# RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

arXiv: https://arxiv.org/abs/2410.06231 · HTML: https://mlsanity.com/paper/2410.06231/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 60 references that are in the map.
- First posted on arXiv 8 Oct 2024.

## Builds on (most cited first, 30 of 50)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [On Layer Normalization in the Transformer Architecture](https://mlsanity.com/paper/2002.04745/) (2020)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis](https://mlsanity.com/paper/2012.03927/) (2020)
- [NeRD: Neural Reflectance Decomposition from Image Collections](https://mlsanity.com/paper/2012.03918/) (2020)
- [Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model](https://mlsanity.com/paper/2311.06214/) (2023)
- [GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting](https://mlsanity.com/paper/2404.19702/) (2024)
- [PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting](https://mlsanity.com/paper/2104.00674/) (2021)
- [GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces](https://mlsanity.com/paper/2311.17977/) (2023)
- [GS-IR: 3D Gaussian Splatting for Inverse Rendering](https://mlsanity.com/paper/2311.16473/) (2023)
- [Photographic Image Synthesis with Cascaded Refinement Networks](https://mlsanity.com/paper/1707.09405/) (2017)
- [DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model](https://mlsanity.com/paper/2311.09217/) (2023)
- [Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition](https://mlsanity.com/paper/2110.14373/) (2021)
- [Neural Reflectance Fields for Appearance Acquisition](https://mlsanity.com/paper/2008.03824/) (2020)
- [Modeling Indirect Illumination for Inverse Rendering](https://mlsanity.com/paper/2204.06837/) (2022)
- [TensoIR: Tensorial Inverse Rendering](https://mlsanity.com/paper/2304.12461/) (2023)
- [PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction](https://mlsanity.com/paper/2311.12024/) (2023)
- [Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising](https://mlsanity.com/paper/2206.03380/) (2022)
- [RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation](https://mlsanity.com/paper/2211.09869/) (2022)

## Built on by (most cited first, 23 of 23)

- [RayZer: A Self-supervised Large View Synthesis Model](https://mlsanity.com/paper/2505.00702/) (2025)
- [UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting](https://mlsanity.com/paper/2506.15673/) (2025)
- [MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data](https://mlsanity.com/paper/2412.14166/) (2024)
- [LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fields](https://mlsanity.com/paper/2504.20026/) (2025)
- [LightSwitch: Multi-view Relighting with Material-guided Diffusion](https://mlsanity.com/paper/2508.06494/) (2025)
- [Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation](https://mlsanity.com/paper/2412.15211/) (2024)
- [ROGR: Relightable 3D Objects using Generative Relighting](https://mlsanity.com/paper/2510.03163/) (2025)
- [SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training](https://mlsanity.com/paper/2512.05354/) (2025)
- [NeAR: Coupled Neural Asset-Renderer Stack](https://mlsanity.com/paper/2511.18600/) (2025)
- [Large Material Gaussian Model for Relightable 3D Generation](https://mlsanity.com/paper/2509.22112/) (2025)
- [LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows](https://mlsanity.com/paper/2604.05182/) (2026)
- [GAINS: Gaussian-based Inverse Rendering from Sparse Multi-View Captures](https://mlsanity.com/paper/2512.09925/) (2025)
- [TokenLight: Precise Lighting Control in Images using Attribute Tokens](https://mlsanity.com/paper/2604.15310/) (2026)
- [F-RNG: Feed-Forward Relightable Neural Gaussians](https://mlsanity.com/paper/2605.25975/) (2026)
- [HorizonRelight: Relighting Long-horizon Videos Consistently via Diffusion Transformers](https://mlsanity.com/paper/2606.29095/) (2026)
- [EgoRelight: Egocentric Human Capture and Illumination Recovery for Relightable and Photoreal Avatar Rendering](https://mlsanity.com/paper/2605.28401/) (2026)
- [TRON: Tracing Rays to Orchestrate a Neural Renderer for 3D Gaussian Reconstructions](https://mlsanity.com/paper/2606.11314/) (2026)
- [Extracting Neural Materials from Images](https://mlsanity.com/paper/2606.26715/) (2026)
- [Diffusion-Based Material Regularization for Physics-Based Inverse Rendering](https://mlsanity.com/paper/2606.31065/) (2026)
- [LumiTokens: 3D Relighting via Token-Space Lighting Transformation](https://mlsanity.com/paper/2608.18215/) (2026)
- [Luce: Relightable Gaussians for 3D Asset Generation](https://mlsanity.com/paper/2608.23943/) (2026)
- [RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting](https://mlsanity.com/paper/2609.07414/) (2026)
- [MapLightning: Online Vectorized HD Map Construction with 1D Map Tokens](https://mlsanity.com/paper/2610.01905/) (2026)

## Abstract (arXiv)

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/.