. Additionally, we construct a high-quality Mobile-Spec dataset to support our research, and our experiments validate the effectiveness of Lr-MSI in the tone enhancement task. This work aims to establish a solid foundation for advancing spectral vision in mobile photography. The code is available at \url{https://github.com/CalayZhou/JDM-HDRNet}.

Hao Zhu, Shaowen Xie, Zhen Liu et al.

Implicit neural representation (INR) characterizes the attributes of a signal as a function of corresponding coordinates which emerges as a sharp weapon for solving inverse problems. However, the expressive power of INR is limited by the spectral bias in the network training. In this paper, we find that such a frequency-related problem could be greatly solved by re-arranging the coordinates of the input signal, for which we propose the disorder-invariant implicit neural representation (DINER) by augmenting a hash-table to a traditional INR backbone. Given discrete signals sharing the same histogram of attributes and different arrangement orders, the hash-table could project the coordinates into the same distribution for which the mapped signal can be better modeled using the subsequent INR network, leading to significantly alleviated spectral bias. Furthermore, the expressive power of the DINER is determined by the width of the hash-table. Different width corresponds to different geometrical elements in the attribute space, \textit{e.g.}, 1D curve, 2D curved-plane and 3D curved-volume when the width is set as $1$, $2$ and $3$, respectively. More covered areas of the geometrical elements result in stronger expressive power. Experiments not only reveal the generalization of the DINER for different INR backbones (MLP vs. SIREN) and various tasks (image/video representation, phase retrieval, refractive index recovery, and neural radiance field optimization) but also show the superiority over the state-of-the-art algorithms both in quality and speed. \textit{Project page:} \url{https://ezio77.github.io/DINER-website/}

Shaowen Xie, Hao Zhu, Zhen Liu et al.

Implicit neural representation (INR) characterizes the attributes of a signal as a function of corresponding coordinates which emerges as a sharp weapon for solving inverse problems. However, the capacity of INR is limited by the spectral bias in the network training. In this paper, we find that such a frequency-related problem could be largely solved by re-arranging the coordinates of the input signal, for which we propose the disorder-invariant implicit neural representation (DINER) by augmenting a hash-table to a traditional INR backbone. Given discrete signals sharing the same histogram of attributes and different arrangement orders, the hash-table could project the coordinates into the same distribution for which the mapped signal can be better modeled using the subsequent INR network, leading to significantly alleviated spectral bias. Experiments not only reveal the generalization of the DINER for different INR backbones (MLP vs. SIREN) and various tasks (image/video representation, phase retrieval, and refractive index recovery) but also show the superiority over the state-of-the-art algorithms both in quality and speed.

Tao Yan, Maoqi Zhang, Sen Wan et al.

Electroencephalography (EEG) analysis extracts critical information from brain signals, which has provided fundamental support for various applications, including brain-disease diagnosis and brain-computer interface. However, the real-time processing of large-scale EEG signals at high energy efficiency has placed great challenges for electronic processors on edge computing devices. Here, we propose the EEG opto-processor based on diffractive photonic computing units (DPUs) to effectively process the extracranial and intracranial EEG signals and perform epileptic seizure detection. The signals of EEG channels within a second-time window are optically encoded as inputs to the constructed diffractive neural networks for classification, which monitors the brain state to determine whether it's the symptom of an epileptic seizure or not. We developed both the free-space and integrated DPUs as edge computing systems and demonstrated their applications for real-time epileptic seizure detection with the benchmark datasets, i.e., the CHB-MIT extracranial EEG dataset and Epilepsy-iEEG-Multicenter intracranial EEG dataset, at high computing performance. Along with the channel selection mechanism, both the numerical evaluations and experimental results validated the sufficient high classification accuracies of the proposed opto-processors for supervising the clinical diagnosis. Our work opens up a new research direction of utilizing photonic computing techniques for processing large-scale EEG signals in promoting its broader applications.

Bin Jiang, Zhihao Li, M. Salman Asif et al.

The event camera's low power consumption and ability to capture microsecond brightness changes make it attractive for various computer vision tasks. Existing event representation methods typically convert events into frames, voxel grids, or spikes for deep neural networks (DNNs). However, these approaches often sacrifice temporal granularity or require specialized devices for processing. This work introduces a novel token-based event representation, where each event is considered a fundamental processing unit termed an event-token. This approach preserves the sequence's intricate spatiotemporal attributes at the event level. Moreover, we propose a Three-way Attention mechanism in the Event Transformer Block (ETB) to collaboratively construct temporal and spatial correlations between events. We compare our proposed token-based event representation extensively with other prevalent methods for object classification and optical flow estimation. The experimental results showcase its competitive performance while demanding minimal computational resources on standard devices. Our code is publicly accessible at \url{https://github.com/NJUVISION/EventTransformer}.

Yifei Zeng, Yuanxun Lu, Xinya Ji et al.

We introduce AvatarBooth, a novel method for generating high-quality 3D avatars using text prompts or specific images. Unlike previous approaches that can only synthesize avatars based on simple text descriptions, our method enables the creation of personalized avatars from casually captured face or body images, while still supporting text-based model generation and editing. Our key contribution is the precise avatar generation control by using dual fine-tuned diffusion models separately for the human face and body. This enables us to capture intricate details of facial appearance, clothing, and accessories, resulting in highly realistic avatar generations. Furthermore, we introduce pose-consistent constraint to the optimization process to enhance the multi-view consistency of synthesized head images from the diffusion model and thus eliminate interference from uncontrolled human poses. In addition, we present a multi-resolution rendering strategy that facilitates coarse-to-fine supervision of 3D avatar generation, thereby enhancing the performance of the proposed system. The resulting avatar model can be further edited using additional text descriptions and driven by motion sequences. Experiments show that AvatarBooth outperforms previous text-to-3D methods in terms of rendering and geometric quality from either text prompts or specific images. Please check our project website at https://zeng-yifei.github.io/avatarbooth_page/.

Zhicheng Cai, Xiaohan Ding, Qiu Shen et al.

We propose Re-parameterized Refocusing Convolution (RefConv) as a replacement for regular convolutional layers, which is a plug-and-play module to improve the performance without any inference costs. Specifically, given a pre-trained model, RefConv applies a trainable Refocusing Transformation to the basis kernels inherited from the pre-trained model to establish connections among the parameters. For example, a depth-wise RefConv can relate the parameters of a specific channel of convolution kernel to the parameters of the other kernel, i.e., make them refocus on the other parts of the model they have never attended to, rather than focus on the input features only. From another perspective, RefConv augments the priors of existing model structures by utilizing the representations encoded in the pre-trained parameters as the priors and refocusing on them to learn novel representations, thus further enhancing the representational capacity of the pre-trained model. Experimental results validated that RefConv can improve multiple CNN-based models by a clear margin on image classification (up to 1.47% higher top-1 accuracy on ImageNet), object detection and semantic segmentation without introducing any extra inference costs or altering the original model structure. Further studies demonstrated that RefConv can reduce the redundancy of channels and smooth the loss landscape, which explains its effectiveness.

Yiyu Zhuang, Qi Zhang, Ying Feng et al.

We present LoD-NeuS, an efficient neural representation for high-frequency geometry detail recovery and anti-aliased novel view rendering. Drawing inspiration from voxel-based representations with the level of detail (LoD), we introduce a multi-scale tri-plane-based scene representation that is capable of capturing the LoD of the signed distance function (SDF) and the space radiance. Our representation aggregates space features from a multi-convolved featurization within a conical frustum along a ray and optimizes the LoD feature volume through differentiable rendering. Additionally, we propose an error-guided sampling strategy to guide the growth of the SDF during the optimization. Both qualitative and quantitative evaluations demonstrate that our method achieves superior surface reconstruction and photorealistic view synthesis compared to state-of-the-art approaches.

Xingwu Sun, Yanfeng Chen, Yiqing Huang et al. · tencent-ai

In this paper, we introduce Hunyuan-Large, which is currently the largest open-source Transformer-based mixture of experts model, with a total of 389 billion parameters and 52 billion activation parameters, capable of handling up to 256K tokens. We conduct a thorough evaluation of Hunyuan-Large's superior performance across various benchmarks including language understanding and generation, logical reasoning, mathematical problem-solving, coding, long-context, and aggregated tasks, where it outperforms LLama3.1-70B and exhibits comparable performance when compared to the significantly larger LLama3.1-405B model. Key practice of Hunyuan-Large include large-scale synthetic data that is orders larger than in previous literature, a mixed expert routing strategy, a key-value cache compression technique, and an expert-specific learning rate strategy. Additionally, we also investigate the scaling laws and learning rate schedule of mixture of experts models, providing valuable insights and guidances for future model development and optimization. The code and checkpoints of Hunyuan-Large are released to facilitate future innovations and applications. Codes: https://github.com/Tencent/Hunyuan-Large Models: https://huggingface.co/tencent/Tencent-Hunyuan-Large

Qianyun He, Xinya Ji, Yicheng Gong et al.

We present a novel approach for synthesizing 3D talking heads with controllable emotion, featuring enhanced lip synchronization and rendering quality. Despite significant progress in the field, prior methods still suffer from multi-view consistency and a lack of emotional expressiveness. To address these issues, we collect EmoTalk3D dataset with calibrated multi-view videos, emotional annotations, and per-frame 3D geometry. By training on the EmoTalk3D dataset, we propose a \textit{`Speech-to-Geometry-to-Appearance'} mapping framework that first predicts faithful 3D geometry sequence from the audio features, then the appearance of a 3D talking head represented by 4D Gaussians is synthesized from the predicted geometry. The appearance is further disentangled into canonical and dynamic Gaussians, learned from multi-view videos, and fused to render free-view talking head animation. Moreover, our model enables controllable emotion in the generated talking heads and can be rendered in wide-range views. Our method exhibits improved rendering quality and stability in lip motion generation while capturing dynamic facial details such as wrinkles and subtle expressions. Experiments demonstrate the effectiveness of our approach in generating high-fidelity and emotion-controllable 3D talking heads. The code and EmoTalk3D dataset are released at https://nju-3dv.github.io/projects/EmoTalk3D.

Hao Zhu, Zhen Liu, Qi Zhang et al.

Implicit Neural Representation (INR), which utilizes a neural network to map coordinate inputs to corresponding attributes, is causing a revolution in the field of signal processing. However, current INR techniques suffer from the "frequency"-specified spectral bias and capacity-convergence gap, resulting in imperfect performance when representing complex signals with multiple "frequencies". We have identified that both of these two characteristics could be handled by increasing the utilization of definition domain in current activation functions, for which we propose the FINER++ framework by extending existing periodic/non-periodic activation functions to variable-periodic ones. By initializing the bias of the neural network with different ranges, sub-functions with various frequencies in the variable-periodic function are selected for activation. Consequently, the supported frequency set can be flexibly tuned, leading to improved performance in signal representation. We demonstrate the generalization and capabilities of FINER++ with different activation function backbones (Sine, Gauss. and Wavelet) and various tasks (2D image fitting, 3D signed distance field representation, 5D neural radiance fields optimization and streamable INR transmission), and we show that it improves existing INRs. Project page: {https://liuzhen0212.github.io/finerpp/}

Yuxiao He, Yiyu Zhuang, Yanwen Wang et al.

Creating a 360° parametric model of a human head is a very challenging task. While recent advancements have demonstrated the efficacy of leveraging synthetic data for building such parametric head models, their performance remains inadequate in crucial areas such as expression-driven animation, hairstyle editing, and text-based modifications. In this paper, we build a dataset of artist-designed high-fidelity human heads and propose to create a novel parametric 360° renderable parametric head model from it. Our scheme decouples the facial motion/shape and facial appearance, which are represented by a classic parametric 3D mesh model and an attached neural texture, respectively. We further propose a training method for decompositing hairstyle and facial appearance, allowing free-swapping of the hairstyle. A novel inversion fitting method is presented based on single image input with high generalization and fidelity. To the best of our knowledge, our model is the first parametric 3D full-head that achieves 360° free-view synthesis, image-based fitting, appearance editing, and animation within a single model. Experiments show that facial motions and appearances are well disentangled in the parametric space, leading to SOTA performance in rendering and animating quality. The code and SynHead100 dataset are released at https://nju-3dv.github.io/projects/Head360.

Zhicheng Cai, Hao Zhu, Qiu Shen et al.

Representing signals using coordinate networks dominates the area of inverse problems recently, and is widely applied in various scientific computing tasks. Still, there exists an issue of spectral bias in coordinate networks, limiting the capacity to learn high-frequency components. This problem is caused by the pathological distribution of the neural tangent kernel's (NTK's) eigenvalues of coordinate networks. We find that, this pathological distribution could be improved using classical normalization techniques (batch normalization and layer normalization), which are commonly used in convolutional neural networks but rarely used in coordinate networks. We prove that normalization techniques greatly reduces the maximum and variance of NTK's eigenvalues while slightly modifies the mean value, considering the max eigenvalue is much larger than the most, this variance change results in a shift of eigenvalues' distribution from a lower one to a higher one, therefore the spectral bias could be alleviated. Furthermore, we propose two new normalization techniques by combining these two techniques in different ways. The efficacy of these normalization techniques is substantiated by the significant improvements and new state-of-the-arts achieved by applying normalization-based coordinate networks to various tasks, including the image compression, computed tomography reconstruction, shape representation, magnetic resonance imaging, novel view synthesis and multi-view stereo reconstruction.

Chengkang Shen, Hao Zhu, You Zhou et al.

Myocardial motion tracking stands as an essential clinical tool in the prevention and detection of cardiovascular diseases (CVDs), the foremost cause of death globally. However, current techniques suffer from incomplete and inaccurate motion estimation of the myocardium in both spatial and temporal dimensions, hindering the early identification of myocardial dysfunction. To address these challenges, this paper introduces the Neural Cardiac Motion Field (NeuralCMF). NeuralCMF leverages implicit neural representation (INR) to model the 3D structure and the comprehensive 6D forward/backward motion of the heart. This method surpasses pixel-wise limitations by offering the capability to continuously query the precise shape and motion of the myocardium at any specific point throughout the cardiac cycle, enhancing the detailed analysis of cardiac dynamics beyond traditional speckle tracking. Notably, NeuralCMF operates without the need for paired datasets, and its optimization is self-supervised through the physics knowledge priors in both space and time dimensions, ensuring compatibility with both 2D and 3D echocardiogram video inputs. Experimental validations across three representative datasets support the robustness and innovative nature of the NeuralCMF, marking significant advantages over existing state-of-the-art methods in cardiac imaging and motion tracking.

Kaiwen Zhang, Zhenyu Tang, Xiaotao Hu et al.

Diffusion models have demonstrated exceptional visual quality in video generation, making them promising for autonomous driving world modeling. However, existing video diffusion-based world models struggle with flexible-length, long-horizon predictions and integrating trajectory planning. This is because conventional video diffusion models rely on global joint distribution modeling of fixed-length frame sequences rather than sequentially constructing localized distributions at each timestep. In this work, we propose Epona, an autoregressive diffusion world model that enables localized spatiotemporal distribution modeling through two key innovations: 1) Decoupled spatiotemporal factorization that separates temporal dynamics modeling from fine-grained future world generation, and 2) Modular trajectory and video prediction that seamlessly integrate motion planning with visual modeling in an end-to-end framework. Our architecture enables high-resolution, long-duration generation while introducing a novel chain-of-forward training strategy to address error accumulation in autoregressive loops. Experimental results demonstrate state-of-the-art performance with 7.4\% FVD improvement and minutes longer prediction duration compared to prior works. The learned world model further serves as a real-time motion planner, outperforming strong end-to-end planners on NAVSIM benchmarks. Code will be publicly available at \href{https://github.com/Kevin-thu/Epona/}{https://github.com/Kevin-thu/Epona/}.

Delong Wu, Hao Zhu, Qi Zhang et al.

Implicit Neural Representation (INR) has become a popular method for representing visual signals (e.g., 2D images and 3D scenes), demonstrating promising results in various downstream applications. Given its potential as a medium for visual signals, exploring the development of a neural blending method that utilizes INRs is a natural progression. Neural blending involves merging two INRs to create a new INR that encapsulates information from both original representations. A direct approach involves applying traditional image editing methods to the INR rendering process. However, this method often results in blending distortions, artifacts, and color shifts, primarily due to the discretization of the underlying pixel grid and the introduction of boundary conditions for solving variational problems. To tackle this issue, we introduce the Neural Poisson Solver, a plug-and-play and universally applicable framework across different signal dimensions for blending visual signals represented by INRs. Our Neural Poisson Solver offers a variational problem-solving approach based on the continuous Poisson equation, demonstrating exceptional performance across various domains. Specifically, we propose a gradient-guided neural solver to represent the solution process of the variational problem, refining the target signal to achieve natural blending results. We also develop a Poisson equation-based loss and optimization scheme to train our solver, ensuring it effectively blends the input INR scenes while preserving their inherent structure and semantic content. The lack of dependence on additional prior knowledge makes our method easily adaptable to various task categories, highlighting its versatility. Comprehensive experimental results validate the robustness of our approach across multiple dimensions and blending tasks.

Qingrui Zhao, Kaiyue Yang, Xiyu Wang et al.

Humanoid robots require diverse motor skills to integrate into complex environments, but bridging the kinematic and dynamic embodiment gap from human data remains a major bottleneck. We demonstrate through Hessian analysis that traditional optimization-based retargeting is inherently non-convex and prone to local optima, leading to physical artifacts like joint jumps and self-penetration. To address this, we reformulate the targeting problem as learning data distribution rather than optimizing optimal solutions, where we propose NMR, a Neural Motion Retargeting framework that transforms static geometric mapping into a dynamics-aware learned process. We first propose Clustered-Expert Physics Refinement (CEPR), a hierarchical data pipeline that leverages VAE-based motion clustering to group heterogeneous movements into latent motifs. This strategy significantly reduces the computational overhead of massively parallel reinforcement learning experts, which project and repair noisy human demonstrations onto the robot's feasible motion manifold. The resulting high-fidelity data supervises a non-autoregressive CNN-Transformer architecture that reasons over global temporal context to suppress reconstruction noise and bypass geometric traps. Experiments on the Unitree G1 humanoid across diverse dynamic tasks (e.g., martial arts, dancing) show that NMR eliminates joint jumps and significantly reduces self-collisions compared to state-of-the-art baselines. Furthermore, NMR-generated references accelerate the convergence of downstream whole-body control policies, establishing a scalable path for bridging the human-robot embodiment gap.

Zhicheng Cai, Hao Zhu, Linsen Chen et al.

Implicit neural representation (INR) models signals as continuous functions using neural networks, offering efficient and differentiable optimization for inverse problems across diverse disciplines. However, the representational capacity of INR defined by the range of functions the neural network can characterize, is inherently limited by the low-dimensional feature space in conventional multilayer perceptron (MLP) architectures. While widening the MLP can linearly increase feature space dimensionality, it also leads to a quadratic growth in computational and memory costs. To address this limitation, we propose the split-layer, a novel reformulation of MLP construction. The split-layer divides each layer into multiple parallel branches and integrates their outputs via Hadamard product, effectively constructing a high-degree polynomial space. This approach significantly enhances INR's representational capacity by expanding the feature space dimensionality without incurring prohibitive computational overhead. Extensive experiments demonstrate that the split-layer substantially improves INR performance, surpassing existing methods across multiple tasks, including 2D image fitting, 2D CT reconstruction, 3D shape representation, and 5D novel view synthesis.

Yifei Zeng, Yajie Bao, Jiachen Qian et al.

Prevailing 3D texture generation methods, which often rely on multi-view fusion, are frequently hindered by inter-view inconsistencies and incomplete coverage of complex surfaces, limiting the fidelity and completeness of the generated content. To overcome these challenges, we introduce TEXTRIX, a native 3D attribute generation framework for high-fidelity texture synthesis and downstream applications such as precise 3D part segmentation. Our approach constructs a latent 3D attribute grid and leverages a Diffusion Transformer equipped with sparse attention, enabling direct coloring of 3D models in volumetric space and fundamentally avoiding the limitations of multi-view fusion. Built upon this native representation, the framework naturally extends to high-precision 3D segmentation by training the same architecture to predict semantic attributes on the grid. Extensive experiments demonstrate state-of-the-art performance on both tasks, producing seamless, high-fidelity textures and accurate 3D part segmentation with precise boundaries.

Zhijian Shu, Cheng Lin, Tao Xie et al.

3D vision foundation models like Visual Geometry Grounded Transformer (VGGT) have advanced greatly in geometric perception. However, it is time-consuming and memory-intensive for long sequences, limiting application to large-scale scenes beyond hundreds of images. To address this, we propose LiteVGGT, achieving up to 10x speedup and substantial memory reduction, enabling efficient processing of 1000-image scenes. We derive two key insights for 3D reconstruction: (1) tokens from local image regions have inherent geometric correlations, leading to high similarity and computational redundancy; (2) token similarity across adjacent network layers remains stable, allowing for reusable merge decisions. Guided by these, we design a simple yet efficient strategy, dubbed geometry-aware cached token merging. We analyze each token's geometric importance, optimizing anchor token selection to better preserve key information for reconstruction. We also cache and reuse merge indices across layers, substantially reducing latency with minimal accuracy impact. This strategy retains VGGT's core performance, enabling efficient fine-tuning and FP8 quantization for further gains. Extensive experiments validate LiteVGGT's effectiveness, scalability, and robustness. Project page: https://garlicba.github.io/LiteVGGT/

Zijian Wu, Boyao Zhou, Liangxiao Hu et al.

We present UIKA, a feed-forward animatable Gaussian head model from an arbitrary number of unposed inputs, including a single image, multi-view captures, and smartphone-captured videos. Unlike the traditional avatar method, which requires a studio-level multi-view capture system and reconstructs a human-specific model through a long-time optimization process, we rethink the task through the lenses of model representation, network design, and data preparation. First, we introduce a UV-guided avatar modeling strategy, in which each input image is associated with a pixel-wise facial correspondence estimation. Such correspondence estimation allows us to reproject each valid pixel color from screen space to UV space, which is independent of camera pose and character expression. Furthermore, we design learnable UV tokens on which the attention mechanism can be applied at both the screen and UV levels. The learned UV tokens can be decoded into canonical Gaussian attributes using aggregated UV information from all input views. To train our large avatar model, we additionally prepare a large-scale, identity-rich synthetic training dataset. Our method significantly outperforms existing approaches in both monocular and multi-view settings. Project page: https://zijian-wu.github.io/uika-page/

Zhengxuan Li, Qinhui Yang, Yiyu Zhuang et al.

We present Pressure2Motion, a novel motion capture algorithm that synthesizes human motion from a ground pressure sequence and text prompt. It eliminates the need for specialized lighting setups, cameras, or wearable devices, making it suitable for privacy-preserving, low-light, and low-cost motion capture scenarios. Such a task is severely ill-posed due to the indeterminate nature of the pressure signals to full-body motion. To address this issue, we introduce Pressure2Motion, a generative model that leverages pressure features as input and utilizes a text prompt as a high-level guiding constraint. Specifically, our model utilizes a dual-level feature extractor that accurately interprets pressure data, followed by a hierarchical diffusion model that discerns broad-scale movement trajectories and subtle posture adjustments. Both the physical cues gained from the pressure sequence and the semantic guidance derived from descriptive texts are leveraged to guide the motion generation with precision. To the best of our knowledge, Pressure2Motion is a pioneering work in leveraging both pressure data and linguistic priors for motion generation, and the established MPL benchmark is the first benchmark for this task. Experiments show our method generates high-fidelity, physically plausible motions, establishing a new state-of-the-art for this task. The codes and benchmarks will be publicly released upon publication.

Li Wang, Yiyu Zhuang, Yanwen Wang et al.

3D human pose estimation from sketches has broad applications in computer animation and film production. Unlike traditional human pose estimation, this task presents unique challenges due to the abstract and disproportionate nature of sketches. Previous sketch-to-pose methods, constrained by the lack of large-scale sketch-3D pose annotations, primarily relied on optimization with heuristic rules-an approach that is both time-consuming and limited in generalizability. To address these challenges, we propose a novel approach leveraging a "learn from synthesis" strategy. First, a diffusion model is trained to synthesize sketch images from 2D poses projected from 3D human poses, mimicking disproportionate human structures in sketches. This process enables the creation of a synthetic dataset, SKEP-120K, consisting of 120k accurate sketch-3D pose annotation pairs across various sketch styles. Building on this synthetic dataset, we introduce an end-to-end data-driven framework for estimating human poses and shapes from diverse sketch styles. Our framework combines existing 2D pose detectors and generative diffusion priors for sketch feature extraction with a feed-forward neural network for efficient 2D pose estimation. Multiple heuristic loss functions are incorporated to guarantee geometric coherence between the derived 3D poses and the detected 2D poses while preserving accurate self-contacts. Qualitative, quantitative, and subjective evaluations collectively show that our model substantially surpasses previous ones in both estimation accuracy and speed for sketch-to-pose tasks.

Jiuyun Zhang, Zhan Shi, Linsen Chen et al.

Existing computational spectral imaging systems typically rely on coded aperture and beam splitters that block a substantial fraction of incident light, degrading reconstruction quality under light-starved conditions. To address this limitation, we develop the Oscillating Dispersion Imaging Spectrometer (ODIS), which for the first time achieves near-full light throughput by axially translating a disperser between the conjugate image plane and a defocused position, sequentially capturing a panchromatic (PAN) image and a dispersed measurement along a single optical path. We further propose a PAN-guided Dispersion-Aware Deep Unfolding Network (PDAUN) that recovers high-fidelity spectral information from maskless dispersion under PAN structural guidance. Its data-fidelity step derives an FFT-Woodbury preconditioned solver by exploiting the cyclic-convolution property of the ODIS forward model, while a Dispersion-Aware Deformable Convolution module (DADC) corrects sub-pixel spectral misalignment using PAN features. Experiments show state-of-the-art performance on standard benchmarks, and cross-system comparisons confirm that ODIS yields decisive gains under low illumination. High-fidelity reconstruction is validated on a physical prototype.

Tao Lv, Daoming Zhou, Chenglong Huang et al.

Computational spectral imaging (CSI) achieves real-time hyperspectral imaging through co-designed optics and algorithms, but typical CSI methods suffer from a bulky footprint and limited fidelity. Therefore, Spectral Deconvolution imaging (SDI) methods based on PSF engineering have been proposed to achieve high-fidelity compact CSI design recently. However, the composite convolution-integration operations of SDI render the normal-equation coefficient matrix scene-dependent, which hampers the efficient exploitation of imaging priors and poses challenges for accurate reconstruction. To tackle the inherent data-dependent operators in SDI, we introduce a Hierarchical Spatial-Spectral Aggregation Unfolding Framework (HSFAUF). By decomposing subproblems and projecting them into the frequency domain, HSFAUF transforms nonlinear processes into linear mappings, thereby enabling efficient solutions. Furthermore, to integrate spatial-spectral priors during iterative refinement, we propose a Spatial-Frequency Aggregation Transformer (SFAT), which explicitly aggregates information across spatial and frequency domains. By integrating SFAT into HSFAUF, we develop a Transformer-based deep unfolding method, \textbf{H}ierarchical \textbf{S}patial-\textbf{F}requency \textbf{A}ggregation \textbf{U}nfolding \textbf{T}ransformer (HSFAUT), to solve the inverse problem of SDI. Systematic simulated and real experiments show that HSFAUT surpasses SOTA methods with cheaper memory and computational costs, while exhibiting optimal performance on different SDI systems.

Shenhao Zhu, Junming Leo Chen, Zuozhuo Dai et al.

In this study, we introduce a methodology for human image animation by leveraging a 3D human parametric model within a latent diffusion framework to enhance shape alignment and motion guidance in curernt human generative techniques. The methodology utilizes the SMPL(Skinned Multi-Person Linear) model as the 3D human parametric model to establish a unified representation of body shape and pose. This facilitates the accurate capture of intricate human geometry and motion characteristics from source videos. Specifically, we incorporate rendered depth images, normal maps, and semantic maps obtained from SMPL sequences, alongside skeleton-based motion guidance, to enrich the conditions to the latent diffusion model with comprehensive 3D shape and detailed pose attributes. A multi-layer motion fusion module, integrating self-attention mechanisms, is employed to fuse the shape and motion latent representations in the spatial domain. By representing the 3D human parametric model as the motion guidance, we can perform parametric shape alignment of the human body between the reference image and the source video motion. Experimental evaluations conducted on benchmark datasets demonstrate the methodology's superior ability to generate high-quality human animations that accurately capture both pose and shape variations. Furthermore, our approach also exhibits superior generalization capabilities on the proposed in-the-wild dataset. Project page: https://fudan-generative-vision.github.io/champ.

Yunzhong Zhang, Bo Xiong, You Zhou et al.

The need for accurate and non-intrusive flow measurement methods has led to the widespread adoption of Particle Image Velocimetry (PIV), a powerful diagnostic tool in fluid motion estimation. This study investigates the tremendous potential of spike cameras (a type of ultra-high-speed, high-dynamic-range camera) in PIV. We propose a deep learning framework, Spike Imaging Velocimetry (SIV), designed specifically for highly turbulent and intricate flow fields. To aggregate motion features from the spike stream while minimizing information loss, we incorporate a Detail-Preserving Hierarchical Transform (DPHT) module. Additionally, we introduce a Graph Encoder (GE) to extract contextual features from highly complex fluid flows. Furthermore, we present a spike-based PIV dataset, Particle Scenes with Spike and Displacement (PSSD), which provides labeled data for three challenging fluid dynamics scenarios. Our proposed method achieves superior performance compared to existing baseline methods on PSSD. The datasets and our implementation of SIV are open-sourced in the supplementary materials.

Xinya Ji, Sebastian Weiss, Manuel Kansy et al.

Despite recent progress in 3D Gaussian-based head avatar modeling, efficiently generating high fidelity avatars remains a challenge. Current methods typically rely on extensive multi-view capture setups or monocular videos with per-identity optimization during inference, limiting their scalability and ease of use on unseen subjects. To overcome these efficiency drawbacks, we propose \OURS, a feed-forward method to generate high-quality Gaussian head avatars from only a few input images while supporting real-time animation. Our approach directly learns a per-pixel Gaussian representation from the input images, and aggregates multi-view information using a transformer-based encoder that fuses image features from both DINOv3 and Stable Diffusion VAE. For real-time animation, we extend the explicit Gaussian representations with per-Gaussian features and introduce a lightweight MLP-based dynamic network to predict 3D Gaussian deformations from expression codes. Furthermore, to enhance geometric smoothness of the 3D head, we employ point maps from a pre-trained large reconstruction model as geometry supervision. Experiments show that our approach significantly outperforms existing methods in both rendering quality and inference efficiency, while supporting real-time dynamic avatar animation.

Shuang Wu, Youtian Lin, Feihu Zhang et al.

Generating high-quality 3D assets from text and images has long been challenging, primarily due to the absence of scalable 3D representations capable of capturing intricate geometry distributions. In this work, we introduce Direct3D, a native 3D generative model scalable to in-the-wild input images, without requiring a multiview diffusion model or SDS optimization. Our approach comprises two primary components: a Direct 3D Variational Auto-Encoder (D3D-VAE) and a Direct 3D Diffusion Transformer (D3D-DiT). D3D-VAE efficiently encodes high-resolution 3D shapes into a compact and continuous latent triplane space. Notably, our method directly supervises the decoded geometry using a semi-continuous surface sampling strategy, diverging from previous methods relying on rendered images as supervision signals. D3D-DiT models the distribution of encoded 3D latents and is specifically designed to fuse positional information from the three feature maps of the triplane latent, enabling a native 3D generative model scalable to large-scale 3D datasets. Additionally, we introduce an innovative image-to-3D generation pipeline incorporating semantic and pixel-level image conditions, allowing the model to produce 3D shapes consistent with the provided conditional image input. Extensive experiments demonstrate the superiority of our large-scale pre-trained Direct3D over previous image-to-3D approaches, achieving significantly better generation quality and generalization ability, thus establishing a new state-of-the-art for 3D content creation. Project page: https://nju-3dv.github.io/projects/Direct3D/.

Kailai Zhou, Fuqiang Yang, Shixian Wang et al.

RGB-Thermal (RGBT) multispectral vision is essential for robust perception in complex environments. Most RGBT tasks follow a case-by-case research paradigm, relying on manually customized models to learn task-oriented representations. Nevertheless, this paradigm is inherently constrained by artificial inductive bias, modality bias, and data bottleneck. To address these limitations, we make the initial attempt to build a Generalized RGBT MultiSpectral foundation model (M-SpecGene), which aims to learn modality-invariant representations from large-scale broad data in a self-supervised manner. M-SpecGene provides new insights into multispectral fusion and integrates prior case-by-case studies into a unified paradigm. Considering the unique characteristic of information imbalance in RGBT data, we introduce the Cross-Modality Structural Sparsity (CMSS) metric to quantify the information density across two modalities. Then we develop the GMM-CMSS progressive masking strategy to facilitate a flexible, easy-to-hard, and object-centric pre-training process. Comprehensive experiments validate M-SpecGene's generalizability across eleven datasets for four RGBT downstream tasks. The code will be available at https://github.com/CalayZhou/M-SpecGene.

Menghua Wu, Hao Zhu, Linjia Huang et al.

Synthesizing high-quality 3D face models from natural language descriptions is very valuable for many applications, including avatar creation, virtual reality, and telepresence. However, little research ever tapped into this task. We argue the major obstacle lies in 1) the lack of high-quality 3D face data with descriptive text annotation, and 2) the complex mapping relationship between descriptive language space and shape/appearance space. To solve these problems, we build Describe3D dataset, the first large-scale dataset with fine-grained text descriptions for text-to-3D face generation task. Then we propose a two-stage framework to first generate a 3D face that matches the concrete descriptions, then optimize the parameters in the 3D shape and texture space with abstract description to refine the 3D face model. Extensive experimental results show that our method can produce a faithful 3D face that conforms to the input descriptions with higher accuracy and quality than previous methods. The code and Describe3D dataset are released at https://github.com/zhuhao-nju/describe3d .

Yunze Xiao, Hao Zhu, Haotian Yang et al.

Recovering detailed facial geometry from a set of calibrated multi-view images is valuable for its wide range of applications. Traditional multi-view stereo (MVS) methods adopt an optimization-based scheme to regularize the matching cost. Recently, learning-based methods integrate all these into an end-to-end neural network and show superiority of efficiency. In this paper, we propose a novel architecture to recover extremely detailed 3D faces within dozens of seconds. Unlike previous learning-based methods that regularize the cost volume via 3D CNN, we propose to learn an implicit function for regressing the matching cost. By fitting a 3D morphable model from multi-view images, the features of multiple images are extracted and aggregated in the mesh-attached UV space, which makes the implicit function more effective in recovering detailed facial shape. Our method outperforms SOTA learning-based MVS in accuracy by a large margin on the FaceScape dataset. The code and data are released in https://github.com/zhuhao-nju/mvfr.

Yiyu Zhuang, Hao Zhu, Xusen Sun et al.

We propose a parametric model that maps free-view images into a vector space of coded facial shape, expression and appearance with a neural radiance field, namely Morphable Facial NeRF. Specifically, MoFaNeRF takes the coded facial shape, expression and appearance along with space coordinate and view direction as input to an MLP, and outputs the radiance of the space point for photo-realistic image synthesis. Compared with conventional 3D morphable models (3DMM), MoFaNeRF shows superiority in directly synthesizing photo-realistic facial details even for eyes, mouths, and beards. Also, continuous face morphing can be easily achieved by interpolating the input shape, expression and appearance codes. By introducing identity-specific modulation and texture encoder, our model synthesizes accurate photometric details and shows strong representation ability. Our model shows strong ability on multiple applications including image-based fitting, random generation, face rigging, face editing, and novel view synthesis. Experiments show that our method achieves higher representation ability than previous parametric models, and achieves competitive performance in several applications. To the best of our knowledge, our work is the first facial parametric model built upon a neural radiance field that can be used in fitting, generation and manipulation. The code and data is available at https://github.com/zhuhao-nju/mofanerf.

Hao Zhu, Haotian Yang, Longwei Guo et al.

In this paper, we present a large-scale detailed 3D face dataset, FaceScape, and the corresponding benchmark to evaluate single-view facial 3D reconstruction. By training on FaceScape data, a novel algorithm is proposed to predict elaborate riggable 3D face models from a single image input. FaceScape dataset releases $16,940$ textured 3D faces, captured from $847$ subjects and each with $20$ specific expressions. The 3D models contain the pore-level facial geometry that is also processed to be topologically uniform. These fine 3D facial models can be represented as a 3D morphable model for coarse shapes and displacement maps for detailed geometry. Taking advantage of the large-scale and high-accuracy dataset, a novel algorithm is further proposed to learn the expression-specific dynamic details using a deep neural network. The learned relationship serves as the foundation of our 3D face prediction system from a single image input. Different from most previous methods, our predicted 3D models are riggable with highly detailed geometry under different expressions. We also use FaceScape data to generate the in-the-wild and in-the-lab benchmark to evaluate recent methods of single-view face reconstruction. The accuracy is reported and analyzed on the dimensions of camera pose and focal length, which provides a faithful and comprehensive evaluation and reveals new challenges. The unprecedented dataset, benchmark, and code have been released at https://github.com/zhuhao-nju/facescape.

Kailai Zhou, Linsen Chen, Xun Cao

Multispectral pedestrian detection is capable of adapting to insufficient illumination conditions by leveraging color-thermal modalities. On the other hand, it is still lacking of in-depth insights on how to fuse the two modalities effectively. Compared with traditional pedestrian detection, we find multispectral pedestrian detection suffers from modality imbalance problems which will hinder the optimization process of dual-modality network and depress the performance of detector. Inspired by this observation, we propose Modality Balance Network (MBNet) which facilitates the optimization process in a much more flexible and balanced manner. Firstly, we design a novel Differential Modality Aware Fusion (DMAF) module to make the two modalities complement each other. Secondly, an illumination aware feature alignment module selects complementary features according to the illumination conditions and aligns the two modality features adaptively. Extensive experimental results demonstrate MBNet outperforms the state-of-the-arts on both the challenging KAIST and CVC-14 multispectral pedestrian datasets in terms of the accuracy and the computational efficiency. Code is available at https://github.com/CalayZhou/MBNet.

Hao Zhu, Xinxin Zuo, Sen Wang et al.

This paper presents a novel framework to recover detailed human body shapes from a single image. It is a challenging task due to factors such as variations in human shapes, body poses, and viewpoints. Prior methods typically attempt to recover the human body shape using a parametric based template that lacks the surface details. As such the resulting body shape appears to be without clothing. In this paper, we propose a novel learning-based framework that combines the robustness of parametric model with the flexibility of free-form 3D deformation. We use the deep neural networks to refine the 3D shape in a Hierarchical Mesh Deformation (HMD) framework, utilizing the constraints from body joints, silhouettes, and per-pixel shading information. We are able to restore detailed human body shapes beyond skinned models. Experiments demonstrate that our method has outperformed previous state-of-the-art approaches, achieving better accuracy in terms of both 2D IoU number and 3D metric distance. The code is available in https://github.com/zhuhao-nju/hmd.git

Yifei Zeng, Yanqin Jiang, Siyu Zhu et al.

Recent progress in pre-trained diffusion models and 3D generation have spurred interest in 4D content creation. However, achieving high-fidelity 4D generation with spatial-temporal consistency remains a challenge. In this work, we propose STAG4D, a novel framework that combines pre-trained diffusion models with dynamic 3D Gaussian splatting for high-fidelity 4D generation. Drawing inspiration from 3D generation techniques, we utilize a multi-view diffusion model to initialize multi-view images anchoring on the input video frames, where the video can be either real-world captured or generated by a video diffusion model. To ensure the temporal consistency of the multi-view sequence initialization, we introduce a simple yet effective fusion strategy to leverage the first frame as a temporal anchor in the self-attention computation. With the almost consistent multi-view sequences, we then apply the score distillation sampling to optimize the 4D Gaussian point cloud. The 4D Gaussian spatting is specially crafted for the generation task, where an adaptive densification strategy is proposed to mitigate the unstable Gaussian gradient for robust optimization. Notably, the proposed pipeline does not require any pre-training or fine-tuning of diffusion networks, offering a more accessible and practical solution for the 4D generation task. Extensive experiments demonstrate that our method outperforms prior 4D generation works in rendering quality, spatial-temporal consistency, and generation robustness, setting a new state-of-the-art for 4D generation from diverse inputs, including text, image, and video.

Mingjie Ji, Zhan Shi, Kailai Zhou et al.

Self-supervised video denoising methods typically extend image-based frameworks into the temporal dimension, yet they often struggle to integrate inter-frame temporal consistency with intra-frame spatial specificity. Existing Video Blind-Spot Networks (BSNs) require noise independence by masking the center pixel, this constraint prevents the use of spatial evidence for texture recovery, thereby severing spatiotemporal correlations and causing texture loss. To address this, we propose Frames2Residual (F2R), a spatiotemporal decoupling framework that explicitly divides self-supervised training into two distinct stages: blind temporal consistency modeling and non-blind spatial texture recovery. In Stage 1, a blind temporal estimator learns inter-frame consistency using a frame-wise blind strategy, producing a temporally consistent anchor. In Stage 2, a non-blind spatial refiner leverages this anchor to safely reintroduce the center frame and recover intra-frame high-frequency spatial residuals while preserving temporal stability. Extensive experiments demonstrate that our decoupling strategy allows F2R to outperform existing self-supervised methods on both sRGB and raw video benchmarks.

Zhen Liu, Hao Zhu, Qi Zhang et al.

Implicit Neural Representation (INR), which utilizes a neural network to map coordinate inputs to corresponding attributes, is causing a revolution in the field of signal processing. However, current INR techniques suffer from a restricted capability to tune their supported frequency set, resulting in imperfect performance when representing complex signals with multiple frequencies. We have identified that this frequency-related problem can be greatly alleviated by introducing variable-periodic activation functions, for which we propose FINER. By initializing the bias of the neural network within different ranges, sub-functions with various frequencies in the variable-periodic function are selected for activation. Consequently, the supported frequency set of FINER can be flexibly tuned, leading to improved performance in signal representation. We demonstrate the capabilities of FINER in the contexts of 2D image fitting, 3D signed distance field representation, and 5D neural radiance fields optimization, and we show that it outperforms existing INRs.

Xusen Sun, Longhao Zhang, Hao Zhu et al.

Audio-driven talking head generation has drawn much attention in recent years, and many efforts have been made in lip-sync, expressive facial expressions, natural head pose generation, and high video quality. However, no model has yet led or tied on all these metrics due to the one-to-many mapping between audio and motion. In this paper, we propose VividTalk, a two-stage generic framework that supports generating high-visual quality talking head videos with all the above properties. Specifically, in the first stage, we map the audio to mesh by learning two motions, including non-rigid expression motion and rigid head motion. For expression motion, both blendshape and vertex are adopted as the intermediate representation to maximize the representation ability of the model. For natural head motion, a novel learnable head pose codebook with a two-phase training mechanism is proposed. In the second stage, we proposed a dual branch motion-vae and a generator to transform the meshes into dense motion and synthesize high-quality video frame-by-frame. Extensive experiments show that the proposed VividTalk can generate high-visual quality talking head videos with lip-sync and realistic enhanced by a large margin, and outperforms previous state-of-the-art works in objective and subjective comparisons.

Yiyu Zhuang, Jiaxi Lv, Hao Wen et al.

Creating a high-fidelity, animatable 3D full-body avatar from a single image is a challenging task due to the diverse appearance and poses of humans and the limited availability of high-quality training data. To achieve fast and high-quality human reconstruction, this work rethinks the task from the perspectives of dataset, model, and representation. First, we introduce a large-scale HUman-centric GEnerated dataset, HuGe100K, consisting of 100K diverse, photorealistic sets of human images. Each set contains 24-view frames in specific human poses, generated using a pose-controllable image-to-multi-view model. Next, leveraging the diversity in views, poses, and appearances within HuGe100K, we develop a scalable feed-forward transformer model to predict a 3D human Gaussian representation in a uniform space from a given human image. This model is trained to disentangle human pose, body shape, clothing geometry, and texture. The estimated Gaussians can be animated without post-processing. We conduct comprehensive experiments to validate the effectiveness of the proposed dataset and method. Our model demonstrates the ability to efficiently reconstruct photorealistic humans at 1K resolution from a single input image using a single GPU instantly. Additionally, it seamlessly supports various applications, as well as shape and texture editing tasks. Project page: https://yiyuzhuang.github.io/IDOL/.