1 citations · 1 across the 9 of their papers we have counts for
11 papers
Rollout-Marginal Distillation for Long-Horizon Autoregressive Video Generation
Chenjian Gao, Zhihao Hu, Jianqi Ma +3
Autoregressive (AR) video diffusion enables low-latency, streamable video generation, but prediction errors often accumulate over long rollouts. Training the generator on its own r…
Decoupled Illumination Priors for Spatially Controllable Multi-View Indoor Scene Relighting
Chenjian Gao, Linning Xu, Tianfan Xue
Indoor scene relighting demands photorealism, precise spatial control, and strict multi-view consistency. While diffusion-based image editing models enable semantic lighting manipu…
DynamicTree: Interactive Real Tree Animation via Sparse Voxel Spectrum
Yaokun Li, Lihe Ding, Xiao Chen +2
Generating dynamic and interactive 3D trees has wide applications in virtual reality, games, and world simulation. However, existing methods still face various challenges in genera…
FullPart: Generating each 3D Part at Full Resolution
Lihe Ding, Shaocong Dong, Yaokun Li +10
Part-based 3D generation holds great potential for various applications. Previous part generators that represent parts using implicit vector-set tokens often suffer from insufficie…
DiffIER: Optimizing Diffusion Models with Iterative Error Reduction
Ao Chen, Lihe Ding, Tianfan Xue
Diffusion models have demonstrated remarkable capabilities in generating high-quality samples and enhancing performance across diverse domains through Classifier-Free Guidance (CFG…
From Gallery to Wrist: Realistic 3D Bracelet Insertion in Videos
Chenjian Gao, Lihe Ding, Rui Han +3
Inserting 3D objects into videos is a longstanding challenge in computer graphics with applications in augmented reality, virtual try-on, and video composition. Achieving both temp…
From One to More: Contextual Part Latents for 3D Generation
Shaocong Dong, Lihe Ding, Xiao Chen +10
Recent advances in 3D generation have transitioned from multi-view 2D rendering approaches to 3D-native latent diffusion frameworks that exploit geometric priors in ground truth da…
LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning
Chenjian Gao, Lihe Ding, Xin Cai +3
Video editing using diffusion models has achieved remarkable results in generating high-quality edits for videos. However, current methods often rely on large-scale pretraining, li…
Interactive3D: Create What You Want by Interactive 3D Generation
Shaocong Dong, Lihe Ding, Zhanpeng Huang +3
3D object generation has undergone significant advancements, yielding high-quality results. However, fall short of achieving precise user control, often yielding results that do no…
Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors
Lihe Ding, Shaocong Dong, Zhanpeng Huang +5
Most 3D generation research focuses on up-projecting 2D foundation models into the 3D space, either by minimizing 2D Score Distillation Sampling (SDS) loss or fine-tuning on multi-…
Obj-NeRF: Extract Object NeRFs from Multi-view Images
Zhiyi Li, Lihe Ding, Tianfan Xue
Neural Radiance Fields (NeRFs) have demonstrated remarkable effectiveness in novel view synthesis within 3D environments. However, extracting a radiance field of one specific objec…