Robust pose estimation which guarantees positive depths
Chun Li, John E. McInroy · 2023
Read Robust pose estimation which guarantees positive depths by Chun Li, John E. McInroy (2023) 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/pmc-10719315.txt.
Description
Chun Li and John McInroy published a computer vision paper in two thousand twenty-three on estimating camera pose. Working out how a camera moved between two views is core to 3D vision. Standard methods wobble under noise and can place points behind the camera, a physical impossibility handled only by after-the-fact checks.
The authors derived a new algorithm that estimates point depths directly, baking the positive-depth requirement into the maths itself. On synthetic and real tests it matched leading methods for reprojection accuracy under heavy noise. Unlike rivals, it guaranteed positive depths for every point by construction. The paper offers the derivation plus benchmarks as its contribution.
Catalog record
| CREATOR | Chun Li, John E. McInroy |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 135 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |