Model card
PesRec.
Xingwen Cao et al. (LIESMARS, Wuhan University)open-sourceMulti-task CNN: spatial layout estimator + 3D object detector + mesh generator
End-to-end parametric indoor semantic scene reconstruction from a single RGB image. Published in International Journal of Applied Earth Observation and Geoinformation, Sep 2024.
§ 01 · Benchmarks
Every benchmark PesRec has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | sun-rgb-d | Computer Vision · Optical Character Recognition | iou | 79.7% | #1 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 05 · Sources & freshness
Where these numbers come from.
journal
1
result
1 of 1 rows marked verified.