17 papers
HiMat: DiT-based Ultra-High Resolution SVBRDF Generation
Zixiong Wang, Jian Yang, Yiwei Hu +2
Creating ultra-high-resolution spatially varying bidirectional reflectance functions (SVBRDFs) is critical for photorealistic 3D content creation, to faithfully represent fine-scal…
GS-ROR: Bidirectional-guided 3DGS and SDF for Reflective Object Relighting and Reconstruction
Zuo-Liang Zhu, Beibei Wang, Jian Yang
3D Gaussian Splatting (3DGS) has shown a powerful capability for novel view synthesis due to its detailed expressive ability and highly efficient rendering speed. Unfortunately, cr…
SRUG: Shadow-Guided Relightable Urban Scene with Generation Model
Yonghao Zhao, Zexin Yin, Jian Yang +2
Creating relightable urban scenes from images or videos is widely useful but highly ill-posed. Urban environments are typically unbounded and extend beyond the visible regions. As…
F-RNG: Feed-Forward Relightable Neural Gaussians
Guangming Fu, Jiahui Fan, Jian Yang +2
Capturing relightable 3D assets from real-world objects is a widely researched problem. Several per-scene optimization-based methods, based on 3D Gaussian splatting (3DGS), support…
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…
Toward Visually Realistic Simulation: A Benchmark for Evaluating Robot Manipulation in Simulation
Yixin Zhu, Zixiong Wang, Jian Yang +4
Reliable simulation evaluation of robot manipulation policies serves as a high-fidelity proxy for real-world performance. Although existing benchmarks cover a wide range of task ca…