12 papers
LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation
Ziqi Ma, Shreya Sharma, Mohamed El Banani +8
Camera-controlled video models are rapidly advancing toward long generation horizons and complex camera control. A key failure mode is 3D inconsistency: as the camera moves, object…
Monocular Avatar Reconstruction via Cascaded Diffusion Priors and UV-Space Differentiable Shading
Hong Li, Minqi Meng, Yanjun Liang +10
Reconstructing high-fidelity, relightable 3D avatars from a single in-the-wild image is a challenging ill-posed problem, primarily hindered by the scarcity of high-quality PBR data…
Relit-LiVE: Relight Video by Jointly Learning Environment Video
Weiqing Xiao, Hong Li, Xiuyu Yang +7
Recent advances have shown that large-scale video diffusion models can be repurposed as neural renderers by first decomposing videos into intrinsic scene representations and then p…
UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors
Houyuan Chen, Hong Li, Xianghao Kong +8
Recent progress has shown that video diffusion models (VDMs) can be repurposed for diverse multimodal graphics tasks. However, existing methods often train separate models for each…
Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation
Shaocong Xu, Songlin Wei, Qizhe Wei +12
Transparent objects remain notoriously hard for perception systems: refraction, reflection and transmission break the assumptions behind stereo, ToF and purely discriminative monoc…
Light-X: Generative 4D Video Rendering with Camera and Illumination Control
Tianqi Liu, Zhaoxi Chen, Zihao Huang +8
Recent advances in illumination control extend image-based methods to video, yet still facing a trade-off between lighting fidelity and temporal consistency. Moving beyond relighti…
NeAR: Coupled Neural Asset-Renderer Stack
Hong Li, Chongjie Ye, Houyuan Chen +12
Neural asset authoring and neural rendering have traditionally evolved as disjoint paradigms: one generates digital assets for fixed graphics pipelines, while the other maps conven…
One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation
Zheng Geng, Nan Wang, Shaocong Xu +5
Estimating the 6D pose of arbitrary unseen objects from a single reference image is critical for robotics operating in the long-tail of real-world instances. However, this setting…
Light of Normals: Unified Feature Representation for Universal Photometric Stereo
Houyuan Chen, Hong Li, Chongjie Ye +11
Universal photometric stereo (PS) is defined by two factors: it must (i) operate under arbitrary, unknown lighting conditions and (ii) avoid reliance on specific illumination model…
Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting
Nan Wang, Yuantao Chen, Lixing Xiao +11
Neural rendering techniques, including NeRF and Gaussian Splatting (GS), rely on photometric consistency to produce high-quality reconstructions. However, in real-world scenarios,…
ORV: 4D Occupancy-centric Robot Video Generation
Xiuyu Yang, Bohan Li, Shaocong Xu +9
Recent embodied intelligence suffers from data scarcity, while conventional simulators lack visual realism. Controllable video generation is emerging as a promising data engine, ye…
OccluGaussian: Occlusion-Aware Gaussian Splatting for Large Scene Reconstruction and Rendering
Shiyong Liu, Xiao Tang, Zhihao Li +6
In large-scale scene reconstruction using 3D Gaussian splatting, it is common to partition the scene into multiple smaller regions and reconstruct them individually. However, exist…