TY - GEN
T1 - Take Your Model Further
T2 - 37th AAAI Conference on Artificial Intelligence, AAAI 2023
AU - Chen, Rongshan
AU - Sheng, Hao
AU - Yang, Da
AU - Wang, Sizhe
AU - Cui, Zhenglong
AU - Cong, Ruixuan
N1 - Publisher Copyright:
Copyright © 2023, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2023/6/27
Y1 - 2023/6/27
N2 - Most existing light field (LF) disparity estimation algorithms focus on handling occlusion, texture-less or other areas that harm LF structure to improve accuracy, while ignoring other potential modeling ideas. In this paper, we propose a novel idea called Bad Pixel (BadPix) correction for method modeling, then implement a general post-refinement network for LF disparity estimation: Bad-pixel Correction Network (BpCNet). Given an initial disparity map generated by a specific algorithm, we assume that all BadPixs on it are in a small range. Then BpCNet is modeled as a fine-grained search strategy, and a more accurate result can be obtained by evaluating the consistency of LF images in this limited range. Due to the assumption and the consistency between input and output, BpCNet can perform as a general post-refinement network, and can work on almost all existing algorithms iteratively. We demonstrate the feasibility of our theory through extensive experiments, and achieve remarkable performance on the HCI 4D Light Field Benchmark.
AB - Most existing light field (LF) disparity estimation algorithms focus on handling occlusion, texture-less or other areas that harm LF structure to improve accuracy, while ignoring other potential modeling ideas. In this paper, we propose a novel idea called Bad Pixel (BadPix) correction for method modeling, then implement a general post-refinement network for LF disparity estimation: Bad-pixel Correction Network (BpCNet). Given an initial disparity map generated by a specific algorithm, we assume that all BadPixs on it are in a small range. Then BpCNet is modeled as a fine-grained search strategy, and a more accurate result can be obtained by evaluating the consistency of LF images in this limited range. Due to the assumption and the consistency between input and output, BpCNet can perform as a general post-refinement network, and can work on almost all existing algorithms iteratively. We demonstrate the feasibility of our theory through extensive experiments, and achieve remarkable performance on the HCI 4D Light Field Benchmark.
UR - https://www.scopus.com/pages/publications/85167720524
U2 - 10.1609/aaai.v37i1.25106
DO - 10.1609/aaai.v37i1.25106
M3 - 会议稿件
AN - SCOPUS:85167720524
T3 - Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023
SP - 331
EP - 339
BT - AAAI-23 Technical Tracks 1
A2 - Williams, Brian
A2 - Chen, Yiling
A2 - Neville, Jennifer
PB - AAAI press
Y2 - 7 February 2023 through 14 February 2023
ER -