V-FUSE: Volumetric Depth Map Fusion with Long-Range Constraints

Nathaniel Burgdorfer, Philippos Mordohai

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We introduce a learning-based depth map fusion framework that accepts a set of depth and confidence maps generated by a Multi-View Stereo (MVS) algorithm as input and improves them. This is accomplished by integrating volumetric visibility constraints that encode long-range surface relationships across different views into an end-to-end trainable architecture. We also introduce a depth search window estimation sub-network trained jointly with the larger fusion sub-network to reduce the depth hypothesis search space along each ray. Our method learns to model depth consensus and violations of visibility constraints directly from the data; effectively removing the necessity of fine-tuning fusion parameters. Extensive experiments on MVS datasets show substantial improvements in the accuracy of the output fused depth and confidence maps. Our code is available at https://github.com/nburgdorfer/V-FUSE

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
Pages3426-3435
Number of pages10
ISBN (Electronic)9798350307184
DOIs
StatePublished - 2023
Event2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 - Paris, France
Duration: 2 Oct 20236 Oct 2023

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
ISSN (Print)1550-5499

Conference

Conference2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
Country/TerritoryFrance
CityParis
Period2/10/236/10/23

Fingerprint

Dive into the research topics of 'V-FUSE: Volumetric Depth Map Fusion with Long-Range Constraints'. Together they form a unique fingerprint.

Cite this