Qing Wang

Xin Huang, Ruizhi Shao, Qi Zhang et al.

Recent text-to-3D methods employing diffusion models have made significant advancements in 3D human generation. However, these approaches face challenges due to the limitations of text-to-image diffusion models, which lack an understanding of 3D structures. Consequently, these methods struggle to achieve high-quality human generation, resulting in smooth geometry and cartoon-like appearances. In this paper, we propose HumanNorm, a novel approach for high-quality and realistic 3D human generation. The main idea is to enhance the model's 2D perception of 3D geometry by learning a normal-adapted diffusion model and a normal-aligned diffusion model. The normal-adapted diffusion model can generate high-fidelity normal maps corresponding to user prompts with view-dependent and body-aware text. The normal-aligned diffusion model learns to generate color images aligned with the normal maps, thereby transforming physical geometry details into realistic appearance. Leveraging the proposed normal diffusion model, we devise a progressive geometry generation strategy and a multi-step Score Distillation Sampling (SDS) loss to enhance the performance of 3D human generation. Comprehensive experiments substantiate HumanNorm's ability to generate 3D humans with intricate geometry and realistic appearances. HumanNorm outperforms existing text-to-3D methods in both geometry and texture quality. The project page of HumanNorm is https://humannorm.github.io/.

Rongxuan Tan, Qing Wang, Xueyan Wang et al.

Significant strides have been made in enhancing the accuracy of Multi-View Stereo (MVS)-based 3D reconstruction. However, untextured areas with unstable photometric consistency often remain incompletely reconstructed. In this paper, we propose a resilient and effective multi-view stereo approach (MP-MVS). We design a multi-scale windows PatchMatch (mPM) to obtain reliable depth of untextured areas. In contrast with other multi-scale approaches, which is faster and can be easily extended to PatchMatch-based MVS approaches. Subsequently, we improve the existing checkerboard sampling schemes by limiting our sampling to distant regions, which can effectively improve the efficiency of spatial propagation while mitigating outlier generation. Finally, we introduce and improve planar prior assisted PatchMatch of ACMP. Instead of relying on photometric consistency, we utilize geometric consistency information between multi-views to select reliable triangulated vertices. This strategy can obtain a more accurate planar prior model to rectify photometric consistency measurements. Our approach has been tested on the ETH3D High-res multi-view benchmark with several state-of-the-art approaches. The results demonstrate that our approach can reach the state-of-the-art. The associated codes will be accessible at https://github.com/RongxuanTan/MP-MVS.

Yaning Li, Xue Wang, Hao Zhu et al.

Existing light field representations, such as epipolar plane image (EPI) and sub-aperture images, do not consider the structural characteristics across the views, so they usually require additional disparity and spatial structure cues for follow-up tasks. Besides, they have difficulties dealing with occlusions or larger disparity scenes. To this end, this paper proposes a novel Epipolar Focus Spectrum (EFS) representation by rearranging the EPI spectrum. Different from the classical EPI representation where an EPI line corresponds to a specific depth, there is a one-to-one mapping from the EFS line to the view. Accordingly, compared to a sparsely-sampled light field, a densely-sampled one with the same field of view (FoV) leads to a more compact distribution of such linear structures in the double-cone-shaped region with the identical opening angle in its corresponding EFS. Hence the EFS representation is invariant to the scene depth. To demonstrate its effectiveness, we develop a trainable EFS-based pipeline for light field reconstruction, where a dense light field can be reconstructed by compensating the "missing EFS lines" given a sparse light field, yielding promising results with cross-view consistency, especially in the presence of severe occlusion and large disparity. Experimental results on both synthetic and real-world datasets demonstrate the validity and superiority of the proposed method over SOTA methods.

Xin Huang, Qi Zhang, Ying Feng et al.

We propose LIRF (Local Implicit Ray Function), a generalizable neural rendering approach for novel view rendering. Current generalizable neural radiance fields (NeRF) methods sample a scene with a single ray per pixel and may therefore render blurred or aliased views when the input views and rendered views capture scene content with different resolutions. To solve this problem, we propose LIRF to aggregate the information from conical frustums to construct a ray. Given 3D positions within conical frustums, LIRF takes 3D coordinates and the features of conical frustums as inputs and predicts a local volumetric radiance field. Since the coordinates are continuous, LIRF renders high-quality novel views at a continuously-valued scale via volume rendering. Besides, we predict the visible weights for each input view via transformer-based feature matching to improve the performance in occluded areas. Experimental results on real-world scenes validate that our method outperforms state-of-the-art methods on novel view rendering of unseen scenes at arbitrary scales.

Qi Zhang, Xin Huang, Ying Feng et al.

This paper studies the problem of view synthesis with certain amount of rotations from a pair of images, what we called stereo unstructured magnification. While the multi-plane image representation is well suited for view synthesis with depth invariant, how to generalize it to unstructured views remains a significant challenge. This is primarily due to the depth-dependency caused by camera frontal parallel representation. Here we propose a novel multiple homography image (MHI) representation, comprising of a set of scene planes with fixed normals and distances. A two-stage network is developed for novel view synthesis. Stage-1 is an MHI reconstruction module that predicts the MHIs and composites layered multi-normal images along the normal direction. Stage-2 is a normal-blending module to find blending weights. We also derive an angle-based cost to guide the blending of multi-normal images by exploiting per-normal geometry. Compared with the state-of-the-art methods, our method achieves superior performance for view synthesis qualitatively and quantitatively, especially for cases when the cameras undergo rotations.

Xiaohang Yang, Qing Wang, Jiahao Yang et al.

Motion retargeting seeks to faithfully replicate the spatio-temporal motion characteristics of a source character onto a target character with a different body shape. Apart from motion semantics preservation, ensuring geometric plausibility and maintaining temporal consistency are also crucial for effective motion retargeting. However, many existing methods prioritize either geometric plausibility or temporal consistency. Neglecting geometric plausibility results in interpenetration while neglecting temporal consistency leads to motion jitter. In this paper, we propose a novel sequence-to-sequence model for seamless Spatial-Temporal aware motion Retargeting (STaR), with penetration and consistency constraints. STaR consists of two modules: (1) a spatial module that incorporates dense shape representation and a novel limb penetration constraint to ensure geometric plausibility while preserving motion semantics, and (2) a temporal module that utilizes a temporal transformer and a novel temporal consistency constraint to predict the entire motion sequence at once while enforcing multi-level trajectory smoothness. The seamless combination of the two modules helps us achieve a good balance between the semantic, geometric, and temporal targets. Extensive experiments on the Mixamo and ScanRet datasets demonstrate that our method produces plausible and coherent motions while significantly reducing interpenetration rates compared with other approaches. Code page: https://github.com/XiaohangYang829/STaR.

Zhaokai Sun, Li Zhang, Qing Wang et al.

Overlapping Speech Detection (OSD) aims to identify regions where multiple speakers overlap in a conversation, a critical challenge in multi-party speech processing. This work proposes a speaker-aware progressive OSD model that leverages a progressive training strategy to enhance the correlation between subtasks such as voice activity detection (VAD) and overlap detection. To improve acoustic representation, we explore the effectiveness of state-of-the-art self-supervised learning (SSL) models, including WavLM and wav2vec 2.0, while incorporating a speaker attention module to enrich features with frame-level speaker information. Experimental results show that the proposed method achieves state-of-the-art performance, with an F1 score of 82.76\% on the AMI test set, demonstrating its robustness and effectiveness in OSD.

Yilan Dong, Haohe Liu, Qing Wang et al.

Existing 3D Gaussian Splatting (3DGS) methods for hand rendering rely on rigid skeletal motion with an oversimplified non-rigid motion model, which fails to capture fine geometric and appearance details. Additionally, they perform densification based solely on per-point gradients and process poses independently, ignoring spatial and temporal correlations. These limitations lead to geometric detail loss, temporal instability, and inefficient point distribution. To address these issues, we propose HandSplat, a novel Gaussian Splatting-based framework that enhances both fidelity and stability for hand rendering. To improve fidelity, we extend standard 3DGS attributes with implicit geometry and appearance embeddings for finer non-rigid motion modeling while preserving the static hand characteristic modeled by original 3DGS attributes. Additionally, we introduce a local gradient-aware densification strategy that dynamically refines Gaussian density in high-variation regions. To improve stability, we incorporate pose-conditioned attribute regularization to encourage attribute consistency across similar poses, mitigating temporal artifacts. Extensive experiments on InterHand2.6M demonstrate that HandSplat surpasses existing methods in fidelity and stability while achieving real-time performance. We will release the code and pre-trained models upon acceptance.

Zhiyuan Chang, Mingyang Li, Junjie Wang et al.

Text-to-Image Diffusion Models (T2I DMs) have garnered significant attention for their ability to generate high-quality images from textual descriptions. However, these models often produce images that do not fully align with the input prompts, resulting in semantic inconsistencies. The most prominent issue among these semantic inconsistencies is catastrophic-neglect, where the images generated by T2I DMs miss key objects mentioned in the prompt. We first conduct an empirical study on this issue, exploring the prevalence of catastrophic-neglect, potential mitigation strategies with feature enhancement, and the insights gained. Guided by the empirical findings, we propose an automated repair approach named Patcher to address catastrophic-neglect in T2I DMs. Specifically, Patcher first determines whether there are any neglected objects in the prompt, and then applies attention-guided feature enhancement to these neglected objects, resulting in a repaired prompt. Experimental results on three versions of Stable Diffusion demonstrate that Patcher effectively repairs the issue of catastrophic-neglect, achieving 10.1%-16.3% higher Correct Rate in image generation compared to baselines.

Zhongyun Hu, Ntumba Elie Nsampi, Xue Wang et al.

Image harmonization aims at adjusting the appearance of the foreground to make it more compatible with the background. Without exploring background illumination and its effects on the foreground elements, existing works are incapable of generating a realistic foreground shading. In this paper, we decompose the image harmonization task into two sub-problems: 1) illumination estimation of the background image and 2) re-rendering of foreground objects under background illumination. Before solving these two sub-problems, we first learn a shading-aware illumination descriptor via a well-designed neural rendering framework, of which the key is a shading bases module that generates multiple shading bases from the foreground image. Then we design a background illumination estimation module to extract the illumination descriptor from the background. Finally, the Shading-aware Illumination Descriptor is used in conjunction with the neural rendering framework (SIDNet) to produce the harmonized foreground image containing a novel harmonized shading. Moreover, we construct a photo-realistic synthetic image harmonization dataset that contains numerous shading variations with image-based lighting. Extensive experiments on both synthetic and real data demonstrate the superiority of the proposed method, especially in dealing with foreground shadings.

Xin Huang, Qi Zhang, Ying Feng et al.

We present High Dynamic Range Neural Radiance Fields (HDR-NeRF) to recover an HDR radiance field from a set of low dynamic range (LDR) views with different exposures. Using the HDR-NeRF, we are able to generate both novel HDR views and novel LDR views under different exposures. The key to our method is to model the physical imaging process, which dictates that the radiance of a scene point transforms to a pixel value in the LDR image with two implicit functions: a radiance field and a tone mapper. The radiance field encodes the scene radiance (values vary from 0 to +infty), which outputs the density and radiance of a ray by giving corresponding ray origin and ray direction. The tone mapper models the mapping process that a ray hitting on the camera sensor becomes a pixel value. The color of the ray is predicted by feeding the radiance and the corresponding exposure time into the tone mapper. We use the classic volume rendering technique to project the output radiance, colors, and densities into HDR and LDR images, while only the input LDR images are used as the supervision. We collect a new forward-facing HDR dataset to evaluate the proposed method. Experimental results on synthetic and real-world scenes validate that our method can not only accurately control the exposures of synthesized views but also render views with a high dynamic range.

Yaning Li, Xue Wang, Hao Zhu et al.

The paper aims at removing the aliasing effects of the whole focal stack generated from a sparse-sampled {4D} light field, while keeping the consistency across all the focal layers. We first explore the structural characteristics embedded in the focal stack slice and its corresponding frequency-domain representation, i.e., the Focal Stack Spectrum (FSS). We observe that the energy distribution of the FSS always resides within the same triangular area under different angular sampling rates, additionally the continuity of the Point Spread Function (PSF) is intrinsically maintained in the FSS. Based on these two observations, we propose a learning-based FSS reconstruction approach for one-time aliasing removing over the whole focal stack. Moreover, a novel conjugate-symmetric loss function is proposed for the optimization. Compared to previous works, our method avoids an explicit depth estimation, and can handle challenging large-disparity scenarios. Experimental results on both synthetic and real light field datasets show the superiority of the proposed approach for different scenes and various angular sampling rates.

Guanbin Li, Xin Zhu, Yirui Zeng et al.

Facial action unit (AU) recognition is a crucial task for facial expressions analysis and has attracted extensive attention in the field of artificial intelligence and computer vision. Existing works have either focused on designing or learning complex regional feature representations, or delved into various types of AU relationship modeling. Albeit with varying degrees of progress, it is still arduous for existing methods to handle complex situations. In this paper, we investigate how to integrate the semantic relationship propagation between AUs in a deep neural network framework to enhance the feature representation of facial regions, and propose an AU semantic relationship embedded representation learning (SRERL) framework. Specifically, by analyzing the symbiosis and mutual exclusion of AUs in various facial expressions, we organize the facial AUs in the form of structured knowledge-graph and integrate a Gated Graph Neural Network (GGNN) in a multi-scale CNN framework to propagate node information through the graph for generating enhanced AU representation. As the learned feature involves both the appearance characteristics and the AU relationship reasoning, the proposed model is more robust and can cope with more challenging cases, e.g., illumination change and partial occlusion. Extensive experiments on the two public benchmarks demonstrate that our method outperforms the previous work and achieves state of the art performance.

Yuefeng Chen, Qing Wang

Recently a category of tracking methods based on "tracking-by-detection" is widely used in visual tracking problem. Most of these methods update the classifier online using the samples generated by the tracker to handle the appearance changes. However, the self-updating scheme makes these methods suffer from drifting problem because of the incorrect labels of weak classifiers in training samples. In this paper, we split the class labels into true labels and noise labels and model them by sparse representation. A novel dynamic classifier selection method, robust to noisy training data, is proposed. Moreover, we apply the proposed classifier selection algorithm to visual tracking by integrating a part based online boosting framework. We have evaluated our proposed method on 12 challenging sequences involving severe occlusions, significant illumination changes and large pose variations. Both the qualitative and quantitative evaluations demonstrate that our approach tracks objects accurately and robustly and outperforms state-of-the-art trackers.

Qi Zhang, Chunping Zhang, Jinbo Ling et al.

Light field cameras can capture both spatial and angular information of light rays, enabling 3D reconstruction by a single exposure. The geometry of 3D reconstruction is affected by intrinsic parameters of a light field camera significantly. In the paper, we propose a multi-projection-center (MPC) model with 6 intrinsic parameters to characterize light field cameras based on traditional two-parallel-plane (TPP) representation. The MPC model can generally parameterize light field in different imaging formations, including conventional and focused light field cameras. By the constraints of 4D ray and 3D geometry, a 3D projective transformation is deduced to describe the relationship between geometric structure and the MPC coordinates. Based on the MPC model and projective transformation, we propose a calibration algorithm to verify our light field camera model. Our calibration method includes a close-form solution and a non-linear optimization by minimizing re-projection errors. Experimental results on both simulated and real scene data have verified the performance of our algorithm.

Mantang Guo, Hao Zhu, Guoqing Zhou et al.

A light field records numerous light rays from a real-world scene. However, capturing a dense light field by existing devices is a time-consuming process. Besides, reconstructing a large amount of light rays equivalent to multiple light fields using sparse sampling arises a severe challenge for existing methods. In this paper, we present a learning based method to reconstruct multiple novel light fields between two mutually independent light fields. We indicate that light rays distributed in different light fields have the same consistent constraints under a certain condition. The most significant constraint is a depth related correlation between angular and spatial dimensions. Our method avoids working out the error-sensitive constraint by employing a deep neural network. We solve residual values of pixels on epipolar plane image (EPI) to reconstruct novel light fields. Our method is able to reconstruct 2 to 4 novel light fields between two mutually independent input light fields. We also compare our results with those yielded by a number of alternatives elsewhere in the literature, which shows our reconstructed light fields have better structure similarity and occlusion relationship.

Chunping Zhang, Zhe Ji, Qing Wang

The plenoptic camera can capture both angular and spatial information of the rays, enabling 3D reconstruction by single exposure. The geometry of the recovered scene structure is affected by the calibration of the plenoptic camera significantly. In this paper, we propose a novel unconstrained two-parallel-plane (TPP) model with 7 parameters to describe a 4D light field. By reconstructing scene points from ray-ray association, a 3D projective transformation is deduced to establish the relationship between the scene structure and the TPP parameters. Based on the transformation, we simplify the focused plenoptic camera as a TPP model and calibrate its intrinsic parameters. Our calibration method includes a close-form solution and a nonlinear optimization by minimizing re-projection error. Experiments on both simulated data and real scene data verify the performance of the calibration on the focused plenoptic camera.