# DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal Fusion

arXiv: https://arxiv.org/abs/2012.02177 · HTML: https://mlsanity.com/paper/2012.02177/

## Key facts

- Cited by 68 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2020.

## Built on by (most cited first, 30 of 68)

- [DepthSplat: Connecting Gaussian Splatting and Depth](https://mlsanity.com/paper/2410.13862/) (2024)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats](https://mlsanity.com/paper/2410.12781/) (2024)
- [TransformerFusion: Monocular RGB Scene Reconstruction using Transformers](https://mlsanity.com/paper/2107.02191/) (2021)
- [FreeSplat: Generalizable 3D Gaussian Splatting Towards Free-View Synthesis of Indoor Scenes](https://mlsanity.com/paper/2405.17958/) (2024)
- [SimpleRecon: 3D Reconstruction Without 3D Convolutions](https://mlsanity.com/paper/2208.14743/) (2022)
- [VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction](https://mlsanity.com/paper/2212.08067/) (2022)
- [VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction](https://mlsanity.com/paper/2108.08623/) (2021)
- [VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and Fusion](https://mlsanity.com/paper/2112.00236/) (2021)
- [PreF3R: Pose-Free Feed-Forward 3D Gaussian Splatting from Variable-length Image Sequence](https://mlsanity.com/paper/2411.16877/) (2024)
- [PlanarRecon: Real-time 3D Plane Detection and Reconstruction from Posed Monocular Videos](https://mlsanity.com/paper/2206.07710/) (2022)
- [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)
- [3DVNet: Multi-View Depth Prediction and Volumetric Refinement](https://mlsanity.com/paper/2112.00202/) (2021)
- [WT-MVSNet: Window-based Transformers for Multi-view Stereo](https://mlsanity.com/paper/2205.14319/) (2022)
- [Learning-based Multi-View Stereo: A Survey](https://mlsanity.com/paper/2408.15235/) (2024)
- [RayTran: 3D pose estimation and shape reconstruction of multiple objects from videos with ray-traced transformers](https://mlsanity.com/paper/2203.13296/) (2022)
- [MonoNeuralFusion: Online Monocular Neural 3D Reconstruction with Geometric Priors](https://mlsanity.com/paper/2209.15153/) (2022)
- [FineRecon: Depth-aware Feed-forward Network for Detailed 3D Reconstruction](https://mlsanity.com/paper/2304.01480/) (2023)
- [Consistent Direct Time-of-Flight Video Depth Super-Resolution](https://mlsanity.com/paper/2211.08658/) (2022)
- [Real-Time Dense 3D Mapping of Underwater Environments](https://mlsanity.com/paper/2304.02704/) (2023)
- [CVRecon: Rethinking 3D Geometric Feature Learning For Neural Reconstruction](https://mlsanity.com/paper/2304.14633/) (2023)
- [FreeSplat++: Generalizable 3D Gaussian Splatting for Efficient Indoor Scene Reconstruction](https://mlsanity.com/paper/2503.22986/) (2025)
- [Stereo Matching in Time: 100+ FPS Video Stereo Matching for Extended Reality](https://mlsanity.com/paper/2309.04183/) (2023)
- [AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings](https://mlsanity.com/paper/2406.08960/) (2024)
- [LLaVA-SpaceSGG: Visual Instruct Tuning for Open-vocabulary Scene Graph Generation with Enhanced Spatial Relations](https://mlsanity.com/paper/2412.06322/) (2024)
- [A Confidence-based Iterative Solver of Depths and Surface Normals for Deep Multi-view Stereo](https://mlsanity.com/paper/2201.07609/) (2022)
- [RIAV-MVS: Recurrent-Indexing an Asymmetric Volume for Multi-View Stereo](https://mlsanity.com/paper/2205.14320/) (2022)
- [TemporalStereo: Efficient Spatial-Temporal Stereo Matching Network](https://mlsanity.com/paper/2211.13755/) (2022)
- [Towards 3D Scene Reconstruction from Locally Scale-Aligned Monocular Video Depth](https://mlsanity.com/paper/2202.01470/) (2022)

## Abstract (arXiv)

We propose an online multi-view depth prediction approach on posed video streams, where the scene geometry information computed in the previous time steps is propagated to the current time step in an efficient and geometrically plausible way. The backbone of our approach is a real-time capable, lightweight encoder-decoder that relies on cost volumes computed from pairs of images. We extend it by placing a ConvLSTM cell at the bottleneck layer, which compresses an arbitrary amount of past information in its states. The novelty lies in propagating the hidden state of the cell by accounting for the viewpoint changes between time steps. At a given time step, we warp the previous hidden state into the current camera plane using the previous depth prediction. Our extension brings only a small overhead of computation time and memory consumption, while improving the depth predictions significantly. As a result, we outperform the existing state-of-the-art multi-view stereo methods on most of the evaluated metrics in hundreds of indoor scenes while maintaining a real-time performance. Code available: https://github.com/ardaduz/deep-video-mvs