Controllable Multi-Object Insertion for Detection Data Augmentation
arXiv:2610.26922v1 Announce Type: new Abstract: Controllable object insertion provides a targeted approach to augmenting object detection datasets that require category--count fidelity, annotation alignment, and source-content preservation beyond visual realism. Several approaches have been propose…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-21 04:00 · arXiv cs.CV
Controllable Multi-Object Insertion for Detection Data Augmentation