Research map / Detection and segmentation / 3D detection and driving
Lifting Object Detection Datasets into 3D
João Carreira, Sara Vicente, Lourdes Agapito, Jorge P. Batista
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 camera refinement (ablation) | full method · Synthetic VOC-like test set (mean) | symmetric RMS error: 8.01 -> 6.96 | Improved |
| add reference silhouette imprinting (ablation) | full method · Synthetic VOC-like test set (mean) | symmetric RMS error: 7.53 -> 6.96 | Improved |
| use full method instead of Puffball | Puffball · Synthetic VOC-like test set (mean) | symmetric RMS error: 9.57 -> 6.96 | Improved |
| use full method instead of rigid SfM convex hull | SFMc · Synthetic VOC-like test set (mean) | symmetric RMS error: 9.40 -> 6.96 | Improved |
| add camera refinement (ablation) | full method · Synthetic VOC-like test set, bicycle | symmetric RMS error: 3.26 -> 4.30 | Hurt |
| add camera refinement (ablation) | full method · Synthetic VOC-like test set, bus | symmetric RMS error: 6.10 -> 6.45 | Hurt |
| add camera refinement (ablation) | full method · Synthetic VOC-like test set, car | symmetric RMS error: 6.33 -> 3.04 | Improved |
| add camera refinement (ablation) | full method · Synthetic VOC-like test set, diningtable | symmetric RMS error: 12.57 -> 8.97 | Improved |
| add camera refinement (ablation) | full method · Synthetic VOC-like test set, train | symmetric RMS error: 20.55 -> 15.73 | Improved |
| add silhouette imprinting (ablation) | full method · Synthetic VOC-like test set, diningtable | symmetric RMS error: 14.30 -> 8.97 | Improved |
| use full method instead of Puffball | Puffball · Synthetic VOC-like test set, bottle | symmetric RMS error: 6.25 -> 8.09 | Hurt |
| use full method instead of Puffball | Puffball · Synthetic VOC-like test set, pottedplant | symmetric RMS error: 7.58 -> 7.72 | Hurt |
Closest papers by meaning
- Weakly-Supervised Learning of Category-Specific 3D Object Shapes (TPAMI 2019 · similarity 0.91)
- Learning Category-Specific Deformable 3D Models for Object Reconstruction (TPAMI 2016 · similarity 0.91)
- UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes (NeurIPS 2024 · similarity 0.88)
- Unsupervised 3D Structure Inference from Category-Specific Image Collections (CVPR 2024 · similarity 0.88)
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos (CVPR 2024 · similarity 0.87)
- ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images (NeurIPS 2024 · 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.
