TY - GEN
T1 - NBVC
T2 - 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020
AU - Mordohai, Philippos
AU - Batsos, Konstantinos
AU - Makadia, Ameesh
AU - Snavely, Noah
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/10/24
Y1 - 2020/10/24
N2 - We present a benchmark for online, video-based depth estimation, a problem that is not covered by the current set of benchmarks for evaluating 3D reconstruction, which focus on offline, batch reconstruction. Online depth estimation from video captured by a moving camera is a key enabling technology for compelling applications in robotics and augmented reality. Inspired by progress in many aspects of robotics due to benchmarks and datasets, we propose a new benchmark called NBVC for evaluating methods for online depth estimation from video. Our benchmark is composed of short video sequences with corresponding high-quality ground truth depth maps, derived from the recent Tanks and Temples dataset. We are hopeful that our work will be instrumental in the development of learning-based algorithms for online depth estimation from video clips, and will also lead to improvements in conventional approaches. In addition to the benchmark, we present a superpixel-based plane sweeping stereo algorithm and use it to investigate various aspects of the problem. The paper contains our initial findings and conclusions.
AB - We present a benchmark for online, video-based depth estimation, a problem that is not covered by the current set of benchmarks for evaluating 3D reconstruction, which focus on offline, batch reconstruction. Online depth estimation from video captured by a moving camera is a key enabling technology for compelling applications in robotics and augmented reality. Inspired by progress in many aspects of robotics due to benchmarks and datasets, we propose a new benchmark called NBVC for evaluating methods for online depth estimation from video. Our benchmark is composed of short video sequences with corresponding high-quality ground truth depth maps, derived from the recent Tanks and Temples dataset. We are hopeful that our work will be instrumental in the development of learning-based algorithms for online depth estimation from video clips, and will also lead to improvements in conventional approaches. In addition to the benchmark, we present a superpixel-based plane sweeping stereo algorithm and use it to investigate various aspects of the problem. The paper contains our initial findings and conclusions.
UR - http://www.scopus.com/inward/record.url?scp=85102397234&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85102397234&partnerID=8YFLogxK
U2 - 10.1109/IROS45743.2020.9340817
DO - 10.1109/IROS45743.2020.9340817
M3 - Conference contribution
AN - SCOPUS:85102397234
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 10076
EP - 10083
BT - 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020
Y2 - 24 October 2020 through 24 January 2021
ER -