Research map / Detection and segmentation / 3D detection and driving
Boxer: Robust Lifting of Open-World 2D Bounding Boxes to 3D
Daniel DeTone, Tianwei Shen, Fan Zhang, Lingni Ma, Julian Straub, Richard Newcombe, Jakob Engel
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 depth (sparse point cloud) input (ablation) | BoxerNet · NymeriaPlus GT2D | mAP: 0.279 -> 0.518 | Improved |
| add depth input (ablation) | BoxerNet · CA-1M GT2D | mAP: 0.126 -> 0.412 | Improved |
| add aleatoric uncertainty head (ablation) | BoxerNet · NymeriaPlus GT2D | mAP: 0.485 -> 0.518 | Improved |
| add aleatoric uncertainty head (ablation) | BoxerNet · CA-1M GT2D | mAP: 0.401 -> 0.412 | Improved |
| add data augmentation (ablation) | BoxerNet · NymeriaPlus GT2D | mAP: 0.497 -> 0.518 | Improved |
| add data augmentation (ablation) | BoxerNet · CA-1M GT2D | mAP: 0.400 -> 0.412 | Improved |
| use full 960x960 instead of 480x480 resolution (ablation) | BoxerNet · NymeriaPlus GT2D | mAP: 0.466 -> 0.518 | Improved |
| add internal training data to public data (ablation) | BoxerNet · NymeriaPlus GT2D | mAP: 0.463 -> 0.518 | Improved |
| add internal training data to public data (ablation) | BoxerNet · CA-1M GT2D | mAP: 0.376 -> 0.412 | Improved |
| train on multiple datasets instead of only CA-1M (ablation) | BoxerNet · NymeriaPlus GT2D | mAP: 0.002 -> 0.518 | Improved |
| replace CuTR with BoxerNet (GT2D, RGB+D) | lifting model · CA-1M per-frame | mAP: 0.250 -> 0.412 | Improved |
| replace CuTR with BoxerNet (GT2D, RGB only) | lifting model · NymeriaPlus per-frame | mAP: 0.010 -> 0.296 | Improved |
Closest papers by meaning
- 3D Bounding Box Estimation Using Deep Learning and Geometry (CVPR 2017 · similarity 0.88)
- LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight (CVPR 2026 · similarity 0.88)
- ImageNet3D: Towards General-Purpose Object-Level 3D Understanding (NeurIPS 2024 · similarity 0.87)
- ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images (NeurIPS 2024 · similarity 0.86)
- OpenBox: Annotate Any Bounding Boxes in 3D (NeurIPS 2025 · similarity 0.86)
- RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection (NeurIPS 2026 · similarity 0.86)
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.
