works on

From the 1 of 7 linked papers with an AI index.

activity
20242026
collaborators

8 papers

cs.CV2026

HandFlow: Fully Generative 4D Hand Recovery with Flow Matching

Mingxi Xu, Bowen Duan, Yi Gu +3

The paper introduces HandFlow, a fully generative flow‑matching framework that reconstructs temporally coherent 3D hand pose and shape from monocular video using ODE integration an…

cs.LG2026

MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy

Jiaxu Wang, Junhao He, Jingkai Sun +5

Learning real-world dynamics from visual observations is crucial for various domains. A common strategy is to calibrate simulators by estimating physical parameters, yet accuracy i…

cs.CV2025

DEGS: Deformable Event-based 3D Gaussian Splatting from RGB and Event Stream

Junhao He, Jiaxu Wang, Jia Li +7

Reconstructing Dynamic 3D Gaussian Splatting (3DGS) from low-framerate RGB videos is challenging. This is because large inter-frame motions will increase the uncertainty of the sol…

cs.CV2025

FixingGS: Enhancing 3D Gaussian Splatting via Training-Free Score Distillation

Zhaorui Wang, Yi Gu, Deming Zhou +1

Recently, 3D Gaussian Splatting (3DGS) has demonstrated remarkable success in 3D reconstruction and novel view synthesis. However, reconstructing 3D scenes from sparse viewpoints r…

gr-qc2025

Learning Null Geodesics for Gravitational Lensing Rendering in General Relativity

Mingyuan Sun, Zheng Fang, Jiaxu Wang +3

We present GravLensX, an innovative method for rendering black holes with gravitational lensing effects using neural networks. The methodology involves training neural networks to…

cs.CV2024

Robust SG-NeRF: Robust Scene Graph Aided Neural Surface Reconstruction

Yi Gu, Dongjun Ye, Zhaorui Wang +3

Neural surface reconstruction relies heavily on accurate camera poses as input. Despite utilizing advanced pose estimators like COLMAP or ARKit, camera poses can still be noisy. Ex…