# Video Depth Estimation by Fusing Flow-to-Depth Proposals

arXiv: https://arxiv.org/abs/1912.12874 · HTML: https://mlsanity.com/paper/1912.12874/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Dec 2019.

## Built on by (most cited first, 23 of 23)

- [The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth](https://mlsanity.com/paper/2104.14540/) (2021)
- [High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization](https://mlsanity.com/paper/2211.15662/) (2022)
- [FWD: Real-time Novel View Synthesis with Forward Warping and Depth](https://mlsanity.com/paper/2206.08355/) (2022)
- [Blind Video Deflickering by Neural Filtering with a Flawed Atlas](https://mlsanity.com/paper/2303.08120/) (2023)
- [MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation](https://mlsanity.com/paper/2307.14336/) (2023)
- [RadarCam-Depth: Radar-Camera Fusion for Depth Estimation with Learned Metric Scale](https://mlsanity.com/paper/2401.04325/) (2024)
- [MACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervision](https://mlsanity.com/paper/2303.03315/) (2023)
- [Deep Video Prior for Video Consistency and Propagation](https://mlsanity.com/paper/2201.11632/) (2022)
- [Monocular Visual-Inertial Depth Estimation](https://mlsanity.com/paper/2303.12134/) (2023)
- [Real-Time Dense 3D Mapping of Underwater Environments](https://mlsanity.com/paper/2304.02704/) (2023)
- [Stereo Matching by Self-supervision of Multiscopic Vision](https://mlsanity.com/paper/2104.04170/) (2021)
- [Reconstructing 4D Spatial Intelligence: A Survey](https://mlsanity.com/paper/2507.21045/) (2025)
- [FutureDepth: Learning to Predict the Future Improves Video Depth Estimation](https://mlsanity.com/paper/2403.12953/) (2024)
- [DurLAR: A High-fidelity 128-channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-modal Autonomous Driving Applications](https://mlsanity.com/paper/2406.10068/) (2024)
- [Video Understanding: From Geometry and Semantics to Unified Models](https://mlsanity.com/paper/2603.17840/) (2026)
- [Joint Depth and Normal Estimation from Real-world Time-of-flight Raw Data](https://mlsanity.com/paper/2108.03649/) (2021)
- [FLODCAST: Flow and Depth Forecasting via Multimodal Recurrent Architectures](https://mlsanity.com/paper/2310.20593/) (2023)
- [RaCalNet: Radar Calibration Network for Sparse-Supervised Metric Depth Estimation](https://mlsanity.com/paper/2506.15560/) (2025)
- [STATIC : Surface Temporal Affine for TIme Consistency in Video Monocular Depth Estimation](https://mlsanity.com/paper/2412.01090/) (2024)
- [Szloca: towards a framework for full 3D tracking through a single camera in context of interactive arts](https://mlsanity.com/paper/2206.12958/) (2022)
- [A Compacted Structure for Cross-domain learning on Monocular Depth and Flow Estimation](https://mlsanity.com/paper/2208.11993/) (2022)
- [Image-Plane Geometric Decoding for View-Invariant Indoor Scene Reconstruction](https://mlsanity.com/paper/2509.25744/) (2025)
- [RAD: Retrieval-Augmented Monocular Metric Depth Estimation for Underrepresented Classes](https://mlsanity.com/paper/2602.09532/) (2026)

## Abstract (arXiv)

Depth from a monocular video can enable billions of devices and robots with a single camera to see the world in 3D. In this paper, we present an approach with a differentiable flow-to-depth layer for video depth estimation. The model consists of a flow-to-depth layer, a camera pose refinement module, and a depth fusion network. Given optical flow and camera pose, our flow-to-depth layer generates depth proposals and the corresponding confidence maps by explicitly solving an epipolar geometry optimization problem. Our flow-to-depth layer is differentiable, and thus we can refine camera poses by maximizing the aggregated confidence in the camera pose refinement module. Our depth fusion network can utilize depth proposals and their confidence maps inferred from different adjacent frames to produce the final depth map. Furthermore, the depth fusion network can additionally take the depth proposals generated by other methods to improve the results further. The experiments on three public datasets show that our approach outperforms state-of-the-art depth estimation methods, and has reasonable cross dataset generalization capability: our model trained on KITTI still performs well on the unseen Waymo dataset.