# Digging into contrastive learning for robust depth estimation with diffusion models

arXiv: https://arxiv.org/abs/2404.09831 · HTML: https://mlsanity.com/paper/2404.09831/

## Key facts

- Cited by 19 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 18 of its 32 references that are in the map.
- First posted on arXiv 15 Apr 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, 18 of 18)

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture](https://mlsanity.com/paper/1411.4734/) (2014)
- [Deeper Depth Prediction with Fully Convolutional Residual Networks](https://mlsanity.com/paper/1606.00373/) (2016)
- [DiffusionDet: Diffusion Model for Object Detection](https://mlsanity.com/paper/2211.09788/) (2022)
- [Unleashing Text-to-Image Diffusion Models for Visual Perception](https://mlsanity.com/paper/2303.02153/) (2023)
- [DDP: Diffusion Model for Dense Visual Prediction](https://mlsanity.com/paper/2303.17559/) (2023)
- [MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer](https://mlsanity.com/paper/2208.03543/) (2022)
- [Robust Monocular Depth Estimation under Challenging Conditions](https://mlsanity.com/paper/2308.09711/) (2023)
- [Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation](https://mlsanity.com/paper/2108.07628/) (2021)
- [Text-image Alignment for Diffusion-based Perception](https://mlsanity.com/paper/2310.00031/) (2023)
- [SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process](https://mlsanity.com/paper/2312.12425/) (2023)
- [Unsupervised Monocular Depth Estimation in Highly Complex Environments](https://mlsanity.com/paper/2107.13137/) (2021)
- [DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Diffusion Model](https://mlsanity.com/paper/2311.17456/) (2023)

## Built on by (most cited first, 19 of 19)

- [From Editor to Dense Geometry Estimator](https://mlsanity.com/paper/2509.04338/) (2025)
- [LongStream: Long-Sequence Streaming Autoregressive Visual Geometry](https://mlsanity.com/paper/2602.13172/) (2026)
- [Synthetic-to-Real Self-supervised Robust Depth Estimation via Learning with Motion and Structure Priors](https://mlsanity.com/paper/2503.20211/) (2025)
- [Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation](https://mlsanity.com/paper/2503.15905/) (2025)
- [MSP-MVS: Multi-Granularity Segmentation Prior Guided Multi-View Stereo](https://mlsanity.com/paper/2407.19323/) (2024)
- [DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo](https://mlsanity.com/paper/2412.11578/) (2024)
- [Depth Anything at Any Condition](https://mlsanity.com/paper/2507.01634/) (2025)
- [From Scale to Speed: Adaptive Test-Time Scaling for Image Editing](https://mlsanity.com/paper/2603.00141/) (2026)
- [Semantic Context Matters: Improving Conditioning for Autoregressive Models](https://mlsanity.com/paper/2511.14063/) (2025)
- [PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling](https://mlsanity.com/paper/2512.04784/) (2025)
- [Always Clear Depth: Robust Monocular Depth Estimation under Adverse Weather](https://mlsanity.com/paper/2505.12199/) (2025)
- [CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating](https://mlsanity.com/paper/2605.11723/) (2026)
- [ER-LoRA: Effective-Rank Guided Adaptation for Weather-Generalized Depth Estimation](https://mlsanity.com/paper/2509.00665/) (2025)
- [DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment Distillation](https://mlsanity.com/paper/2607.02220/) (2026)
- [BaseBoostDepth: Exploiting Larger Baselines For Self-supervised Monocular Depth Estimation](https://mlsanity.com/paper/2407.20437/) (2024)
- [Stable-Sim2Real: Exploring Simulation of Real-Captured 3D Data with Two-Stage Depth Diffusion](https://mlsanity.com/paper/2507.23483/) (2025)
- [Learning Depth from Past Selves: Self-Evolution Contrast for Robust Depth Estimation](https://mlsanity.com/paper/2511.15167/) (2025)
- [OptiGeo: Efficient Monocular Geometry for Embodied Perception in Optically Challenging Scenes](https://mlsanity.com/paper/2608.29881/) (2026)
- [RePer-360: Releasing Perspective Priors for 360^circ Depth Estimation via Self-Modulation](https://mlsanity.com/paper/2603.05999/) (2026)

## Abstract (arXiv)

Recently, diffusion-based depth estimation methods have drawn widespread attention due to their elegant denoising patterns and promising performance. However, they are typically unreliable under adverse conditions prevalent in real-world scenarios, such as rainy, snowy, etc. In this paper, we propose a novel robust depth estimation method called D4RD, featuring a custom contrastive learning mode tailored for diffusion models to mitigate performance degradation in complex environments. Concretely, we integrate the strength of knowledge distillation into contrastive learning, building the `trinity' contrastive scheme. This scheme utilizes the sampled noise of the forward diffusion process as a natural reference, guiding the predicted noise in diverse scenes toward a more stable and precise optimum. Moreover, we extend noise-level trinity to encompass more generic feature and image levels, establishing a multi-level contrast to distribute the burden of robust perception across the overall network. Before addressing complex scenarios, we enhance the stability of the baseline diffusion model with three straightforward yet effective improvements, which facilitate convergence and remove depth outliers. Extensive experiments demonstrate that D4RD surpasses existing state-of-the-art solutions on synthetic corruption datasets and real-world weather conditions. Source code and data are available at urlhttps://github.com/wangjiyuan9/D4RD.