Research map / Detection and segmentation / 3D detection and driving
Clouds of Oriented Gradients for 3D Detection of Objects, Surfaces, and Indoor Scene Layouts
Zhile Ren, Erik B. Sudderth
Read the paperCheck 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 |
|---|---|---|---|
| add COG features to geometric features (ablation) | 3D cuboid detector · SUN RGB-D, 5 large objects (bed) | AP: 45.0 -> 53.0 | Improved |
| add COG features to geometric features (ablation) | 3D cuboid detector · SUN RGB-D (chair) | AP: 36.2 -> 39.0 | Improved |
| add camera-view feature to Geom+COG (ablation) | 3D cuboid detector · SUN RGB-D, toilet | AP: 63.6 -> 57.8 | Hurt |
| add camera-view feature to Geom+COG (ablation) | 3D cuboid detector · SUN RGB-D, bathtub | AP: 49.8 -> 53.2 | Improved |
| add expanded cuboid feature (ablation) | 3D cuboid detector · SUN RGB-D, chair | AP: 40.4 -> 64.1 | Improved |
| add expanded cuboid feature (ablation) | 3D cuboid detector · SUN RGB-D, nightstand | AP: 16.8 -> 29.2 | Improved |
| add contextual cascade (object-to-object features) (ablation) | COG detector with surfaces · SUN RGB-D (19 categories) | mAP: 32.6 -> 36.3 | Improved |
| add object-to-scene-layout features (ablation) | COG detector with context · SUN RGB-D (19 categories) | mAP: 36.3 -> 36.6 | Improved |
| add contextual cascade (ablation) | COG detector with surfaces · SUN RGB-D (10 categories) | mAP: 49.4 -> 54.0 | Improved |
| use Manhattan voxels with structured learning instead of cubical voxels (ablation) | layout predictor · SUN RGB-D layout | free-space IOU: 72.33 -> 78.96 | Improved |
| add contextual cues from detected objects to layout (ablation) | layout predictor · SUN RGB-D layout | free-space IOU: 78.96 -> 80.03 | Improved |
| use linear SVM instead of RBF SVM in cascade (ablation) | cascaded classifier · SUN RGB-D | detection performance | No clear effect |
Closest papers by meaning
- Three-Dimensional Object Detection and Layout Prediction Using Clouds of Oriented Gradients (CVPR 2016 · similarity 0.97)
- 3D Object Detection With Latent Support Surfaces (CVPR 2018 · similarity 0.88)
- Cubify Anything: Scaling Indoor 3D Object Detection (CVPR 2025 · similarity 0.88)
- H^2A^2: Homogeneity-Aware and Heterogeneity-Aware Feature Perception for Unified Indoor 3D Object Detection (CVPR 2026 · similarity 0.88)
- Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping (NeurIPS 2025 · similarity 0.88)
- Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection (CVPR 2025 · similarity 0.87)
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.
