Robust light field angular super-resolution via multi-dimensional feature fusion and attention-guided refinement
Xiyao Hua, Boni Su, Daili Yang · 2026
Read Robust light field angular super-resolution via multi-dimensional feature fusion and attention-guided refinement by Xiyao Hua, Boni Su, Daili Yang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0353845.txt.
Description
Hua, Su, and Yang presented a new computer method in 2026 for sharpening light field images. A light field camera records a scene from many angles at once, but cheap versions capture only a few views. Filling in the missing views is hard when objects block each other or sit at very different depths.
Their system blends clues from space, angle, and scene shape, then uses focused attention to clean up the result. Tests on both made-up and real scenes beat older methods, most clearly near blocked edges and fine textures. Better angle filling could help future cameras that let viewers shift viewpoint after a photo is taken.
Catalog record
| CREATOR | Xiyao Hua, Boni Su, Daili Yang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 66435 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |