notesum.ai
Published at November 25Three Cars Approaching within 100m! Enhancing Distant Geometry by Tri-Axis Voxel Scanning for Camera-based Semantic Scene Completion
cs.CV
Released Date: November 25, 2024
Authors: Jongseong Bae1, Junwoo Ha1, Ha Young Kim2
Aff.: 1Department of Artificial Intelligence, Yonsei University; 2Graduate School of Information, Yonsei University

|
1 road 1 (15.30%) |
1 sidewalk 1 (11.13%) |
1 parking 1 (1.12%) |
1 other-grnd. 1 (0.56%) |
1 building 1 (14.1%) |
1 car 1 (3.92%) |
1 truck 1 (0.16%) |
1 bicycle 1 (0.03%) |
1 motorcycle 1 (0.03%) |
1 other-veh. 1 (0.20%) |
1 vegetation 1 (39.3%) |
1 trunk 1 (0.51%) |
1 terrain 1 (9.17%) |
1 person 1 (0.07%) |
1 bicyclist 1 (0.07%) |
1 motorcyclist 1 (0.05%) |
1 fence 1 (3.90%) |
1 pole 1 (0.29%) |
1 traf.-sign 1 (0.08%) |
||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Method | Input | IoU | mIoU | |||||||||||||||||||
| MonoScene [4] | M | 34.16 | 11.08 | 54.70 | 27.10 | 24.80 | 5.70 | 14.40 | 18.80 | 3.30 | 0.50 | 0.70 | 4.40 | 14.90 | 2.40 | 19.50 | 1.00 | 1.40 | 0.40 | 11.10 | 3.30 | 2.10 |
| TPVFormer [10] | M | 34.25 | 11.26 | 55.10 | 27.20 | 27.40 | 6.50 | 14.80 | 19.20 | 3.70 | 1.00 | 0.50 | 2.30 | 13.90 | 2.60 | 20.40 | 1.10 | 2.40 | 0.30 | 11.00 | 2.90 | 1.50 |
| SurroundOcc [31] | M | 34.72 | 11.86 | 56.90 | 28.30 | 30.20 | 6.80 | 15.20 | 20.60 | 1.40 | 1.60 | 1.20 | 4.40 | 14.90 | 3.40 | 19.30 | 1.40 | 2.00 | 0.10 | 11.30 | 3.90 | 2.40 |
| OccFormer [39] | M | 34.53 | 12.32 | 55.90 | 30.30 | 31.50 | 6.50 | 15.70 | 21.60 | 1.20 | 1.50 | 1.70 | 3.20 | 16.80 | 3.90 | 21.30 | 2.20 | 1.10 | 0.20 | 11.90 | 3.80 | 3.70 |
| IAMSSC [33] | M | 43.74 | 12.37 | 54.00 | 25.50 | 24.70 | 6.90 | 19.20 | 21.30 | 3.80 | 1.10 | 0.60 | 3.90 | 22.70 | 5.80 | 19.40 | 1.50 | 2.90 | 0.50 | 11.90 | 5.30 | 4.10 |
| VoxFormer-T [14] | S-T | 43.21 | 13.41 | 54.10 | 26.90 | 25.10 | 7.30 | 23.50 | 21.70 | 3.60 | 1.90 | 1.60 | 4.10 | 24.40 | 8.10 | 24.20 | 1.60 | 1.10 | 0.00 | 13.10 | 6.60 | 5.70 |
| HASSC-T [27] | S-T | 42.87 | 14.38 | 55.30 | 29.60 | 25.90 | 11.30 | 23.10 | 23.00 | 2.90 | 1.90 | 1.50 | 4.90 | 24.80 | 9.80 | 26.50 | 1.40 | 3.00 | 0.00 | 14.30 | 7.00 | 7.10 |
| H2GFormer-T [28] | S-T | 43.52 | 14.60 | 57.90 | 30.40 | 30.00 | 6.90 | 24.00 | 23.70 | 5.20 | 0.60 | 1.20 | 5.00 | 25.20 | 10.70 | 25.80 | 1.10 | 0.10 | 0.00 | 14.60 | 7.50 | 9.30 |
| Symphonies [11] | S | 42.19 | 15.04 | 58.40 | 29.30 | 26.90 | 11.70 | 24.70 | 23.60 | 3.20 | 3.60 | 2.60 | 5.60 | 24.20 | 10.00 | 23.10 | 3.20 | 1.90 | 2.00 | 16.10 | 7.70 | 8.00 |
| StereoScene [13] | S | 43.34 | 15.36 | 61.90 | 31.20 | 30.70 | 10.70 | 24.20 | 22.80 | 2.80 | 3.40 | 2.40 | 6.10 | 23.80 | 8.40 | 27.00 | 2.90 | 2.20 | 0.50 | 16.50 | 7.00 | 7.20 |
| MonoOcc-L [41] | S | - | 15.63 | 59.10 | 30.90 | 27.10 | 9.80 | 22.90 | 23.90 | 7.20 | 4.50 | 2.40 | 7.70 | 25.00 | 9.80 | 26.10 | 2.80 | 4.70 | 0.60 | 16.90 | 7.30 | 8.40 |
| CGFormer [38] | S | 44.41 | 16.63 | 64.30 | 34.20 | 34.10 | 12.10 | 25.80 | 26.10 | 4.30 | 3.70 | 1.30 | 2.70 | 24.50 | 11.20 | 29.30 | 1.70 | 3.60 | 0.40 | 18.70 | 8.70 | 9.30 |
| HTCL-S [12] | S-T | 44.23 | 17.09 | 64.40 | 34.80 | 33.80 | 12.40 | 25.90 | 27.30 | 10.80 | 1.80 | 2.20 | 5.40 | 25.30 | 10.80 | 31.20 | 1.10 | 3.10 | 0.90 | 21.10 | 9.00 | 8.30 |
| ScanSSC (ours) | S | 44.54 | 17.40 | 66.20 | 35.90 | 35.10 | 12.50 | 25.30 | 27.10 | 3.50 | 3.50 | 3.20 | 6.10 | 25.20 | 11.00 | 30.60 | 1.80 | 5.30 | 0.70 | 20.50 | 8.40 | 8.90 |