Light Field Depth Estimation via Stitched Epipolar Plane Images
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Pages (from-to) | 6866-6879 |
Journal / Publication | IEEE Transactions on Visualization and Computer Graphics |
Volume | 30 |
Issue number | 10 |
Online published | 19 Dec 2023 |
Publication status | Published - Oct 2024 |
Link(s)
Abstract
Depth estimation is a fundamental problem in light field processing. Epipolar-plane image (EPI)-based methods often encounter challenges such as low accuracy in slope computation due to discretization errors and limited angular resolution. Besides, existing methods perform well in most regions but struggle to produce sharp edges in occluded regions and resolve ambiguities in texture-less regions. To address these issues, we propose the concept of stitched-EPI (SEPI) to enhance slope computation. SEPI achieves this by shifting and concatenating lines from different EPIs that correspond to the same 3D point. Moreover, we introduce the half-SEPI algorithm, which focuses exclusively on the non-occluded portion of lines to handle occlusion. Additionally, we present a depth propagation strategy aimed at improving depth estimation in texture-less regions. This strategy involves determining the depth of such regions by progressing from the edges towards the interior, prioritizing accurate regions over coarse regions. Through extensive experimental evaluations and ablation studies, we validate the effectiveness of our proposed method. The results demonstrate its superior ability to generate more accurate and robust depth maps across all regions compared to state-of-the-art methods. © 2023 IEEE.
Research Area(s)
- Light Field, Depth Estimation, Stitched-EPI, Occlusion, Texture-less Region
Bibliographic Note
Research Unit(s) information for this publication is provided by the author(s) concerned.
Citation Format(s)
Light Field Depth Estimation via Stitched Epipolar Plane Images. / Zhou, Ping; Shi, Langqing; Liu, Xiaoyang et al.
In: IEEE Transactions on Visualization and Computer Graphics, Vol. 30, No. 10, 10.2024, p. 6866-6879.
In: IEEE Transactions on Visualization and Computer Graphics, Vol. 30, No. 10, 10.2024, p. 6866-6879.
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review