IA-MVS: Instance-Focused Adaptive Depth Sampling for Multi-View Stereo
Not on the map. Why?
Abstract (arXiv)
Multi-view stereo (MVS) models based on progressive depth hypothesis narrowing have made remarkable advancements. However, existing methods haven't fully utilized the potential that the depth coverage of individual instances is smaller than that of the entire scene, which restricts further improvements in depth estimation precision. Moreover, inevitable deviations in the initial stage accumulate as the process advances. In this paper, we propose Instance-Adaptive MVS (IA-MVS). It enhances the precision of depth estimation by narrowing the depth hypothesis range and conducting refinement on each instance. Additionally, a filtering mechanism based on intra-instance depth continuity priors is incorporated to boost robustness. Furthermore, recognizing that existing confidence estimation can degrade IA-MVS performance on point clouds. We have developed a detailed mathematical model for confidence estimation based on conditional probability. The proposed method can be widely applied in models based on MVSNet without imposing extra training burdens. Our method achieves state-of-the-art performance on the DTU benchmark. The source code is available at https://github.com/KevinWang73106/IA-MVS.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 35 references that are in the map. First posted on arXiv 19 May 2025.
Builds on
28 of 35 references.
References · 28
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2023Segment Anythingcited by 8,234
- 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
- 2016Pyramid Scene Parsing Networkcited by 2,479
- 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
- 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
- 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,222
- 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
- 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 718
- 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
- 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 417
- 2020PatchmatchNet: Learned Multi-View Patchmatch Stereocited by 207
16 more
- 2023EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anythingcited by 188
- 2019Cost Volume Pyramid Based Depth Inference for Multi-View Stereocited by 154
- 2019Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awarenesscited by 151
- 2021TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformerscited by 117
- 2020Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinementcited by 105
- 2022Rethinking Depth Estimation for Multi-View Stereo: A Unified Representationcited by 82
- 2021AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Networkcited by 71
- 2022MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depthcited by 53
- 2024MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereocited by 50
- 2021Generalized Binary Search Network for Highly-Efficient Multi-View Stereocited by 32
- 2022WT-MVSNet: Window-based Transformers for Multi-view Stereocited by 20
- 2021Curvature-guided dynamic scale networks for Multi-view Stereocited by 17
- 2024GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereocited by 16
- 2023When Epipolar Constraint Meets Non-local Operators in Multi-View Stereocited by 14
- 2023CostFormer:Cost Transformer for Cost Aggregation in Multi-view Stereocited by 9
- 2023GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereocited by 8
Built on by
Not cited yet.