# STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation

arXiv: https://arxiv.org/abs/2302.01334 · HTML: https://mlsanity.com/paper/2302.01334/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 57 references that are in the map.
- First posted on arXiv 2 Feb 2023.

## Builds on (most cited first, 30 of 37)

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [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)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://mlsanity.com/paper/1803.02276/) (2018)
- [Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement](https://mlsanity.com/paper/2012.05609/) (2020)
- [Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation](https://mlsanity.com/paper/1805.09806/) (2018)
- [Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds](https://mlsanity.com/paper/2109.00179/) (2021)
- [Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints](https://mlsanity.com/paper/1802.05522/) (2018)
- [Playing for Benchmarks](https://mlsanity.com/paper/1709.07322/) (2017)
- [Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos](https://mlsanity.com/paper/1811.06152/) (2018)
- [Semi-Supervised Deep Learning for Monocular Depth Map Prediction](https://mlsanity.com/paper/1702.02706/) (2017)
- [AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network](https://mlsanity.com/paper/2203.11799/) (2022)
- [Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation](https://mlsanity.com/paper/2005.14553/) (2020)
- [DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation](https://mlsanity.com/paper/2104.10834/) (2021)
- [Enhancing Photorealism Enhancement](https://mlsanity.com/paper/2105.04619/) (2021)
- [Efficient Semantic Scene Completion Network with Spatial Group Convolution](https://mlsanity.com/paper/1907.05091/) (2019)
- [SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimation](https://mlsanity.com/paper/1810.01849/) (2018)
- [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)
- [Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation](https://mlsanity.com/paper/2108.07628/) (2021)
- [Unsupervised Monocular Depth Estimation for Night-time Images using Adversarial Domain Feature Adaptation](https://mlsanity.com/paper/2010.01402/) (2020)
- [PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds](https://mlsanity.com/paper/2109.05566/) (2021)
- [GANVO: Unsupervised Deep Monocular Visual Odometry and Depth Estimation with Generative Adversarial Networks](https://mlsanity.com/paper/1809.05786/) (2018)
- [VIBUS: Data-efficient 3D Scene Parsing with VIewpoint Bottleneck and Uncertainty-Spectrum Modeling](https://mlsanity.com/paper/2210.11472/) (2022)

## Built on by (most cited first, 30 of 37)

- [MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving](https://mlsanity.com/paper/2307.15058/) (2023)
- [PhysGen3D: Crafting a Miniature Interactive World from a Single Image](https://mlsanity.com/paper/2503.20746/) (2025)
- [Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models](https://mlsanity.com/paper/2505.23757/) (2025)
- [P-MapNet: Far-seeing Map Generator Enhanced by both SDMap and HDMap Priors](https://mlsanity.com/paper/2403.10521/) (2024)
- [MonoOcc: Digging into Monocular Semantic Occupancy Prediction](https://mlsanity.com/paper/2403.08766/) (2024)
- [Tri-Perspective View Decomposition for Geometry-Aware Depth Completion](https://mlsanity.com/paper/2403.15008/) (2024)
- [Hint-AD: Holistically Aligned Interpretability in End-to-End Autonomous Driving](https://mlsanity.com/paper/2409.06702/) (2024)
- [Synthetic-to-Real Self-supervised Robust Depth Estimation via Learning with Motion and Structure Priors](https://mlsanity.com/paper/2503.20211/) (2025)
- [Delving into Shape-aware Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2304.08491/) (2023)
- [Training-Free Model Merging for Multi-target Domain Adaptation](https://mlsanity.com/paper/2407.13771/) (2024)
- [Learnable Differencing Center for Nighttime Depth Perception](https://mlsanity.com/paper/2306.14538/) (2023)
- [Adaptive Surface Normal Constraint for Geometric Estimation from Monocular Images](https://mlsanity.com/paper/2402.05869/) (2024)
- [UncAD: Towards Safe End-to-end Autonomous Driving via Online Map Uncertainty](https://mlsanity.com/paper/2504.12826/) (2025)
- [Depth Anything at Any Condition](https://mlsanity.com/paper/2507.01634/) (2025)
- [Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video](https://mlsanity.com/paper/2412.11395/) (2024)
- [All-day Depth Completion](https://mlsanity.com/paper/2405.17315/) (2024)
- [SCP-Diff: Spatial-Categorical Joint Prior for Diffusion Based Semantic Image Synthesis](https://mlsanity.com/paper/2403.09638/) (2024)
- [Dusk Till Dawn: Self-supervised Nighttime Stereo Depth Estimation using Visual Foundation Models](https://mlsanity.com/paper/2405.11158/) (2024)
- [Diffusion-based Visual Anagram as Multi-task Learning](https://mlsanity.com/paper/2412.02693/) (2024)
- [Always Clear Depth: Robust Monocular Depth Estimation under Adverse Weather](https://mlsanity.com/paper/2505.12199/) (2025)
- [Advancing Depth Anything Model for Unsupervised Monocular Depth Estimation in Endoscopy](https://mlsanity.com/paper/2409.07723/) (2024)
- [Sample-efficient Unsupervised Policy Cloning from Ensemble Self-supervised Labeled Videos](https://mlsanity.com/paper/2412.10778/) (2024)
- [ER-LoRA: Effective-Rank Guided Adaptation for Weather-Generalized Depth Estimation](https://mlsanity.com/paper/2509.00665/) (2025)
- [DPF: Learning Dense Prediction Fields with Weak Supervision](https://mlsanity.com/paper/2303.16890/) (2023)
- [LED: Light Enhanced Depth Estimation at Night](https://mlsanity.com/paper/2409.08031/) (2024)
- [Faithfulness to Refusal: A Causal Audit of Neuron Selectors](https://mlsanity.com/paper/2607.05355/) (2026)
- [DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision](https://mlsanity.com/paper/2309.06941/) (2023)
- [PromptMono: Cross Prompting Attention for Self-Supervised Monocular Depth Estimation in Challenging Environments](https://mlsanity.com/paper/2501.13796/) (2025)
- [HMAD: Advancing E2E Driving with Anchored Offset Proposals and Simulation-Supervised Multi-target Scoring](https://mlsanity.com/paper/2505.23129/) (2025)
- [Adapting Depth Anything to Adverse Imaging Conditions with Events](https://mlsanity.com/paper/2601.02020/) (2026)

## Abstract (arXiv)

Self-supervised depth estimation draws a lot of attention recently as it can promote the 3D sensing capabilities of self-driving vehicles. However, it intrinsically relies upon the photometric consistency assumption, which hardly holds during nighttime. Although various supervised nighttime image enhancement methods have been proposed, their generalization performance in challenging driving scenarios is not satisfactory. To this end, we propose the first method that jointly learns a nighttime image enhancer and a depth estimator, without using ground truth for either task. Our method tightly entangles two self-supervised tasks using a newly proposed uncertain pixel masking strategy. This strategy originates from the observation that nighttime images not only suffer from underexposed regions but also from overexposed regions. By fitting a bridge-shaped curve to the illumination map distribution, both regions are suppressed and two tasks are bridged naturally. We benchmark the method on two established datasets: nuScenes and RobotCar and demonstrate state-of-the-art performance on both of them. Detailed ablations also reveal the mechanism of our proposal. Last but not least, to mitigate the problem of sparse ground truth of existing datasets, we provide a new photo-realistically enhanced nighttime dataset based upon CARLA. It brings meaningful new challenges to the community. Codes, data, and models are available at https://github.com/ucaszyp/STEPS.