research
Synthetic Spatial Hints Transferred to Real Images
Privileged coordinates used only in training raised six real-world vision benchmarks by 3.23 points on average.
Summary
Privileged coordinates used only in training raised six real-world vision benchmarks by 3.23 points on average.
Where-OPD gives a teacher textual spatial guidance from procedurally generated scenes while the student sees only the image and question. The teacher locates and combines evidence across relevant regions; the student learns that behavior without human grounding labels or an external teacher model. Training only on synthetic scenes improved counting, document and chart tasks and produced a 3.23-point average gain across six real-world perception benchmarks. The transfer is measured on the reported models and tests.
Why it matters
Privileged coordinates used only in training raised six real-world vision benchmarks by 3.23 points on average.
Limits and context
- Where-OPD gives a teacher textual spatial guidance from procedurally generated scenes while the student sees only the image and question.
- Training only on synthetic scenes improved counting, document and chart tasks and produced a 3.23-point average gain across six real-world perception benchmarks.
Key claims
Privileged coordinates used only in training raised six real-world vision benchmarks by 3.23 points on average.
Qualification: Where-OPD gives a teacher textual spatial guidance from procedurally generated scenes while the student sees only the image and question.
Evidence: source-2026-10-02-010
Sources
- arXiv preprint 2610.02117arXiv · primary research
Corrections
No corrections have been recorded for this story.