RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

• URL: http://arxiv.org/abs/2410.06231v2
• Date: Thu, 10 Oct 2024 05:41:49 GMT
• Title: RelitLRM: Generative Relightable Radiance for Large Reconstruction Models
• Authors: 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,
• Abstract summary: We propose RelitLRM for generating high-quality Gaussian splatting representations of 3D objects under novel illuminations. Unlike prior inverse rendering methods requiring dense captures and slow optimization, RelitLRM adopts a feed-forward transformer-based model. We show our sparse-view feed-forward RelitLRM offers competitive relighting results to state-of-the-art dense-view optimization-based baselines.
• Score: 52.672706620003765
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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/.

Related papers

• EnvGS: Modeling View-Dependent Appearance with Environment Gaussian [78.74634059559891]
  EnvGS is a novel approach that employs a set of Gaussian primitives as an explicit 3D representation for capturing reflections of environments. To efficiently render these environment Gaussian primitives, we developed a ray-tracing-based reflection that leverages the GPU's RT core for fast rendering. Results from multiple real-world and synthetic datasets demonstrate that our method produces significantly more detailed reflections.
  arXiv  Detail & Related papers  (2024-12-19T18:59:57Z)
• IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations [64.07859467542664]
  Capturing geometric and material information from images remains a fundamental challenge in computer vision and graphics. Traditional optimization-based methods often require hours of computational time to reconstruct geometry, material properties, and environmental lighting from dense multi-view inputs. We introduce IDArb, a diffusion-based model designed to perform intrinsic decomposition on an arbitrary number of images under varying illuminations.
  arXiv  Detail & Related papers  (2024-12-16T18:52:56Z)
• Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion [45.81230812844384]
  We present a novel framework that boosts intrinsic estimation by leveraging auxiliary multi-lighting conditions from 2D diffusion priors. We train a large G-buffer model with a U-Net backbone to accurately predict surface normals and materials.
  arXiv  Detail & Related papers  (2024-12-12T18:58:09Z)
• MIRReS: Multi-bounce Inverse Rendering using Reservoir Sampling [17.435649250309904]
  We present MIRReS, a novel two-stage inverse rendering framework. Our method extracts an explicit geometry (triangular mesh) in stage one, and introduces a more realistic physically-based inverse rendering model. Our method effectively estimates indirect illumination, including self-shadowing and internal reflections.
  arXiv  Detail & Related papers  (2024-06-24T07:00:57Z)
• GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement [51.97726804507328]
  We propose a novel approach for 3D mesh reconstruction from multi-view images. Our method takes inspiration from large reconstruction models that use a transformer-based triplane generator and a Neural Radiance Field (NeRF) model trained on multi-view images.
  arXiv  Detail & Related papers  (2024-06-09T05:19:24Z)
• NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illumination [48.42173911185454]
  Inverse rendering methods aim to estimate geometry, materials and illumination from multi-view RGB images. We propose an end-to-end inverse rendering pipeline that decomposes materials and illumination from multi-view images.
  arXiv  Detail & Related papers  (2023-03-29T12:05:19Z)
• Extracting Triangular 3D Models, Materials, and Lighting From Images [59.33666140713829]
  We present an efficient method for joint optimization of materials and lighting from multi-view image observations. We leverage meshes with spatially-varying materials and environment that can be deployed in any traditional graphics engine.
  arXiv  Detail & Related papers  (2021-11-24T13:58:20Z)
• DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer [78.91753256634453]
  We consider the challenging problem of predicting intrinsic object properties from a single image by exploiting differentiables. In this work, we propose DIBR++, a hybrid differentiable which supports these effects by combining specularization and ray-tracing. Compared to more advanced physics-based differentiables, DIBR++ is highly performant due to its compact and expressive model.
  arXiv  Detail & Related papers  (2021-10-30T01:59:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.