Research map / Detection and segmentation / 3D detection and driving
DetAny4D: Detect Anything 4D Temporally in a Streaming RGB Video
Jiawei Hou, Shenghao Zhang, Can Wang, Zheng Gu, Yonggen Ling, Taiping Zeng, Xiangyang Xue, Jingbo Zhang
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 and camera heads (multi-task) (ablation) | DetAny4D · DA4D (10% train) | Var_v: 0.91 -> 0.60 | Improved |
| add depth and camera heads (multi-task) (ablation) | DetAny4D · DA4D (10% train) | AP3D: 26.88 -> 27.15 | Improved |
| add pose head and consistency loss (ablation) | DetAny4D · DA4D (10% train) | Var_v: 0.59 -> 0.54 | Improved |
| add soft dimension loss (ablation) | DetAny4D · DA4D (10% train) | AP3D: 26.78 -> 26.84 | No clear effect |
| add vertices chamfer loss (ablation) | DetAny4D · DA4D (10% train) | AP3D: 26.84 -> 26.88 | No clear effect |
| end-to-end 4D model vs single-frame DetAny3D | DetAny4D · DA4D full | Var_v: 0.99 -> 0.70 | Improved |
| end-to-end 4D model vs single-frame DetAny3D | DetAny4D · DA4D full | AP3D: 27.16 -> 27.48 | Improved |
| DetAny4D vs DetAny3D | DetAny4D · MP3D | AP3D: 25.14 -> 24.98 | Hurt |
| DetAny4D vs DetAny3D | DetAny4D · HM3D | AP3D: 26.80 -> 26.79 | No clear effect |
| end-to-end RGB sequence vs multi-stage ConceptGraph* | DetAny4D · DA4D | F1@IoU0.5: 41.9 -> 45.5 | Improved |
| end-to-end RGB sequence vs pre-scanned point cloud SpatialLM | DetAny4D · DA4D | F1@IoU0.5: 12.8 -> 45.5 | Improved |
Closest papers by meaning
- Detect Anything 3D in the Wild (ICCV 2025 · similarity 0.89)
- Real-time Stereo-based 3D Object Detection for Streaming Perception (NeurIPS 2024 · similarity 0.87)
- Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding (NeurIPS 2025 · similarity 0.87)
- Uni$^2$Det: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D Detection (ICLR 2025 · similarity 0.86)
- IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer (NeurIPS 2026 · similarity 0.86)
- Cubify Anything: Scaling Indoor 3D Object Detection (CVPR 2025 · 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.
