mlsanityData to 7 Oct 2026

Revisiting PatchMatch Multi-View Stereo for Urban 3D Reconstruction

arXiv 2207.08439 ↗First posted 18 Jul 2022cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

In this paper, a complete pipeline for image-based 3D reconstruction of urban scenarios is proposed, based on PatchMatch Multi-View Stereo (MVS). Input images are firstly fed into an off-the-shelf visual SLAM system to extract camera poses and sparse keypoints, which are used to initialize PatchMatch optimization. Then, pixelwise depths and normals are iteratively computed in a multi-scale framework with a novel depth-normal consistency loss term and a global refinement algorithm to balance the inherently local nature of PatchMatch. Finally, a large-scale point cloud is generated by back-projecting multi-view consistent estimates in 3D. The proposed approach is carefully evaluated against both classical MVS algorithms and monocular depth networks on the KITTI dataset, showing state of the art performances.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 24 of its 37 references that are in the map. First posted on arXiv 18 Jul 2022.

Builds on

24 of 37 references.

References · 24

  1. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  2. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  3. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  4. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  5. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  6. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  7. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 379
  8. 2017Sparsity Invariant CNNscited by 325
  9. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  10. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  11. 2019Multi-Scale Geometric Consistency Guided Multi-View Stereocited by 105
  12. 2018DeepTAM: Deep Tracking and Mappingcited by 87
12 more
  1. 2018Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometrycited by 85
  2. 2020MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Cameracited by 59
  3. 2019Planar Prior Assisted PatchMatch Multi-View Stereocited by 57
  4. 2018LEGO: Learning Edge with Geometry all at Once by Watching Videoscited by 47
  5. 2019TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereocited by 34
  6. 2019Robust Semi-Supervised Monocular Depth Estimation with Reprojected Distancescited by 27
  7. 2019DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstructioncited by 23
  8. 2020Boosting Monocular Depth Estimation with Lightweight 3D Point Fusioncited by 14
  9. 2021Advancing Self-supervised Monocular Depth Learning with Sparse LiDARcited by 13
  10. 2019Joint Graph-based Depth Refinement and Normal Estimationcited by 12
  11. 2019Self-supervised Learning for Single View Depth and Surface Normal Estimationcited by 8
  12. 2018Multi-View Stereo with Asymmetric Checkerboard Propagation and Multi-Hypothesis Joint View Selectioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 0; 2026: 1.

3 papers.

  1. 2022Learning Neural Radiance Fields from Multi-View Geometrycited by 1
  2. 2023Informative Rays Selection for Few-Shot Neural Radiance Fieldscited by 1
  3. 2026City-Mesh3R: Simulation-Ready City-Scale 3D Mesh Reconstruction from Multi-View Imagescited by 0