Abstract | ||
---|---|---|
2D image editing has been a well-studied problem. However, 2D image processing techniques cannot be directly applied to the emerging light field image (LFI) due to the particular structural characteristics of LFI. Without a dedicatedly designed editing scheme for LFI, users need to manually edit each sub-view of the LFI. This process is extremely time consuming, and more importantly, users have no ways to guarantee parallax consistency between sub-views. This poster proposes two different LFI editing schemes including the direct editing scheme and the deep-learning-based scheme. These schemes enable automatic propagation of the user’s edits, particularly “augmentation” editing, from central view to all the other sub-views of LFI. In particular, the learning-based scheme employs interleaved spatial-angular convolutions (4D CNN) to enable effective learning of both spatial and angular features, which are subsequently used to help the augmentation editing. We constructed a preliminary LFI dataset and compared the proposed two schemes. The experimental results show that the learning-based scheme produces higher PSNR (0.51dB) and more pleasant subjective editing results than the direct editing. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/VRW50115.2020.00153 | VR Workshops |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhicheng Lu | 1 | 0 | 1.69 |
Xiaoming Chen | 2 | 0 | 0.34 |
Yuk Ying Chung | 3 | 211 | 25.47 |
Zhibo Chen | 4 | 270 | 44.69 |