# GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion Transformers

arXiv: https://arxiv.org/abs/2604.20715 · HTML: https://mlsanity.com/paper/2604.20715/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 28 of its 47 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 28 of 28)

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision](https://mlsanity.com/paper/2410.19115/) (2024)
- [MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details](https://mlsanity.com/paper/2507.02546/) (2025)
- [Sapiens: Foundation for Human Vision Models](https://mlsanity.com/paper/2408.12569/) (2024)
- [RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion models](https://mlsanity.com/paper/2405.00666/) (2024)
- [VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models](https://mlsanity.com/paper/2502.02492/) (2025)
- [DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation](https://mlsanity.com/paper/2402.11929/) (2024)
- [Neural Gaffer: Relighting Any Object via Diffusion](https://mlsanity.com/paper/2406.07520/) (2024)
- [Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis](https://mlsanity.com/paper/2505.09358/) (2025)
- [SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting](https://mlsanity.com/paper/2402.18848/) (2024)
- [Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction](https://mlsanity.com/paper/2504.07961/) (2025)
- [Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models](https://mlsanity.com/paper/2406.08475/) (2024)
- [LightLab: Controlling Light Sources in Images with Diffusion Models](https://mlsanity.com/paper/2505.09608/) (2025)
- [A Survey on Intrinsic Images: Delving Deep Into Lambert and Beyond](https://mlsanity.com/paper/2112.03842/) (2021)
- [CosmicMan: A Text-to-Image Foundation Model for Humans](https://mlsanity.com/paper/2404.01294/) (2024)
- [Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset](https://mlsanity.com/paper/2503.14485/) (2025)
- [SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces](https://mlsanity.com/paper/2501.09756/) (2025)
- [Relightable Full-Body Gaussian Codec Avatars](https://mlsanity.com/paper/2501.14726/) (2025)
- [NSF: Neural Surface Fields for Human Modeling from Monocular Depth](https://mlsanity.com/paper/2308.14847/) (2023)
- [GenLit: Reformulating Single-Image Relighting as Video Generation](https://mlsanity.com/paper/2412.11224/) (2024)
- [Event-based Non-Rigid Reconstruction from Contours](https://mlsanity.com/paper/2210.06270/) (2022)
- [Gen-3Diffusion: Realistic Image-to-3D Generation via 2D & 3D Diffusion Synergy](https://mlsanity.com/paper/2412.06698/) (2024)
- [PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image](https://mlsanity.com/paper/2510.11649/) (2025)
- [HumanOLAT: A Large-Scale Dataset for Full-Body Human Relighting and Novel-View Synthesis](https://mlsanity.com/paper/2508.09137/) (2025)

## Built on by (most cited first, 3 of 3)

- [LiveLight: Real-time Streaming Video Relighting with Interactive Control](https://mlsanity.com/paper/2608.01771/) (2026)
- [EasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX Generation](https://mlsanity.com/paper/2605.22051/) (2026)
- [Revisiting Avatar-As-Image: High-Fidelity Registration is All You Need](https://mlsanity.com/paper/2609.11722/) (2026)

## Abstract (arXiv)

Relighting a person from a single photo is an attractive but ill-posed task, as a 2D image ambiguously entangles 3D geometry, intrinsic appearance, and illumination. Current methods either use sequential pipelines that suffer from error accumulation, or they do not explicitly leverage 3D geometry during relighting, which limits physical consistency. Since relighting and estimation of 3D geometry are mutually beneficial tasks, we propose a unified Multi-Modal Diffusion Transformer (DiT) that jointly solves for both: GeoRelight. We make this possible through two key technical contributions: isotropic NDC-Orthographic Depth (iNOD), a distortion-free 3D representation compatible with latent diffusion models; and a strategic mixed-data training method that combines synthetic and auto-labeled real data. By solving geometry and relighting jointly, GeoRelight achieves better performance than both sequential models and previous systems that ignored geometry.