# Synthetic-to-Real Self-supervised Robust Depth Estimation via Learning with Motion and Structure Priors

arXiv: https://arxiv.org/abs/2503.20211 · HTML: https://mlsanity.com/paper/2503.20211/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 49 references that are in the map.
- First posted on arXiv 26 Mar 2025.

## Builds on (most cited first, 30 of 41)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth](https://mlsanity.com/paper/2104.14540/) (2021)
- [MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer](https://mlsanity.com/paper/2208.03543/) (2022)
- [Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2211.13202/) (2022)
- [Unsupervised Scale-consistent Depth Learning from Video](https://mlsanity.com/paper/2105.11610/) (2021)
- [Multi-Frame Self-Supervised Depth with Transformers](https://mlsanity.com/paper/2204.07616/) (2022)
- [DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning](https://mlsanity.com/paper/2003.13446/) (2020)
- [Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark](https://mlsanity.com/paper/2108.03830/) (2021)
- [Robust Monocular Depth Estimation under Challenging Conditions](https://mlsanity.com/paper/2308.09711/) (2023)
- [SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenes](https://mlsanity.com/paper/2211.03660/) (2022)
- [Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2109.12484/) (2021)
- [Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth](https://mlsanity.com/paper/2203.15174/) (2022)
- [Instant3D: Instant Text-to-3D Generation](https://mlsanity.com/paper/2311.08403/) (2023)
- [Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation](https://mlsanity.com/paper/2108.07628/) (2021)
- [STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation](https://mlsanity.com/paper/2302.01334/) (2023)
- [R4Dyn: Exploring Radar for Self-Supervised Monocular Depth Estimation of Dynamic Scenes](https://mlsanity.com/paper/2108.04814/) (2021)
- [Unsupervised Monocular Depth Estimation for Night-time Images using Adversarial Domain Feature Adaptation](https://mlsanity.com/paper/2010.01402/) (2020)
- [Self-supervised Monocular Depth Estimation: Let's Talk About The Weather](https://mlsanity.com/paper/2307.08357/) (2023)
- [PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes](https://mlsanity.com/paper/2210.01612/) (2022)
- [STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition](https://mlsanity.com/paper/2301.03046/) (2023)
- [Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions](https://mlsanity.com/paper/2407.16698/) (2024)
- [Unsupervised Monocular Depth Estimation in Highly Complex Environments](https://mlsanity.com/paper/2107.13137/) (2021)
- [Self-supervised Geometric Features Discovery via Interpretable Attention for Vehicle Re-Identification and Beyond](https://mlsanity.com/paper/2010.09221/) (2020)

## Built on by (most cited first, 22 of 22)

- [Depth Anything at Any Condition](https://mlsanity.com/paper/2507.01634/) (2025)
- [LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistency](https://mlsanity.com/paper/2602.18735/) (2026)
- [TextSplat: Text-Guided Semantic Fusion for Generalizable Gaussian Splatting](https://mlsanity.com/paper/2504.09588/) (2025)
- [One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems](https://mlsanity.com/paper/2605.22144/) (2026)
- [4DPC2hat: Towards Dynamic Point Cloud Understanding with Failure-Aware Bootstrapping](https://mlsanity.com/paper/2602.03890/) (2026)
- [ER-LoRA: Effective-Rank Guided Adaptation for Weather-Generalized Depth Estimation](https://mlsanity.com/paper/2509.00665/) (2025)
- [Learning Depth from Past Selves: Self-Evolution Contrast for Robust Depth Estimation](https://mlsanity.com/paper/2511.15167/) (2025)
- [Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy](https://mlsanity.com/paper/2605.00719/) (2026)
- [GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow Scenes](https://mlsanity.com/paper/2605.23602/) (2026)
- [Discriminately Treating Motion Components Evolves Joint Depth and Ego-Motion Learning](https://mlsanity.com/paper/2511.01502/) (2025)
- [Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO](https://mlsanity.com/paper/2607.11581/) (2026)
- [Robust Brain Tumor Segmentation with Incomplete MRI Modalities Using H"older Divergence and Mutual Information-Enhanced Knowledge Transfer](https://mlsanity.com/paper/2507.01254/) (2025)
- [AR as an Evaluation Playground: Bridging Metrics and Visual Perception of Computer Vision Models](https://mlsanity.com/paper/2508.04102/) (2025)
- [VSE-MOT: Multi-Object Tracking in Low-Quality Video Scenes Guided by Visual Semantic Enhancement](https://mlsanity.com/paper/2509.14060/) (2025)
- [Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matching](https://mlsanity.com/paper/2604.18623/) (2026)
- [Boosting Robustness for All-Weather Self-Supervised Depth Estimation in Autonomous Driving](https://mlsanity.com/paper/2607.21526/) (2026)
- [Monocular Depth Estimation from a Single Image: Progress and Opportunities](https://mlsanity.com/paper/2609.01172/) (2026)
- [Weather-Conditioned Depth Anything](https://mlsanity.com/paper/2609.04827/) (2026)
- [AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation](https://mlsanity.com/paper/2609.29816/) (2026)
- [Proxy2World: Learning to Generate Worlds From Lightweight Proxies without Seeing Them](https://mlsanity.com/paper/2609.35023/) (2026)
- [GHOST: Geometry-Constrained Hybrid Diffusion for Open-Vocabulary 3D Scene Graph Generation](https://mlsanity.com/paper/2610.16455/) (2026)
- [OpenDepth: Repurposing Image Editing Priors for Robust Open-World Monocular Depth Estimation](https://mlsanity.com/paper/2610.17610/) (2026)

## Abstract (arXiv)

Self-supervised depth estimation from monocular cameras in diverse outdoor conditions, such as daytime, rain, and nighttime, is challenging due to the difficulty of learning universal representations and the severe lack of labeled real-world adverse data. Previous methods either rely on synthetic inputs and pseudo-depth labels or directly apply daytime strategies to adverse conditions, resulting in suboptimal results. In this paper, we present the first synthetic-to-real robust depth estimation framework, incorporating motion and structure priors to capture real-world knowledge effectively. In the synthetic adaptation, we transfer motion-structure knowledge inside cost volumes for better robust representation, using a frozen daytime model to train a depth estimator in synthetic adverse conditions. In the innovative real adaptation, which targets to fix synthetic-real gaps, models trained earlier identify the weather-insensitive regions with a designed consistency-reweighting strategy to emphasize valid pseudo-labels. We introduce a new regularization by gathering explicit depth distributions to constrain the model when facing real-world data. Experiments show that our method outperforms the state-of-the-art across diverse conditions in multi-frame and single-frame evaluations. We achieve improvements of 7.5% and 4.3% in AbsRel and RMSE on average for nuScenes and Robotcar datasets (daytime, nighttime, rain). In zero-shot evaluation of DrivingStereo (rain, fog), our method generalizes better than the previous ones.