RelitLRM: Generative Relightable Radiance for Large Reconstruction Models
원문 초록
We propose RelitLRM, a Large Reconstruction Model (LRM) for generating high-quality Gaussian splatting representations of 3D objects under novel illuminations from sparse (4-8) posed images captured under unknown static lighting. Unlike prior inverse rendering methods requiring dense captures and slow optimization, often causing artifacts like incorrect highlights or shadow baking, RelitLRM adopts a feed-forward transformer-based model with a novel combination of a geometry reconstructor and a relightable appearance generator based on diffusion. The model is trained end-to-end on synthetic multi-view renderings of objects under varying known illuminations. This architecture design enables to effectively decompose geometry and appearance, resolve the ambiguity between material and lighting, and capture the multi-modal distribution of shadows and specularity in the relit appearance. We show our sparse-view feed-forward RelitLRM offers competitive relighting results to state-of-the-art dense-view optimization-based baselines while being significantly faster. Our project page is available at: https://relit-lrm.github.io/.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
TextureSplat: Per-Primitive Texture Mapping for Reflective Gaussian Splatting
SVG-IR: Spatially-Varying Gaussian Splatting for Inverse Rendering
TensoFlow: Tensorial Flow-based Sampler for Inverse Rendering
Shadow Art Kanji: Inverse Rendering Application
ROSA: Reconstructing Object Shape and Appearance Textures by Adaptive Detail Transfer
Materialist: Physically Based Editing Using Single-Image Inverse Rendering
토론
이 논문과 연결된 포럼 글이 아직 없습니다.