TY - GEN
T1 - AI-based Holl-filling with Temporal Consistency
AU - Chen, Li Jyun
AU - Yang, Jar Ferr
AU - Hong, Li
N1 - Funding Information:
This work was partially supported by the Ministry of Science and Technology under Grant MOST 109-2218-E-006-032 and Qualcomm, USA under Grant SOW#NAT-435536.
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Depth image-based rendering (DIBR) has been recently considered as a significant technology for generating 3D virtual views. However, the hole-filling method is still the main challenge in the DIBR engine because of the occlusions of foreground objects. While looking into the video sequences, the occluded parts in a frame may be revealed in the past or future frames. The temporal information could be the useful cues to recover the occlusions of the current frame. In this paper, we design an encoder-decoder neural model with a bounded region attention module to effectively fill the holes. This attention module is aim to extract the useful hints from neighbor frames.
AB - Depth image-based rendering (DIBR) has been recently considered as a significant technology for generating 3D virtual views. However, the hole-filling method is still the main challenge in the DIBR engine because of the occlusions of foreground objects. While looking into the video sequences, the occluded parts in a frame may be revealed in the past or future frames. The temporal information could be the useful cues to recover the occlusions of the current frame. In this paper, we design an encoder-decoder neural model with a bounded region attention module to effectively fill the holes. This attention module is aim to extract the useful hints from neighbor frames.
UR - http://www.scopus.com/inward/record.url?scp=85124141540&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85124141540&partnerID=8YFLogxK
U2 - 10.1109/ISPACS51563.2021.9651045
DO - 10.1109/ISPACS51563.2021.9651045
M3 - Conference contribution
AN - SCOPUS:85124141540
T3 - ISPACS 2021 - International Symposium on Intelligent Signal Processing and Communication Systems: 5G Dream to Reality, Proceeding
BT - ISPACS 2021 - International Symposium on Intelligent Signal Processing and Communication Systems
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2021
Y2 - 16 November 2021 through 19 November 2021
ER -