paper-with-me

Papers

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

2024-10-08 · Tianyuan Zhang, Zhengfei Kuang, Haian Jin, Zexiang Xu, Sai Bi, Hao Tan, He Zhang, Yiwei Hu, Milos Hasan, William T. Freeman, Kai Zhang, Fujun Luan

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/.

📄 PDF Abstract BibTeX arXiv:2410.06231

Code (0)

등록된 구현이 없습니다.

Tasks

Inverse Rendering

Similar Papers 제목 키워드 기반

Relightable Full-Body Gaussian Codec Avatars

2025-01-24 · Shaofei Wang, Tomas Simon, Igor Santesteban, Timur Bagautdinov 외

We propose Relightable Full-Body Gaussian Codec Avatars, a new approach for modeling relightable full-body avatars with fine-grained details including face and hands. The unique challenge for relighting full-body avatars…

A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesis

2024-09-13 · Yohan Poirier-Ginter, Alban Gauthier, Julien Philip, Jean-Francois Lalonde 외

Relighting radiance fields is severely underconstrained for multi-view data, which is most often captured under a single illumination condition; It is especially hard for full scenes containing multiple objects. We intro…

URAvatar: Universal Relightable Gaussian Codec Avatars

2024-10-31 · Junxuan Li, Chen Cao, Gabriel Schwartz, Rawal Khirodkar 외

We present a new approach to creating photorealistic and relightable head avatars from a phone scan with unknown illumination. The reconstructed avatars can be animated and relit in real time with the global illumination…

Inverse Rendering

RISE-SDF: a Relightable Information-Shared Signed Distance Field for Glossy Object Inverse Rendering

2024-09-30 · Deheng Zhang, Jingyu Wang, Shaofei Wang, Marko Mihajlovic 외

In this paper, we propose a novel end-to-end relightable neural inverse rendering system that achieves high-quality reconstruction of geometry and material properties, thus enabling high-quality relighting. The cornersto…

Inverse Rendering

LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fields

2025-01-01 · CVPR 2025 1 · Zhengqin Li, Dilin Wang, Ka Chen, Zhaoyang Lv 외

We present Large Inverse Rendering Model (LIRM), a transformer architecture that jointly reconstructs high-quality shape, materials, and radiance fields with view-dependent effects in less than a second. Our model bu…

3D ReconstructionInverse RenderingMulti-View 3D Reconstruction