# Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis

arXiv: https://arxiv.org/abs/2505.09358 · HTML: https://mlsanity.com/paper/2505.09358/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 101 of its 134 references that are in the map.
- First posted on arXiv 14 May 2025.

## Placed in

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

## Builds on (most cited first, 30 of 101)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)

## Built on by (most cited first, 30 of 78)

- [GSFix3D: Diffusion-Guided Repair of Novel Views in Gaussian Splatting](https://mlsanity.com/paper/2508.14717/) (2025)
- [3D-RE-GEN: 3D Reconstruction of Indoor Scenes with a Generative Framework](https://mlsanity.com/paper/2512.17459/) (2025)
- [LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models](https://mlsanity.com/paper/2601.14674/) (2026)
- [UniDAC: Universal Metric Depth Estimation for Any Camera](https://mlsanity.com/paper/2603.27105/) (2026)
- [CtrlVDiff: Controllable Video Generation via Unified Multimodal Video Diffusion](https://mlsanity.com/paper/2511.21129/) (2025)
- [UniSER: A Foundation Model for Unified Soft Effects Removal](https://mlsanity.com/paper/2511.14183/) (2025)
- [Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers](https://mlsanity.com/paper/2511.18673/) (2025)
- [THFM: A Unified Video Foundation Model for 4D Human Perception and Beyond](https://mlsanity.com/paper/2603.25892/) (2026)
- [Denoise to Track: Harnessing Video Diffusion Priors for Robust Correspondence](https://mlsanity.com/paper/2512.04619/) (2025)
- [Reflection Removal through Efficient Adaptation of Diffusion Transformers](https://mlsanity.com/paper/2512.05000/) (2025)
- [MoE3D: A Mixture-of-Experts Module for 3D Reconstruction](https://mlsanity.com/paper/2601.05208/) (2026)
- [DVD: Deterministic Video Depth Estimation with Generative Priors](https://mlsanity.com/paper/2603.12250/) (2026)
- [PoseMaster: A Unified 3D Native Framework for Stylized Pose Generation](https://mlsanity.com/paper/2506.21076/) (2025)
- [Elastic3D: Controllable Stereo Video Conversion with Guided Latent Decoding](https://mlsanity.com/paper/2512.14236/) (2025)
- [See-through: Single-image Layer Decomposition for Anime Characters](https://mlsanity.com/paper/2602.03749/) (2026)
- [Depth Completion as Parameter-Efficient Test-Time Adaptation](https://mlsanity.com/paper/2602.14751/) (2026)
- [GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion Transformers](https://mlsanity.com/paper/2604.20715/) (2026)
- [Towards Consistent Video Geometry Estimation](https://mlsanity.com/paper/2605.30060/) (2026)
- [FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry](https://mlsanity.com/paper/2607.11588/) (2026)
- [StableMTL: Repurposing Latent Diffusion Models for Multi-Task Learning from Partially Annotated Synthetic Datasets](https://mlsanity.com/paper/2506.08013/) (2025)
- [VENTURA: Adapting Image Diffusion Models for Unified Task Conditioned Navigation](https://mlsanity.com/paper/2510.01388/) (2025)
- [FlyAwareV2: A Multimodal Cross-Domain UAV Dataset for Urban Scene Understanding](https://mlsanity.com/paper/2510.13243/) (2025)
- [StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space](https://mlsanity.com/paper/2512.10959/) (2025)
- [MatSpray: Fusing 2D Material World Knowledge on 3D Geometry](https://mlsanity.com/paper/2512.18314/) (2025)
- [Visual Autoregressive Modelling for Monocular Depth Estimation](https://mlsanity.com/paper/2512.22653/) (2025)
- [Depth Anything in 360^circ: Towards Scale Invariance in the Wild](https://mlsanity.com/paper/2512.22819/) (2025)
- [StableDPT: Temporal Stable Monocular Video Depth Estimation](https://mlsanity.com/paper/2601.02793/) (2026)
- [Monocular Normal Estimation via Shading Sequence Estimation](https://mlsanity.com/paper/2602.09929/) (2026)
- [SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacification](https://mlsanity.com/paper/2603.19547/) (2026)
- [The First Controllable Bokeh Rendering Challenge at NTIRE 2026](https://mlsanity.com/paper/2605.05510/) (2026)

## Abstract (arXiv)

The success of deep learning in computer vision over the past decade has hinged on large labeled datasets and strong pretrained models. In data-scarce settings, the quality of these pretrained models becomes crucial for effective transfer learning. Image classification and self-supervised learning have traditionally been the primary methods for pretraining CNNs and transformer-based architectures. Recently, the rise of text-to-image generative models, particularly those using denoising diffusion in a latent space, has introduced a new class of foundational models trained on massive, captioned image datasets. These models' ability to generate realistic images of unseen content suggests they possess a deep understanding of the visual world. In this work, we present Marigold, a family of conditional generative models and a fine-tuning protocol that extracts the knowledge from pretrained latent diffusion models like Stable Diffusion and adapts them for dense image analysis tasks, including monocular depth estimation, surface normals prediction, and intrinsic decomposition. Marigold requires minimal modification of the pre-trained latent diffusion model's architecture, trains with small synthetic datasets on a single GPU over a few days, and demonstrates state-of-the-art zero-shot generalization. Project page: https://marigoldcomputervision.github.io