Camera movement understanding on CameraBench 10K-sample VQA subset 1.0 (test)
29.3Translation (In) ErrorRandom Chance
Evaluation results
| Method | Links | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Random Chance2026.01 | 29.3 | 9.7 | 6.7 | 8.6 | 15.8 | 11.5 | 11.1 | 10.2 | 15 | 15.4 | 12.7 | 7.7 | 8.9 | 10.2 | 9.7 | 12.2 | |
| COLMAP2026.01 | 36.2 | 13.1 | 11.9 | 19.7 | 34.1 | 30 | 13.9 | 14.2 | 43.9 | 46.4 | 28.3 | 19.1 | 42.1 | 48.7 | 7.5 | 27.3 | |
| MASt3R2026.01 | 47.5 | 21.1 | 23.5 | 40.2 | 38.7 | 38.1 | 42.2 | 46.6 | 66.6 | 58 | 63.2 | 40.3 | 50.4 | 53.5 | 15.7 | 43.1 | |
| LLaVA-OneVisionParameters=7B2026.01 | 48.2 | 13.9 | 13 | 17.4 | 24.4 | 20.8 | 11 | 14.8 | 34.5 | 34.6 | 17.4 | 32.3 | 19.9 | 21.4 | 19.4 | 22.9 | |
| InternLMXComposer2.5Parameters=7B2026.01 | 50.5 | 10.9 | 11.7 | 10.7 | 15 | 10.9 | 12.2 | 17 | 14.7 | 14.3 | 15.1 | 18 | 12.1 | 18.6 | 22.5 | 17 | |
| LLaVA-VideoParameters=7B2026.01 | 56.3 | 15.7 | 17 | 19.9 | 27.9 | 24.3 | 16.7 | 17.4 | 34.6 | 37.9 | 27.7 | 38.3 | 16.6 | 22.4 | 22.8 | 26.4 | |
| VGGSFM2026.01 | 56.6 | 28.9 | 28.7 | 38.2 | 48.9 | 35.3 | 21.7 | 17.3 | 60.9 | 58.7 | 46.6 | 43.3 | 61.4 | 55.5 | 16.7 | 41.3 | |
| Qwen2.5-VLParameters=7B2026.01 | 57.7 | 15.3 | 19.3 | 31.4 | 35.5 | 28.4 | 30.7 | 44.7 | 64.6 | 68.7 | 56.1 | 35.1 | 19.4 | 24.9 | 20.4 | 36.9 | |
| DUSt3R2026.01 | 58.9 | 24 | 30.7 | 18 | 38.3 | 26.9 | 18.2 | 24.6 | 59.4 | 63.8 | 32.9 | 27.3 | 61 | 57.9 | 13.1 | 37 | |
| Qwen2.5-VLParameters=32B2026.01 | 59.3 | 16.9 | 20.8 | 33.1 | 37.1 | 30.1 | 32.3 | 46.4 | 66.2 | 70.2 | 57.7 | 36.7 | 20.8 | 26.5 | 21.8 | 38.4 | |
| Qwen2.5-VLParameters=72B2026.01 | 59.7 | 17.3 | 21.2 | 33.5 | 37.5 | 30.4 | 32.7 | 46.8 | 66.6 | 70.7 | 58.1 | 37.1 | 21.2 | 26.9 | 22.2 | 38.8 | |
| Tarsier-RecapParameters=7B2026.01 | 61.5 | 15.6 | 26.5 | 24.4 | 29.7 | 22.1 | 14.8 | 15.5 | 23.5 | 28.1 | 25.3 | 22.2 | 15.7 | 19.3 | 31.6 | 21.6 | |
| InternVL3Parameters=8B2026.01 | 63 | 16 | 19.4 | 29.9 | 31.4 | 28.1 | 30.4 | 28.9 | 42.8 | 50.8 | 43.3 | 37.6 | 21.9 | 23 | 20.7 | 32.4 | |
| InternVL2.5Parameters=26B2026.01 | 65.5 | 12.2 | 21.7 | 24.3 | 28 | 20 | 22.5 | 32.5 | 43.8 | 39.4 | 46.2 | 44.9 | 14.7 | 18.7 | 25.9 | 30.7 | |
| GPT-4o2026.01 | 68.3 | 30.1 | 21.7 | 39.3 | 39.1 | 22.6 | 43 | 40.5 | 46 | 43.4 | 44.9 | 36.6 | 24.7 | 29.6 | 33 | 37.5 | |
| CamReasoner-7BParameters=7B2026.01 | 68.7 | 57.7 | 84.9 | 80.5 | 84.6 | 83.2 | 74.2 | 72.8 | 85.7 | 86.1 | 87.6 | 85.7 | 75.5 | 70.2 | 80.1 | 78.4 | |
| CUT3R2026.01 | 68.9 | 50.4 | 24.7 | 34.2 | 37 | 27.6 | 15.9 | 21.3 | 59.1 | 65 | 65 | 47.5 | 60.7 | 66.2 | 15.1 | 42.7 | |
| InternVL2.5Parameters=8B2026.01 | 69.9 | 13.3 | 28.9 | 26.7 | 24.1 | 23.9 | 19.2 | 33.1 | 38.5 | 31.8 | 38.7 | 38 | 11.8 | 26.1 | 24.1 | 30.4 | |
| InternVideo2-ChatParameters=8B2026.01 | 72 | 19.1 | 19.9 | 18.1 | 18.4 | 24.1 | 12.6 | 10.7 | 23.3 | 23.4 | 17.7 | 23.5 | 20.2 | 16.9 | 20.8 | 22.7 | |
| MegaSAM2026.01 | 73.8 | 43.9 | 24.2 | 29.1 | 45.3 | 44.2 | 11.1 | 10.2 | 79.5 | 82.2 | 73.8 | 65.3 | 71.5 | 75.8 | 22 | 50.1 | |
| InternVL3Parameters=78B2026.01 | 74.2 | 18.7 | 20.2 | 33.5 | 34.8 | 30.3 | 27.2 | 34.4 | 48.6 | 55.1 | 49.2 | 41.5 | 28.4 | 25.8 | 23.3 | 37.9 | |
| Cam-MotionParameters=7B2026.01 | 86.4 | 40.5 | 29.2 | 50.2 | 71.3 | 52.5 | 57.2 | 79.6 | 83.2 | 87.1 | 80.1 | 71 | 33.9 | 43.1 | 77.3 | 63 | |
| Cam-MotionParameters=32B2026.01 | 88.2 | 42.1 | 30.8 | 51.9 | 73.1 | 54.1 | 58.8 | 81.2 | 84.7 | 88.8 | 81.8 | 72.7 | 35.6 | 44.8 | 79.2 | 64.7 | |
| Cam-MotionParameters=72B2026.01 | 89.4 | 43.4 | 32 | 53.1 | 74.2 | 55.2 | 60 | 82.4 | 86 | 90.1 | 83.1 | 73.9 | 36.8 | 46 | 80.4 | 65.9 |