arXiv subjects

Weiwei Xu

Publications and source records attributed to Weiwei Xu.

At least 55 records · Page 3Linked to original sources

arXiv2025

VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework

Existing for audio- and pose-driven human animation methods often struggle with stiff head movements and blurry hands, primarily due to the weak correlation between audio and head movements and the structural complexity of hands. To address these issues, we propose VividAnimator, an end-to-end framework for generating high-quality, half-body human animations driven by audio and sparse hand pose conditions. Our framework introduces three key innovations. First, to overcome the instability and high cost of online codebook training, we pre-train a Hand Clarity Codebook (HCC) that encodes rich, high-fidelity hand texture priors, significantly mitigating hand degradation. Second, we design a Dual-Stream Audio-Aware Module (DSAA) to model lip synchronization and natural head pose dynamics separately while enabling interaction. Third, we introduce a Pose Calibration Trick (PCT) that refines and aligns pose conditions by relaxing rigid constraints, ensuring smooth and natural gesture transitions. Extensive experiments demonstrate that Vivid Animator achieves state-of-the-art performance, producing videos with superior hand detail, gesture realism, and identity consistency, validated by both quantitative metrics and qualitative evaluations.

cs.CV↗

arXiv2025

UniTransfer: Video Concept Transfer via Progressive Spatial and Timestep Decomposition

We propose a novel architecture UniTransfer, which introduces both spatial and diffusion timestep decomposition in a progressive paradigm, achieving precise and controllable video concept transfer. Specifically, in terms of spatial decomposition, we decouple videos into three key components: the foreground subject, the background, and the motion flow. Building upon this decomposed formulation, we further introduce a dual-to-single-stream DiT-based architecture for supporting fine-grained control over different components in the videos. We also introduce a self-supervised pretraining strategy based on random masking to enhance the decomposed representation learning from large-scale unlabeled video data. Inspired by the Chain-of-Thought reasoning paradigm, we further revisit the denoising diffusion process and propose a Chain-of-Prompt (CoP) mechanism to achieve the timestep decomposition. We decompose the denoising process into three stages of different granularity and leverage large language models (LLMs) for stage-specific instructions to guide the generation progressively. We also curate an animal-centric video dataset called OpenAnimal to facilitate the advancement and benchmarking of research in video concept transfer. Extensive experiments demonstrate that our method achieves high-quality and controllable video concept transfer across diverse reference images and scenes, surpassing existing baselines in both visual fidelity and editability. Web Page: https://yu-shaonian.github.io/UniTransfer-Web/

cs.CV↗

arXiv2025

MotionFlow:Learning Implicit Motion Flow for Complex Camera Trajectory Control in Video Generation

Generating videos guided by camera trajectories poses significant challenges in achieving consistency and generalizability, particularly when both camera and object motions are present. Existing approaches often attempt to learn these motions separately, which may lead to confusion regarding the relative motion between the camera and the objects. To address this challenge, we propose a novel approach that integrates both camera and object motions by converting them into the motion of corresponding pixels. Utilizing a stable diffusion network, we effectively learn reference motion maps in relation to the specified camera trajectory. These maps, along with an extracted semantic object prior, are then fed into an image-to-video network to generate the desired video that can accurately follow the designated camera trajectory while maintaining consistent object motions. Extensive experiments verify that our model outperforms SOTA methods by a large margin.

cs.CV↗

arXiv2025

StableIntrinsic: Detail-preserving One-step Diffusion Model for Multi-view Material Estimation

Recovering material information from images has been extensively studied in computer graphics and vision. Recent works in material estimation leverage diffusion model showing promising results. However, these diffusion-based methods adopt a multi-step denoising strategy, which is time-consuming for each estimation. Such stochastic inference also conflicts with the deterministic material estimation task, leading to a high variance estimated results. In this paper, we introduce StableIntrinsic, a one-step diffusion model for multi-view material estimation that can produce high-quality material parameters with low variance. To address the overly-smoothing problem in one-step diffusion, StableIntrinsic applies losses in pixel space, with each loss designed based on the properties of the material. Additionally, StableIntrinsic introduces a Detail Injection Network (DIN) to eliminate the detail loss caused by VAE encoding, while further enhancing the sharpness of material prediction results. The experimental results indicate that our method surpasses the current state-of-the-art techniques by achieving a $9.9\%$ improvement in the Peak Signal-to-Noise Ratio (PSNR) of albedo, and by reducing the Mean Square Error (MSE) for metallic and roughness by $44.4\%$ and $60.0\%$, respectively.

cs.CV↗

arXiv2025

Enhanced Velocity Field Modeling for Gaussian Video Reconstruction

High-fidelity 3D video reconstruction is essential for enabling real-time rendering of dynamic scenes with realistic motion in virtual and augmented reality (VR/AR). The deformation field paradigm of 3D Gaussian splatting has achieved near-photorealistic results in video reconstruction due to the great representation capability of deep deformation networks. However, in videos with complex motion and significant scale variations, deformation networks often overfit to irregular Gaussian trajectories, leading to suboptimal visual quality. Moreover, the gradient-based densification strategy designed for static scene reconstruction proves inadequate to address the absence of dynamic content. In light of these challenges, we propose a flow-empowered velocity field modeling scheme tailored for Gaussian video reconstruction, dubbed FlowGaussian-VR. It consists of two core components: a velocity field rendering (VFR) pipeline which enables optical flow-based optimization, and a flow-assisted adaptive densification (FAD) strategy that adjusts the number and size of Gaussians in dynamic regions. We validate our model's effectiveness on multi-view dynamic reconstruction and novel view synthesis with multiple real-world datasets containing challenging motion scenarios, demonstrating not only notable visual improvements (over 2.5 dB gain in PSNR) and less blurry artifacts in dynamic textures, but also regularized and trackable per-Gaussian trajectories.

cs.CV↗

arXiv2025

Neural Shell Texture Splatting: More Details and Fewer Primitives

Gaussian splatting techniques have shown promising results in novel view synthesis, achieving high fidelity and efficiency. However, their high reconstruction quality comes at the cost of requiring a large number of primitives. We identify this issue as stemming from the entanglement of geometry and appearance in Gaussian Splatting. To address this, we introduce a neural shell texture, a global representation that encodes texture information around the surface. We use Gaussian primitives as both a geometric representation and texture field samplers, efficiently splatting texture features into image space. Our evaluation demonstrates that this disentanglement enables high parameter efficiency, fine texture detail reconstruction, and easy textured mesh extraction, all while using significantly fewer primitives.

cs.GR↗

arXiv2025

A Comparative Study of Halo Mass Estimates from Group Catalogs and Lensing Signals

We compare halo mass estimates from three galaxy group catalogs (redMaPPer, Yang21, and Zou21) with those derived from gravitational lensing measurements. Each catalog employs distinct methodologies, including mass-richness relations, abundance matching, and luminosity-based calibration. A linear correlation is observed between catalog-estimated and lensing-derived masses. The redMaPPer catalog shows the best agreement, especially for lower-redshift groups, with minor deviations in higher-redshift bins. Yang21 is the only catalog containing low mass groups, which gives a reasonably good mass estimation, except for the lowest mass bin. Cross-matched groups between redMaPPer and Yang21 reveal the former catalog provides more accurate mass estimation, while the Yang21 makes under-estimation of halo mass for those sharing the central galaxy with redMaPPer and over-estimation of halo mass for those with different center determination with redMaPPer and for the unique Yang21 groups. These findings emphasize the importance of redshift-dependent calibration and refined group definitions for accurate mass estimation.

astro-ph.CO↗

arXiv2025

SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations

Novel view synthesis (NVS) boosts immersive experiences in computer vision and graphics. Existing techniques, though progressed, rely on dense multi-view observations, restricting their application. This work takes on the challenge of reconstructing photorealistic 3D scenes from sparse or single-view inputs. We introduce SpatialCrafter, a framework that leverages the rich knowledge in video diffusion models to generate plausible additional observations, thereby alleviating reconstruction ambiguity. Through a trainable camera encoder and an epipolar attention mechanism for explicit geometric constraints, we achieve precise camera control and 3D consistency, further reinforced by a unified scale estimation strategy to handle scale discrepancies across datasets. Furthermore, by integrating monocular depth priors with semantic features in the video latent space, our framework directly regresses 3D Gaussian primitives and efficiently processes long-sequence features using a hybrid network structure. Extensive experiments show our method enhances sparse view reconstruction and restores the realistic appearance of 3D scenes.

cs.CV↗

arXiv2025

A Novel Adaptive Low-Rank Matrix Approximation Method for Image Compression and Reconstruction

Low-rank matrix approximation plays an important role in various applications such as image processing, signal processing and data analysis. The existing methods require a guess of the ranks of matrices that represent images or involve additional costs to determine the ranks. A novel efficient orthogonal decomposition with automatic basis extraction (EOD-ABE) is proposed to compute the optimal low-rank matrix approximation with adaptive identification of the optimal rank. By introducing a randomized basis extraction mechanism, EOD-ABE eliminates the need for additional rank determination steps and can compute a rank-revealing approximation to a low-rank matrix. With a computational complexity of $O(mnr)$, where $m$ and $n$ are the dimensions of the matrix and $r$ is its rank, EOD-ABE achieves significant speedups compared to the state-of-the-art methods. Experimental results demonstrate the superior speed, accuracy and robustness of EOD-ABE and indicate that EOD-ABE is a powerful tool for fast image compression and reconstruction and hyperspectral image dimensionality reduction in large-scale applications.

math.NA↗

arXiv2025

XMM-Newton follow-up of a sample of apparent low surface brightness galaxy groups detected in the ROSAT All-Sky Survey

Galaxy cluster cosmology relies on complete and pure samples spanning a large range of masses and redshifts. In Xu et al. (2018) and Xu et al. (2022), we discovered an apparently new population of galaxy groups and clusters with, on average, flatter X-ray surface brightness profiles than known clusters; this cluster population was missed in previous cluster surveys. The discovery of such a new class of objects could have a significant impact on cosmological applications of galaxy clusters. In this work we use a subsample of these systems to assess whether they belong to a new population. We follow up three of these galaxy groups and clusters with high-quality XMM-Newton observations. We produce clean images and spectra and use them for model fitting. We also identify known galaxies, groups, or clusters in the field. The observations reveal that all three systems are composed of multiple groups each, either at the same or at different redshifts. In total, we characterize nine groups. We measure flat surface brightness profiles with slope parameter $β< 0.6$; i.e, less than the canonical $β= 2/3$. For the two main central groups, we even measure $β< 0.4$. When the fluxes for the three observations are split up across the nine identified groups, none of them exceeds the typical flux limit adopted in previous RASS cluster catalogs, $\approx 3 \times 10^{-12}\,\mathrm{erg s^{-1}cm^{-2}}$ in the 0.1$-$2.4 keV energy band. The observations reveal that groups with flat surface brightness profiles exist. Whether they form a new, separate population requires additional follow-up observations of further systems from the Xu et al. sample, given the complexity we have discovered. Such extended low surface brightness systems, as well as multiple systems and projection effects, need to be taken into account when determining selection functions of group and cluster samples.

astro-ph.CO↗

arXiv2025

JGS2: Near Second-order Converging Jacobi/Gauss-Seidel for GPU Elastodynamics

In parallel simulation, convergence and parallelism are often seen as inherently conflicting objectives. Improved parallelism typically entails lighter local computation and weaker coupling, which unavoidably slow the global convergence. This paper presents a novel GPU algorithm that achieves convergence rates comparable to fullspace Newton's method while maintaining good parallelizability just like the Jacobi method. Our approach is built on a key insight into the phenomenon of overshoot. Overshoot occurs when a local solver aggressively minimizes its local energy without accounting for the global context, resulting in a local update that undermines global convergence. To address this, we derive a theoretically second-order optimal solution to mitigate overshoot. Furthermore, we adapt this solution into a pre-computable form. Leveraging Cubature sampling, our runtime cost is only marginally higher than the Jacobi method, yet our algorithm converges nearly quadratically as Newton's method. We also introduce a novel full-coordinate formulation for more efficient pre-computation. Our method integrates seamlessly with the incremental potential contact method and achieves second-order convergence for both stiff and soft materials. Experimental results demonstrate that our approach delivers high-quality simulations and outperforms state-of-the-art GPU methods with 50 to 100 times better convergence.

cs.GR↗

arXiv2025

Accelerating Randomized Algorithms for Low-Rank Matrix Approximation

Randomized algorithms are overwhelming methods for low-rank approximation that can alleviate the computational expenditure with great reliability compared to deterministic algorithms. A crucial thought is generating a standard Gaussian matrix $\mathbf{G}$ and subsequently obtaining the orthonormal basis of the range of $\mathbf{AG}$ for a given matrix $\mathbf{A}$. Recently, the \texttt{farPCA} algorithm offers a framework for randomized algorithms, but the dense Gaussian matrix remains computationally expensive. Motivated by this, we introduce the standardized Bernoulli, sparse sign, and sparse Gaussian matrices to replace the standard Gaussian matrix in \texttt{farPCA} for accelerating computation. These three matrices possess a low computational expenditure in matrix-matrix multiplication and converge in distribution to a standard Gaussian matrix when multiplied by an orthogonal matrix under a mild condition. Therefore, the three corresponding proposed algorithms can serve as a superior alternative to fast adaptive randomized PCA (\texttt{farPCA}). Finally, we leverage random matrix theory (RMT) to derive a tighter error bound for \texttt{farPCA} without shifted techniques. Additionally, we extend this improved error bound to the error analysis of our three fast algorithms, ensuring that the proposed methods deliver more accurate approximations for large-scale matrices. Numerical experiments validate that the three algorithms achieve asymptotically the same performance as \texttt{farPCA} but with lower costs, offering a more efficient approach to low-rank matrix approximation.

stat.CO↗

arXiv2025

A Learning-Based Inexact ADMM for Solving Quadratic Programs

Convex quadratic programs (QPs) constitute a fundamental computational primitive across diverse domains including financial optimization, control systems, and machine learning. The alternating direction method of multipliers (ADMM) has emerged as a preferred first-order approach due to its iteration efficiency - exemplified by the state-of-the-art OSQP solver. Machine learning-enhanced optimization algorithms have recently demonstrated significant success in speeding up the solving process. This work introduces a neural-accelerated ADMM variant that replaces exact subproblem solutions with learned approximations through a parameter-efficient Long Short-Term Memory (LSTM) network. We derive convergence guarantees within the inexact ADMM formalism, establishing that our learning-augmented method maintains primal-dual convergence while satisfying residual thresholds. Extensive experimental results demonstrate that our approach achieves superior solution accuracy compared to existing learning-based methods while delivering significant computational speedups of up to $7\times$, $28\times$, and $22\times$ over Gurobi, SCS, and OSQP, respectively. Furthermore, the proposed method outperforms other learning-to-optimize methods in terms of solution quality. Detailed performance analysis confirms near-perfect compliance with the theoretical assumptions, consequently ensuring algorithm convergence.

math.OC↗

arXiv2025

BuildingBlock: A Hybrid Approach for Structured Building Generation

Three-dimensional building generation is vital for applications in gaming, virtual reality, and digital twins, yet current methods face challenges in producing diverse, structured, and hierarchically coherent buildings. We propose BuildingBlock, a hybrid approach that integrates generative models, procedural content generation (PCG), and large language models (LLMs) to address these limitations. Specifically, our method introduces a two-phase pipeline: the Layout Generation Phase (LGP) and the Building Construction Phase (BCP). LGP reframes box-based layout generation as a point-cloud generation task, utilizing a newly constructed architectural dataset and a Transformer-based diffusion model to create globally consistent layouts. With LLMs, these layouts are extended into rule-based hierarchical designs, seamlessly incorporating component styles and spatial structures. The BCP leverages these layouts to guide PCG, enabling local-customizable, high-quality structured building generation. Experimental results demonstrate BuildingBlock's effectiveness in generating diverse and hierarchically structured buildings, achieving state-of-the-art results on multiple benchmarks, and paving the way for scalable and intuitive architectural workflows.

cs.GR↗

arXiv2025

DecoupledGaussian: Object-Scene Decoupling for Physics-Based Interaction

We present DecoupledGaussian, a novel system that decouples static objects from their contacted surfaces captured in-the-wild videos, a key prerequisite for realistic Newtonian-based physical simulations. Unlike prior methods focused on synthetic data or elastic jittering along the contact surface, which prevent objects from fully detaching or moving independently, DecoupledGaussian allows for significant positional changes without being constrained by the initial contacted surface. Recognizing the limitations of current 2D inpainting tools for restoring 3D locations, our approach proposes joint Poisson fields to repair and expand the Gaussians of both objects and contacted scenes after separation. This is complemented by a multi-carve strategy to refine the object's geometry. Our system enables realistic simulations of decoupling motions, collisions, and fractures driven by user-specified impulses, supporting complex interactions within and across multiple scenes. We validate DecoupledGaussian through a comprehensive user study and quantitative benchmarks. This system enhances digital interaction with objects and scenes in real-world environments, benefiting industries such as VR, robotics, and autonomous driving. Our project page is at: https://wangmiaowei.github.io/DecoupledGaussian.github.io/.

cs.GR↗

arXiv2025

Fine-Grained Controllable Apparel Showcase Image Generation via Garment-Centric Outpainting

In this paper, we propose a novel garment-centric outpainting (GCO) framework based on the latent diffusion model (LDM) for fine-grained controllable apparel showcase image generation. The proposed framework aims at customizing a fashion model wearing a given garment via text prompts and facial images. Different from existing methods, our framework takes a garment image segmented from a dressed mannequin or a person as the input, eliminating the need for learning cloth deformation and ensuring faithful preservation of garment details. The proposed framework consists of two stages. In the first stage, we introduce a garment-adaptive pose prediction model that generates diverse poses given the garment. Then, in the next stage, we generate apparel showcase images, conditioned on the garment and the predicted poses, along with specified text prompts and facial images. Notably, a multi-scale appearance customization module (MS-ACM) is designed to allow both overall and fine-grained text-based control over the generated model's appearance. Moreover, we leverage a lightweight feature fusion operation without introducing any extra encoders or modules to integrate multiple conditions, which is more efficient. Extensive experiments validate the superior performance of our framework compared to state-of-the-art methods.

cs.CV↗

arXiv2025

LiCoEval: Evaluating LLMs on License Compliance in Code Generation

Recent advances in Large Language Models (LLMs) have revolutionized code generation, leading to widespread adoption of AI coding tools by developers. However, LLMs can generate license-protected code without providing the necessary license information, leading to potential intellectual property violations during software production. This paper addresses the critical, yet underexplored, issue of license compliance in LLM-generated code by establishing a benchmark to evaluate the ability of LLMs to provide accurate license information for their generated code. To establish this benchmark, we conduct an empirical study to identify a reasonable standard for "striking similarity" that excludes the possibility of independent creation, indicating a copy relationship between the LLM output and certain open-source code. Based on this standard, we propose LiCoEval, to evaluate the license compliance capabilities of LLMs, i.e., the ability to provide accurate license or copyright information when they generate code with striking similarity to already existing copyrighted code. Using LiCoEval, we evaluate 14 popular LLMs, finding that even top-performing LLMs produce a non-negligible proportion (0.88% to 2.01%) of code strikingly similar to existing open-source implementations. Notably, most LLMs fail to provide accurate license information, particularly for code under copyleft licenses. These findings underscore the urgent need to enhance LLM compliance capabilities in code generation tasks. Our study provides a foundation for future research and development to improve license compliance in AI-assisted software development, contributing to both the protection of open-source software copyrights and the mitigation of legal risks for LLM users.

cs.SE↗

arXiv2025

OmniSR: Shadow Removal under Direct and Indirect Lighting

Shadows can originate from occlusions in both direct and indirect illumination. Although most current shadow removal research focuses on shadows caused by direct illumination, shadows from indirect illumination are often just as pervasive, particularly in indoor scenes. A significant challenge in removing shadows from indirect illumination is obtaining shadow-free images to train the shadow removal network. To overcome this challenge, we propose a novel rendering pipeline for generating shadowed and shadow-free images under direct and indirect illumination, and create a comprehensive synthetic dataset that contains over 30,000 image pairs, covering various object types and lighting conditions. We also propose an innovative shadow removal network that explicitly integrates semantic and geometric priors through concatenation and attention mechanisms. The experiments show that our method outperforms state-of-the-art shadow removal techniques and can effectively generalize to indoor and outdoor scenes under various lighting conditions, enhancing the overall effectiveness and applicability of shadow removal methods.

cs.CV↗