# Point-Based Multi-View Stereo Network

arXiv: https://arxiv.org/abs/1908.04422 · HTML: https://mlsanity.com/paper/1908.04422/

## Key facts

- Cited by 147 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2019.

## Built on by (most cited first, 30 of 147)

- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [Neuralangelo: High-Fidelity Neural Surface Reconstruction](https://mlsanity.com/paper/2306.03092/) (2023)
- [Unifying Voxel-based Representation with Transformer for 3D Object Detection](https://mlsanity.com/paper/2206.00630/) (2022)
- [GaussianPro: 3D Gaussian Splatting with Progressive Propagation](https://mlsanity.com/paper/2402.14650/) (2024)
- [Iterative Geometry Encoding Volume for Stereo Matching](https://mlsanity.com/paper/2303.06615/) (2023)
- [Efficient Neural Radiance Fields for Interactive Free-viewpoint Video](https://mlsanity.com/paper/2112.01517/) (2021)
- [Improving neural implicit surfaces geometry with patch warping](https://mlsanity.com/paper/2112.09648/) (2021)
- [NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction](https://mlsanity.com/paper/2203.11283/) (2022)
- [NeuTex: Neural Texture Mapping for Volumetric Neural Rendering](https://mlsanity.com/paper/2103.00762/) (2021)
- [BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereo](https://mlsanity.com/paper/2209.10248/) (2022)
- [Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation](https://mlsanity.com/paper/2201.01501/) (2022)
- [SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation](https://mlsanity.com/paper/2204.03636/) (2022)
- [Large Spatial Model: End-to-end Unposed Images to Semantic 3D](https://mlsanity.com/paper/2410.18956/) (2024)
- [AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network](https://mlsanity.com/paper/2108.03824/) (2021)
- [IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo](https://mlsanity.com/paper/2112.05126/) (2021)
- [LaRa: Efficient Large-Baseline Radiance Fields](https://mlsanity.com/paper/2407.04699/) (2024)
- [Multiview Stereo with Cascaded Epipolar RAFT](https://mlsanity.com/paper/2205.04502/) (2022)
- [MVSTER: Epipolar Transformer for Efficient Multi-View Stereo](https://mlsanity.com/paper/2204.07346/) (2022)
- [Voxel Field Fusion for 3D Object Detection](https://mlsanity.com/paper/2205.15938/) (2022)
- [Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry](https://mlsanity.com/paper/2112.08177/) (2021)
- [VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction](https://mlsanity.com/paper/2108.08623/) (2021)
- [MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions](https://mlsanity.com/paper/2104.13325/) (2021)
- [Category-Level Metric Scale Object Shape and Pose Estimation](https://mlsanity.com/paper/2109.00326/) (2021)
- [StereOBJ-1M: Large-scale Stereo Image Dataset for 6D Object Pose Estimation](https://mlsanity.com/paper/2109.10115/) (2021)
- [Matrix3D: Large Photogrammetry Model All-in-One](https://mlsanity.com/paper/2502.07685/) (2025)
- [TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo](https://mlsanity.com/paper/2111.07418/) (2021)
- [VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and Fusion](https://mlsanity.com/paper/2112.00236/) (2021)
- [ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation](https://mlsanity.com/paper/2510.23306/) (2025)
- [Generalized Binary Search Network for Highly-Efficient Multi-View Stereo](https://mlsanity.com/paper/2112.02338/) (2021)
- [Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation](https://mlsanity.com/paper/2104.05374/) (2021)

## Abstract (arXiv)

We introduce Point-MVSNet, a novel point-based deep framework for multi-view stereo (MVS). Distinct from existing cost volume approaches, our method directly processes the target scene as point clouds. More specifically, our method predicts the depth in a coarse-to-fine manner. We first generate a coarse depth map, convert it into a point cloud and refine the point cloud iteratively by estimating the residual between the depth of the current iteration and that of the ground truth. Our network leverages 3D geometry priors and 2D texture information jointly and effectively by fusing them into a feature-augmented point cloud, and processes the point cloud to estimate the 3D flow for each point. This point-based architecture allows higher accuracy, more computational efficiency and more flexibility than cost-volume-based counterparts. Experimental results show that our approach achieves a significant improvement in reconstruction quality compared with state-of-the-art methods on the DTU and the Tanks and Temples dataset. Our source code and trained models are available at https://github.com/callmeray/PointMVSNet .