Multi-View Depth Estimation by Using Adaptive Point Graph to Fuse Single-View Depth Probabilities
- 24 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (7) , 6400-6407
Abstract
Recently, some methods estimate depth maps by fusing several adjacent single-view depth probabilities. They have achieved promising performance in multi-view inconsistent areas, such as texture-less surfaces, reflective surfaces, and moving objects. However, these methods involve two new problems: their thin cost volumes contain many invalid values, and the depths of adjacent volume units tend to be very different, which hinders the valid fusion of multi-view information. To deal with these issues, we design a novel point graph based single-views fusing method to estimate depth maps from several sequential images. Our method first estimates the initial probabilistic distribution of the depth map for input images, the distribution is parameterized as a pixel-wise depth and uncertainty. Then, we sample non-uniform depth candidates from the reference image's initial distribution. Diverse from the popular 3D cost volume, we utilize sampled depth candidates to construct an adaptive local point graph to represent multi-view geometric constraints. For pixels with multi-view consistency, we aggregate their local graphs to update their initial depths. And take the updated pixels as control points to refine the depth of the remaining pixels. We demonstrate the effectiveness of the proposed method by quantitative and qualitative comparisons with recent baseline works on the KITTI Odometry dataset and the DADD dataset, and our results surpass all competing methods even without 3D cost volume.Keywords
Funding Information
- National Key R&D Program of China (2023YFC3081700, 2022YFC3803702)
This publication has 24 references indexed in Scilit:
- Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth2022
- AdaBins: Depth Estimation Using Adaptive Bins2021
- The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth2021
- MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera2021
- Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching2020
- 3D Packing for Self-Supervised Monocular Depth Estimation2020
- MVSNet: Depth Inference for Unstructured Multi-view Stereo2018
- Pyramid Stereo Matching Network2018
- Deep Ordinal Regression Network for Monocular Depth Estimation2018
- Video-based, real-time multi-view stereoImage and Vision Computing, 2011