Research map / 3D vision / Depth and stereo
Footprints and Free Space From a Single Color Image
Jamie Watson, Michael Firman, Aron Monszpart, Gabriel J. Brostow
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| predict hidden traversable surfaces and object footprints from one image | Footprints · KITTI | footprint IoU: 0.231 -> 0.239 | Improved |
| predict hidden traversable surfaces and object footprints from one image | Footprints · Matterport | freespace IoU: 0.505 -> 0.652 | Improved |
| predict hidden traversable surfaces and object footprints from one image | Footprints · Matterport | footprint IoU: 0.404 -> 0.426 | Improved |
| add moving-object masks during training (ablation) | Footprints · KITTI | footprint IoU: 0.227 -> 0.239 | Improved |
| add moving-object masks during training (ablation) | Footprints · KITTI | freespace IoU: 0.795 -> 0.797 | No clear effect |
| retain equation (3b) (ablation) | Footprints · KITTI | footprint IoU: 0.225 -> 0.239 | Improved |
| retain equation (3b) in the prior variant (ablation) | Footprints without moving object masks · KITTI | footprint IoU: 0.218 -> 0.227 | Improved |
| set lambda to 0 rather than the default (ablation) | Footprints · KITTI | freespace IoU: 0.797 -> 0.355 | Hurt |
| set lambda to 0.5 rather than the default (ablation) | Footprints · KITTI | footprint IoU: 0.239 -> 0.232 | No clear effect |
| set lambda to 1.0 rather than the default (ablation) | Footprints · KITTI | footprint IoU: 0.239 -> 0.234 | No clear effect |
| set lambda to 0.5 rather than the default (ablation) | Footprints · Matterport | footprint IoU: 0.426 -> 0.452 | Improved |
Closest papers by meaning
- Depth Prediction without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos (AAAI 2019 · similarity 0.87)
- Hidden Footprints: Learning Contextual Walkability from 3D Human Trails (ECCV 2020 · similarity 0.87)
- Learning Spatial Common Sense With Geometry-Aware Recurrent Networks (CVPR 2019 · similarity 0.87)
- RevealNet: Seeing Behind Objects in RGB-D Scans (CVPR 2020 · similarity 0.86)
- Discovering Objects That Can Move (CVPR 2022 · similarity 0.86)
- Large Spatial Model: End-to-end Unposed Images to Semantic 3D (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
