3 papers
cs.GR2026
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…
cs.GR2025
Free Your Hands: Lightweight Turntable-Based Object Capture Pipeline
Jiahui Fan, Fujun Luan, Jian Yang +2
Novel view synthesis (NVS) from multiple captured photos of an object is a widely studied problem. Achieving high quality typically requires dense sampling of input views, which ca…
cs.CV2025
RNG: Relightable Neural Gaussians
Jiahui Fan, Fujun Luan, Jian Yang +2
3D Gaussian Splatting (3DGS) has shown impressive results for the novel view synthesis task, where lighting is assumed to be fixed. However, creating relightable 3D assets, especia…