# TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo

arXiv: https://arxiv.org/abs/1903.10929 · HTML: https://mlsanity.com/paper/1903.10929/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Mar 2019.

## Built on by (most cited first, 30 of 34)

- [Neural 3D Scene Reconstruction with the Manhattan-world Assumption](https://mlsanity.com/paper/2205.02836/) (2022)
- [Multiview Stereo with Cascaded Epipolar RAFT](https://mlsanity.com/paper/2205.04502/) (2022)
- [Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Physically-Grounded Augmentations](https://mlsanity.com/paper/2207.01164/) (2022)
- [PlaneMVS: 3D Plane Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2203.12082/) (2022)
- [HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes with Iterative Intertwined Regularization](https://mlsanity.com/paper/2302.14340/) (2023)
- [SD-MVS: Segmentation-Driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization](https://mlsanity.com/paper/2401.06385/) (2024)
- [PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibility](https://mlsanity.com/paper/2108.08943/) (2021)
- [MSP-MVS: Multi-Granularity Segmentation Prior Guided Multi-View Stereo](https://mlsanity.com/paper/2407.19323/) (2024)
- [A Confidence-based Iterative Solver of Depths and Surface Normals for Deep Multi-view Stereo](https://mlsanity.com/paper/2201.07609/) (2022)
- [GUS-IR: Gaussian Splatting with Unified Shading for Inverse Rendering](https://mlsanity.com/paper/2411.07478/) (2024)
- [SED-MVS: Segmentation-Driven and Edge-Aligned Deformation Multi-View Stereo with Depth Restoration and Occlusion Constraint](https://mlsanity.com/paper/2503.13721/) (2025)
- [Neural Vector Fields for Implicit Surface Representation and Inference](https://mlsanity.com/paper/2204.06552/) (2022)
- [TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo](https://mlsanity.com/paper/2308.09990/) (2023)
- [PHI-MVS: Plane Hypothesis Inference Multi-view Stereo for Large-Scale Scene Reconstruction](https://mlsanity.com/paper/2104.06165/) (2021)
- [PlaNeRF: SVD Unsupervised 3D Plane Regularization for NeRF Large-Scale Scene Reconstruction](https://mlsanity.com/paper/2305.16914/) (2023)
- [Hierarchical Prior Mining for Non-local Multi-View Stereo](https://mlsanity.com/paper/2303.09758/) (2023)
- [A Survey on 3D Reconstruction Techniques in Plant Phenotyping: From Classical Methods to Neural Radiance Fields (NeRF), 3D Gaussian Splatting (3DGS), and Beyond](https://mlsanity.com/paper/2505.00737/) (2025)
- [Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization](https://mlsanity.com/paper/2412.20328/) (2024)
- [DVP-MVS++: Synergize Depth-Normal-Edge and Harmonized Visibility Prior for Multi-View Stereo](https://mlsanity.com/paper/2506.13215/) (2025)
- [PatchMVSNet: Patch-wise Unsupervised Multi-View Stereo for Weakly-Textured Surface Reconstruction](https://mlsanity.com/paper/2203.02156/) (2022)
- [Revisiting PatchMatch Multi-View Stereo for Urban 3D Reconstruction](https://mlsanity.com/paper/2207.08439/) (2022)
- [Rethinking Disparity: A Depth Range Free Multi-View Stereo Based on Disparity](https://mlsanity.com/paper/2211.16905/) (2022)
- [Polarimetric PatchMatch Multi-View Stereo](https://mlsanity.com/paper/2311.07600/) (2023)
- [A Global Depth-Range-Free Multi-View Stereo Transformer Network with Pose Embedding](https://mlsanity.com/paper/2411.01893/) (2024)
- [Visibility-Aware Pixelwise View Selection for Multi-View Stereo Matching](https://mlsanity.com/paper/2302.07182/) (2023)
- [P2SDF for Neural Indoor Scene Reconstruction](https://mlsanity.com/paper/2303.00236/) (2023)
- [Deep PatchMatch MVS with Learned Patch Coplanarity, Geometric Consistency and Adaptive Pixel Sampling](https://mlsanity.com/paper/2210.07582/) (2022)
- [Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo](https://mlsanity.com/paper/2312.15970/) (2023)
- [VisTa3D: A Dataset and Benchmark for Thin Object Reconstruction from Vision, Tactile, and 3D Point Clouds](https://mlsanity.com/paper/2608.20740/) (2026)
- [Improving Multi-View Stereo via Super-Resolution](https://mlsanity.com/paper/2107.13261/) (2021)

## Abstract (arXiv)

One of the most successful approaches in Multi-View Stereo estimates a depth map and a normal map for each view via PatchMatch-based optimization and fuses them into a consistent 3D points cloud. This approach relies on photo-consistency to evaluate the goodness of a depth estimate. It generally produces very accurate results; however, the reconstructed model often lacks completeness, especially in correspondence of broad untextured areas where the photo-consistency metrics are unreliable. Assuming the untextured areas piecewise planar, in this paper we generate novel PatchMatch hypotheses so to expand reliable depth estimates in neighboring untextured regions. At the same time, we modify the photo-consistency measure such to favor standard or novel PatchMatch depth hypotheses depending on the textureness of the considered area. We also propose a depth refinement step to filter wrong estimates and to fill the gaps on both the depth maps and normal maps while preserving the discontinuities. The effectiveness of our new methods has been tested against several state of the art algorithms in the publicly available ETH3D dataset containing a wide variety of high and low-resolution images.