# RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion models

arXiv: https://arxiv.org/abs/2405.00666 · HTML: https://mlsanity.com/paper/2405.00666/

## Key facts

- Cited by 161 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 26 of its 49 references that are in the map.
- First posted on arXiv 1 May 2024.

## 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, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (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)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [PVT v2: Improved Baselines with Pyramid Vision Transformer](https://mlsanity.com/paper/2106.13797/) (2021)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://mlsanity.com/paper/2305.08891/) (2023)
- [Composer: Creative and Controllable Image Synthesis with Composable Conditions](https://mlsanity.com/paper/2302.09778/) (2023)
- [A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications](https://mlsanity.com/paper/2001.06937/) (2020)
- [Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Image](https://mlsanity.com/paper/1905.02722/) (2019)
- [MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation](https://mlsanity.com/paper/2307.14460/) (2023)
- [Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenes](https://mlsanity.com/paper/2304.03266/) (2023)
- [Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracing](https://mlsanity.com/paper/2211.03017/) (2022)
- [OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets](https://mlsanity.com/paper/2007.12868/) (2020)
- [Physically-Based Editing of Indoor Scene Lighting from a Single Image](https://mlsanity.com/paper/2205.09343/) (2022)
- [IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes](https://mlsanity.com/paper/2206.08423/) (2022)
- [Intrinsic Image Decomposition via Ordinal Shading](https://mlsanity.com/paper/2311.12792/) (2023)
- [Generative Models: What Do They Know? Do They Know Things? Let's Find Out!](https://mlsanity.com/paper/2311.17137/) (2023)
- [Self-supervised Outdoor Scene Relighting](https://mlsanity.com/paper/2107.03106/) (2021)
- [Deep Shading: Convolutional Neural Networks for Screen-Space Shading](https://mlsanity.com/paper/1603.06078/) (2016)
- [Alchemist: Parametric Control of Material Properties with Diffusion Models](https://mlsanity.com/paper/2312.02970/) (2023)
- [A Survey on Intrinsic Images: Delving Deep Into Lambert and Beyond](https://mlsanity.com/paper/2112.03842/) (2021)

## Built on by (most cited first, 30 of 161)

- [Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details](https://mlsanity.com/paper/2506.16504/) (2025)
- [Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis](https://mlsanity.com/paper/2505.09358/) (2025)
- [DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models](https://mlsanity.com/paper/2501.18590/) (2025)
- [Colorful Diffuse Intrinsic Image Decomposition in the Wild](https://mlsanity.com/paper/2409.13690/) (2024)
- [UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting](https://mlsanity.com/paper/2506.15673/) (2025)
- [LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relighting](https://mlsanity.com/paper/2412.00177/) (2024)
- [LightLab: Controlling Light Sources in Images with Diffusion Models](https://mlsanity.com/paper/2505.09608/) (2025)
- [Material Anything: Generating Materials for Any 3D Object via Diffusion](https://mlsanity.com/paper/2411.15138/) (2024)
- [MaterialFusion: Enhancing Inverse Rendering with Material Diffusion Priors](https://mlsanity.com/paper/2409.15273/) (2024)
- [MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion](https://mlsanity.com/paper/2503.10289/) (2025)
- [ScribbleLight: Single Image Indoor Relighting with Scribbles](https://mlsanity.com/paper/2411.17696/) (2024)
- [IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations](https://mlsanity.com/paper/2412.12083/) (2024)
- [GenLit: Reformulating Single-Image Relighting as Video Generation](https://mlsanity.com/paper/2412.11224/) (2024)
- [Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion](https://mlsanity.com/paper/2412.09593/) (2024)
- [IntrinsiX: High-Quality PBR Generation using Image Priors](https://mlsanity.com/paper/2504.01008/) (2025)
- [IntrinsicEdit: Precise generative image manipulation in intrinsic space](https://mlsanity.com/paper/2505.08889/) (2025)
- [ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusion](https://mlsanity.com/paper/2410.08168/) (2024)
- [Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering](https://mlsanity.com/paper/2508.14461/) (2025)
- [Uni-Renderer: Unifying Rendering and Inverse Rendering Via Dual Stream Diffusion](https://mlsanity.com/paper/2412.15050/) (2024)
- [LuxDiT: Lighting Estimation with Video Diffusion Transformer](https://mlsanity.com/paper/2509.03680/) (2025)
- [GS-ID: Illumination Decomposition on Gaussian Splatting via Adaptive Light Aggregation and Diffusion-Guided Material Priors](https://mlsanity.com/paper/2408.08524/) (2024)
- [Physically Controllable Relighting of Photographs](https://mlsanity.com/paper/2508.05626/) (2025)
- [Geometry Field Splatting with Gaussian Surfels](https://mlsanity.com/paper/2411.17067/) (2024)
- [TransPixeler: Advancing Text-to-Video Generation with Transparency](https://mlsanity.com/paper/2501.03006/) (2025)
- [GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDR](https://mlsanity.com/paper/2504.10809/) (2025)
- [Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priors](https://mlsanity.com/paper/2411.17249/) (2024)
- [DNF-Intrinsic: Deterministic Noise-Free Diffusion for Indoor Inverse Rendering](https://mlsanity.com/paper/2507.03924/) (2025)
- [Boosting 3D Object Generation through PBR Materials](https://mlsanity.com/paper/2411.16080/) (2024)
- [MaterialPicker: Multi-Modal DiT-Based Material Generation](https://mlsanity.com/paper/2412.03225/) (2024)
- [Materialist: Physically Based Editing Using Single-Image Inverse Rendering](https://mlsanity.com/paper/2501.03717/) (2025)

## Abstract (arXiv)

The three areas of realistic forward rendering, per-pixel inverse rendering, and generative image synthesis may seem like separate and unrelated sub-fields of graphics and vision. However, recent work has demonstrated improved estimation of per-pixel intrinsic channels (albedo, roughness, metallicity) based on a diffusion architecture; we call this the RGBrightarrowX problem. We further show that the reverse problem of synthesizing realistic images given intrinsic channels, XrightarrowRGB, can also be addressed in a diffusion framework. Focusing on the image domain of interior scenes, we introduce an improved diffusion model for RGBrightarrowX, which also estimates lighting, as well as the first diffusion XrightarrowRGB model capable of synthesizing realistic images from (full or partial) intrinsic channels. Our XrightarrowRGB model explores a middle ground between traditional rendering and generative models: we can specify only certain appearance properties that should be followed, and give freedom to the model to hallucinate a plausible version of the rest. This flexibility makes it possible to use a mix of heterogeneous training datasets, which differ in the available channels. We use multiple existing datasets and extend them with our own synthetic and real data, resulting in a model capable of extracting scene properties better than previous work and of generating highly realistic images of interior scenes.