# Generative Models: What Do They Know? Do They Know Things? Let's Find Out!

arXiv: https://arxiv.org/abs/2311.17137 · HTML: https://mlsanity.com/paper/2311.17137/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 59 of its 71 references that are in the map.
- First posted on arXiv 28 Nov 2023.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 30 of 59)

- [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)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets](https://mlsanity.com/paper/2202.00273/) (2022)
- [Scaling up GANs for Text-to-Image Synthesis](https://mlsanity.com/paper/2303.05511/) (2023)
- [Emergent Correspondence from Image Diffusion](https://mlsanity.com/paper/2306.03881/) (2023)
- [Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.04803/) (2023)
- [Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans](https://mlsanity.com/paper/2110.04994/) (2021)
- [StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation](https://mlsanity.com/paper/2011.12799/) (2020)

## Built on by (most cited first, 30 of 50)

- [Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation](https://mlsanity.com/paper/2312.02145/) (2023)
- [Probing the 3D Awareness of Visual Foundation Models](https://mlsanity.com/paper/2404.08636/) (2024)
- [RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion models](https://mlsanity.com/paper/2405.00666/) (2024)
- [Learning Temporally Consistent Video Depth from Video Diffusion Priors](https://mlsanity.com/paper/2406.01493/) (2024)
- [Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis](https://mlsanity.com/paper/2505.09358/) (2025)
- [What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?](https://mlsanity.com/paper/2403.06090/) (2024)
- [Intrinsic Image Diffusion for Indoor Single-view Material Estimation](https://mlsanity.com/paper/2312.12274/) (2023)
- [Video Diffusion Models are Training-free Motion Interpreter and Controller](https://mlsanity.com/paper/2405.14864/) (2024)
- [DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models](https://mlsanity.com/paper/2501.18590/) (2025)
- [From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit](https://mlsanity.com/paper/2506.03093/) (2025)
- [Image Generators are Generalist Vision Learners](https://mlsanity.com/paper/2604.20329/) (2026)
- [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)
- [View Selection for 3D Captioning via Diffusion Ranking](https://mlsanity.com/paper/2404.07984/) (2024)
- [Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment](https://mlsanity.com/paper/2506.02221/) (2025)
- [Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion](https://mlsanity.com/paper/2403.14617/) (2024)
- [ScribbleLight: Single Image Indoor Relighting with Scribbles](https://mlsanity.com/paper/2411.17696/) (2024)
- [Collaborative Control for Geometry-Conditioned PBR Image Generation](https://mlsanity.com/paper/2402.05919/) (2024)
- [GenLit: Reformulating Single-Image Relighting as Video Generation](https://mlsanity.com/paper/2412.11224/) (2024)
- [IntrinsiX: High-Quality PBR Generation using Image Priors](https://mlsanity.com/paper/2504.01008/) (2025)
- [Latent Intrinsics Emerge from Training to Relight](https://mlsanity.com/paper/2405.21074/) (2024)
- [Orchid: Image Latent Diffusion for Joint Appearance and Geometry Generation](https://mlsanity.com/paper/2501.13087/) (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)
- [LuxDiT: Lighting Estimation with Video Diffusion Transformer](https://mlsanity.com/paper/2509.03680/) (2025)
- [Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning](https://mlsanity.com/paper/2411.19458/) (2024)
- [Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting](https://mlsanity.com/paper/2503.21770/) (2025)
- [Compass Control: Multi Object Orientation Control for Text-to-Image Generation](https://mlsanity.com/paper/2504.06752/) (2025)
- [DNF-Intrinsic: Deterministic Noise-Free Diffusion for Indoor Inverse Rendering](https://mlsanity.com/paper/2507.03924/) (2025)
- [Detecting Origin Attribution for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2403.19653/) (2024)

## Abstract (arXiv)

Generative models excel at mimicking real scenes, suggesting they might inherently encode important intrinsic scene properties. In this paper, we aim to explore the following key questions: (1) What intrinsic knowledge do generative models like GANs, Autoregressive models, and Diffusion models encode? (2) Can we establish a general framework to recover intrinsic representations from these models, regardless of their architecture or model type? (3) How minimal can the required learnable parameters and labeled data be to successfully recover this knowledge? (4) Is there a direct link between the quality of a generative model and the accuracy of the recovered scene intrinsics? Our findings indicate that a small Low-Rank Adaptators (LoRA) can recover intrinsic images-depth, normals, albedo and shading-across different generators (Autoregressive, GANs and Diffusion) while using the same decoder head that generates the image. As LoRA is lightweight, we introduce very few learnable parameters (as few as 0.04% of Stable Diffusion model weights for a rank of 2), and we find that as few as 250 labeled images are enough to generate intrinsic images with these LoRA modules. Finally, we also show a positive correlation between the generative model's quality and the accuracy of the recovered intrinsics through control experiments.