TY - GEN
T1 - Measuring the effects of temporal coherence in depth estimation for dynamic scenes
AU - Tsekourakis, Iraklis
AU - Mordohai, Philippos
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - This paper presents a new algorithm for enforcing temporal coherence on depth estimation from multi-view videos of dynamic scenes as well as the first substantial quantitative evaluation of the improvement in depth estimation accuracy due to temporal coherence. The proposed algorithm is generally applicable and practical since it bypasses explicit scene flow estimation, which has a very large state space, and relies only on optical flow which is used to impose soft constraints on depth estimation for the next frame. As a result, our algorithm is applicable to scenes with large depth and motion ranges. The output is a sequence of depth maps that can be used for novel view synthesis among other applications. While it is intuitive that enforcing temporal coherence should improve the accuracy of depth estimation, this improvement has never been assessed quantitatively due to the lack of data with ground truth. To overcome this limitation we use the image prediction error as the criterion and show that the benefits of temporal coherence are significant on a diverse set of multi-view video sequences.
AB - This paper presents a new algorithm for enforcing temporal coherence on depth estimation from multi-view videos of dynamic scenes as well as the first substantial quantitative evaluation of the improvement in depth estimation accuracy due to temporal coherence. The proposed algorithm is generally applicable and practical since it bypasses explicit scene flow estimation, which has a very large state space, and relies only on optical flow which is used to impose soft constraints on depth estimation for the next frame. As a result, our algorithm is applicable to scenes with large depth and motion ranges. The output is a sequence of depth maps that can be used for novel view synthesis among other applications. While it is intuitive that enforcing temporal coherence should improve the accuracy of depth estimation, this improvement has never been assessed quantitatively due to the lack of data with ground truth. To overcome this limitation we use the image prediction error as the criterion and show that the benefits of temporal coherence are significant on a diverse set of multi-view video sequences.
UR - http://www.scopus.com/inward/record.url?scp=85083334749&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85083334749&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2019.00346
DO - 10.1109/CVPRW.2019.00346
M3 - Conference contribution
AN - SCOPUS:85083334749
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 2867
EP - 2875
BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
Y2 - 16 June 2019 through 20 June 2019
ER -