12 papers
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…
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…
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…
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…
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…
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…