Token-Budgeted Candidate Retrieval for 3D Scene-Grounded VLMs: Category Names vs. Pairwise Geometry
arXiv:2610.14207v1 Announce Type: new Abstract: Under a fixed context budget, which objects and relations should a 3D scene-grounded VLM see first? On ScanNet indoor referring benchmarks (Dai et al., 2017), matching the query to object category names outperforms pairwise geometry scoring at every r…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-14 04:00 · arXiv cs.CV
Token-Budgeted Candidate Retrieval for 3D Scene-Grounded VLMs: Category Names vs. Pairwise Geometry