activity
20242026
collaborators

12 papers

cs.CV2026

LiveLight: Real-time Streaming Video Relighting with Interactive Control

Yue Ma, Jiangming Wang, Yucheng Wang +8

We present LiveLight, the first diffusion-based framework for real-time streaming video relighting with interactive 3D lighting control. Achieving this is non-trivial, as it requir…

cs.CV2026

GeoEdit: Geometry-Aware Object Editing via Dual-Branch Denoising

Yi He, Jiangming Wang, Xinyu Wang +5

Precisely manipulating objects in a single photograph (translation, rotation, scaling) while obeying 3D physical constraints remains unsolved for diffusion-based editors. Current 2…

cs.CV2026

GRAFT: Geometric Refinement and Fitting Transformer for Human Scene Reconstruction

Pradyumna YM, Yuxuan Xue, Yue Chen +3

Reconstructing physically plausible 3D human-scene interactions (HSI) from a single image currently presents a trade-off: optimization based methods offer accurate contact but are…

cs.CV2026

GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion Transformers

Yuxuan Xue, Ruofan Liang, Egor Zakharov +6

Relighting a person from a single photo is an attractive but ill-posed task, as a 2D image ambiguously entangles 3D geometry, intrinsic appearance, and illumination. Current method…

cs.CV2026

FastVMT: Eliminating Redundancy in Video Motion Transfer

Yue Ma, Zhikai Wang, Tianhao Ren +9

Video motion transfer aims to synthesize videos by generating visual content according to a text prompt while transferring the motion pattern observed in a reference video. Recent…

cs.CV2026

CamLit: Unified Video Diffusion with Explicit Camera and Lighting Control

Zhiyi Kuang, Chengan He, Egor Zakharov +6

We present CamLit, the first unified video diffusion model that jointly performs novel view synthesis (NVS) and relighting from a single input image. Given one reference image, a u…