Research map / Detection and segmentation / Weakly supervised detection and segmentation
Diff3DETR: Agent-based Diffusion Model for Semi-supervised 3D Object Detection
Jiacheng Deng, Jiahao Lu, Tianzhu 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 agent-based object query generator (ablation) | Diff3DETR baseline · ScanNet 5% labeled | mAP@0.25: 42.2 -> 43.1 | Improved |
| add agent adaptor to the agent-based query generator (ablation) | Diff3DETR · ScanNet 5% labeled | mAP@0.25: 43.1 -> 43.5 | Improved |
| add box-aware denoising module (ablation) | Diff3DETR · ScanNet 5% labeled | mAP@0.25: 43.5 -> 44.3 | Improved |
| add 3D vertex relative position encoding (ablation) | Diff3DETR · ScanNet 5% labeled | mAP@0.25: 44.3 -> 44.6 | Improved |
| add DDIM iterative denoising (ablation) | Diff3DETR · ScanNet 5% labeled | mAP@0.25: 44.6 -> 45.1 | Improved |
| increase decoder layers from 3 to 9 (DDIM=2) (ablation) | Diff3DETR · ScanNet 5% labeled | mAP@0.25: 45.1 -> 46.3 | Improved |
| increase DDIM steps from 2 to 4 (DL=3) (ablation) | Diff3DETR · ScanNet 5% labeled | mAP@0.5: 29.2 -> 28.8 | No clear effect |
| increase decoder layers and DDIM steps beyond 3 and 2 (ablation) | Diff3DETR · ScanNet | training and inference speed | Hurt |
| use agent grid resolution 16x16x4 rather than other resolutions (ablation) | Diff3DETR · ScanNet | mAP | Improved |
| replace Diffusion-SS3D with Diff3DETR | Diffusion-SS3D · ScanNet 5% labeled | mAP@0.25: 43.5 -> 45.1 | Improved |
| replace NESIE with Diff3DETR at 20% labels | NESIE · SUN RGB-D 20% labeled | mAP@0.25: 53.4 -> 53.2 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Diffusion-SS3D — Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detection (NeurIPS 2023) · better on 7 of 7 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- DiffuBox: Refining 3D Object Detection with Point Diffusion (NeurIPS 2024 · similarity 0.89)
- Semi-supervised 3D Object Detection with PatchTeacher and PillarMix (AAAI 2024 · similarity 0.88)
- Leveraging Temporal Cues for Semi-Supervised Multi-View 3D Object Detection (CVPR 2025 · similarity 0.88)
- 3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features (CVPR 2024 · similarity 0.87)
- A-Teacher: Asymmetric Network for 3D Semi-Supervised Object Detection (CVPR 2024 · similarity 0.87)
- Dual-Perspective Knowledge Enrichment for Semi-supervised 3D Object Detection (AAAI 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.
