# The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth

arXiv: https://arxiv.org/abs/2104.14540 · HTML: https://mlsanity.com/paper/2104.14540/

## Key facts

- Cited by 190 papers in the map (data through 14 Oct 2026).
- Builds on 76 of its 102 references that are in the map.
- First posted on arXiv 29 Apr 2021.

## Builds on (most cited first, 30 of 76)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [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)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture](https://mlsanity.com/paper/1411.4734/) (2014)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching](https://mlsanity.com/paper/1912.06378/) (2019)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [End-to-End Learning of Geometry and Context for Deep Stereo Regression](https://mlsanity.com/paper/1703.04309/) (2017)
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://mlsanity.com/paper/1803.02276/) (2018)
- [Sparsity Invariant CNNs](https://mlsanity.com/paper/1708.06500/) (2017)
- [DeepMVS: Learning Multi-view Stereopsis](https://mlsanity.com/paper/1804.00650/) (2018)
- [GA-Net: Guided Aggregation Net for End-to-end Stereo Matching](https://mlsanity.com/paper/1904.06587/) (2019)
- [Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video](https://mlsanity.com/paper/1908.10553/) (2019)
- [Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation](https://mlsanity.com/paper/1805.09806/) (2018)
- [Consistent Video Depth Estimation](https://mlsanity.com/paper/2004.15021/) (2020)
- [DeMoN: Depth and Motion Network for Learning Monocular Stereo](https://mlsanity.com/paper/1612.02401/) (2016)
- [Learning a Multi-View Stereo Machine](https://mlsanity.com/paper/1708.05375/) (2017)
- [Single-Image Depth Perception in the Wild](https://mlsanity.com/paper/1604.03901/) (2016)
- [Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras](https://mlsanity.com/paper/1904.04998/) (2019)
- [Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction](https://mlsanity.com/paper/1803.03893/) (2018)
- [Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos](https://mlsanity.com/paper/1811.06152/) (2018)

## Built on by (most cited first, 30 of 190)

- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior](https://mlsanity.com/paper/2204.02091/) (2022)
- [UniScene: Unified Occupancy-centric Driving Scene Generation](https://mlsanity.com/paper/2412.05435/) (2024)
- [Learning Temporally Consistent Video Depth from Video Diffusion Priors](https://mlsanity.com/paper/2406.01493/) (2024)
- [LocalBins: Improving Depth Estimation by Learning Local Distributions](https://mlsanity.com/paper/2203.15132/) (2022)
- [SimpleRecon: 3D Reconstruction Without 3D Convolutions](https://mlsanity.com/paper/2208.14743/) (2022)
- [Self-Supervised Monocular Depth Estimation with Internal Feature Fusion](https://mlsanity.com/paper/2110.09482/) (2021)
- [Multi-Frame Self-Supervised Depth with Transformers](https://mlsanity.com/paper/2204.07616/) (2022)
- [Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches](https://mlsanity.com/paper/2207.04718/) (2022)
- [STS: Surround-view Temporal Stereo for Multi-view 3D Detection](https://mlsanity.com/paper/2208.10145/) (2022)
- [MVSTER: Epipolar Transformer for Efficient Multi-View Stereo](https://mlsanity.com/paper/2204.07346/) (2022)
- [RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions](https://mlsanity.com/paper/2310.15171/) (2023)
- [Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth](https://mlsanity.com/paper/2203.15174/) (2022)
- [Toward Practical Monocular Indoor Depth Estimation](https://mlsanity.com/paper/2112.02306/) (2021)
- [Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera](https://mlsanity.com/paper/2501.02464/) (2025)
- [R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras](https://mlsanity.com/paper/2308.14713/) (2023)
- [Self-supervised Monocular Depth Estimation: Let's Talk About The Weather](https://mlsanity.com/paper/2307.08357/) (2023)
- [Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving](https://mlsanity.com/paper/2403.17301/) (2024)
- [Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion](https://mlsanity.com/paper/2407.02077/) (2024)
- [WonderTurbo: Generating Interactive 3D World in 0.72 Seconds](https://mlsanity.com/paper/2504.02261/) (2025)
- [Learning Optical Flow, Depth, and Scene Flow without Real-World Labels](https://mlsanity.com/paper/2203.15089/) (2022)
- [Cross-View Completion Models are Zero-shot Correspondence Estimators](https://mlsanity.com/paper/2412.09072/) (2024)
- [Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2110.08192/) (2021)
- [Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark](https://mlsanity.com/paper/2212.08914/) (2022)
- [On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks](https://mlsanity.com/paper/2303.14840/) (2023)
- [MVSAnywhere: Zero-Shot Multi-View Stereo](https://mlsanity.com/paper/2503.22430/) (2025)
- [Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenes](https://mlsanity.com/paper/2304.08993/) (2023)
- [MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation](https://mlsanity.com/paper/2307.14336/) (2023)
- [RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenes](https://mlsanity.com/paper/2303.04456/) (2023)

## Abstract (arXiv)

Self-supervised monocular depth estimation networks are trained to predict scene depth using nearby frames as a supervision signal during training. However, for many applications, sequence information in the form of video frames is also available at test time. The vast majority of monocular networks do not make use of this extra signal, thus ignoring valuable information that could be used to improve the predicted depth. Those that do, either use computationally expensive test-time refinement techniques or off-the-shelf recurrent networks, which only indirectly make use of the geometric information that is inherently available. We propose ManyDepth, an adaptive approach to dense depth estimation that can make use of sequence information at test time, when it is available. Taking inspiration from multi-view stereo, we propose a deep end-to-end cost volume based approach that is trained using self-supervision only. We present a novel consistency loss that encourages the network to ignore the cost volume when it is deemed unreliable, e.g. in the case of moving objects, and an augmentation scheme to cope with static cameras. Our detailed experiments on both KITTI and Cityscapes show that we outperform all published self-supervised baselines, including those that use single or multiple frames at test time.