TY - GEN
T1 - V-FUSE
T2 - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
AU - Burgdorfer, Nathaniel
AU - Mordohai, Philippos
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - 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
AB - 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
UR - http://www.scopus.com/inward/record.url?scp=85185876554&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85185876554&partnerID=8YFLogxK
U2 - 10.1109/ICCV51070.2023.00319
DO - 10.1109/ICCV51070.2023.00319
M3 - Conference contribution
AN - SCOPUS:85185876554
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 3426
EP - 3435
BT - Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
Y2 - 2 October 2023 through 6 October 2023
ER -