Research map / Detection and segmentation / 3D detection and driving
3D Object Detection With Latent Support Surfaces
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Add view-to-camera and scene layout features to COG (ablation) | 3D object detection on SUN RGB-D · SUN RGB-D test, 19 categories | mAP: 19.1 -> 21.9 | Helped |
| Add latent support surfaces to the +view model (ablation) | 3D object detection on SUN RGB-D · SUN RGB-D test, 19 categories | mAP: 21.9 -> 26.7 | Helped |
| Add cascaded contextual detection to the +surface model (ablation) | 3D object detection on SUN RGB-D · SUN RGB-D test, 19 categories | mAP: 26.7 -> 36.3 | Helped |
| Add view-to-camera and scene layout features to COG (ablation) | 3D object detection on SUN RGB-D · SUN RGB-D test, 10 categories | mAP: 29.68 -> 34.4 | Helped |
| Add latent support surfaces to the +view model (ablation) | 3D object detection on SUN RGB-D · SUN RGB-D test, 10 categories | mAP: 34.4 -> 38.7 | Helped |
| Add cascaded contextual detection to the +surface model (ablation) | 3D object detection on SUN RGB-D · SUN RGB-D test, 10 categories | mAP: 38.7 -> 51.0 | Helped |
| Add view-to-camera, scene layout, and support-surface features (ablation) | Whole System · SUN RGB-D test, 19 categories | mAP: 28.9 -> 36.3 | Helped |
| Add view-to-camera, scene layout, and support-surface features (ablation) | Whole System · SUN RGB-D test, 10 categories | mAP: 42.4 -> 51.0 | Helped |
| Use latent support surfaces to constrain small-object search to predicted supporting areas (ablation) | Small-object detection · SUN RGB-D test, Pillow | AP: 0.0 -> 60.9 | Helped |
| Use latent support surfaces to constrain small-object search to predicted supporting areas (ablation) | Small-object detection · SUN RGB-D test, Lamp | AP: 0.0 -> 9.6 | Helped |
| Use the full method rather than Ren et al. (2017) | 3D object detection · SUN RGB-D test, 10 categories | mAP: 47.6 -> 51.0 | Helped |
Closest papers by meaning
- Cubify Anything: Scaling Indoor 3D Object Detection (CVPR 2025 · similarity 0.87)
- UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes (NeurIPS 2024 · similarity 0.86)
- Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection (CVPR 2025 · similarity 0.86)
- Believing is Seeing: Unobserved Object Detection using Generative Models (CVPR 2025 · similarity 0.85)
- ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images (NeurIPS 2024 · similarity 0.85)
- Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping (NeurIPS 2025 · 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.