Research map / Detection and segmentation / 3D detection and driving
AShapeFormer: Semantics-Guided Object-Level Active Shape Encoding for 3D Object Detection via Transformers
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 AShapeFormer to VoteNet | VoteNet · SUN RGB-D validation | mAP@0.25: 57.7 -> 61.2 | Helped |
| Add AShapeFormer to imVoteNet | imVoteNet · SUN RGB-D validation | mAP@0.25: 63.4 -> 65.1 | Helped |
| Add AShapeFormer to VoteNet | VoteNet · ScanNet V2 validation | mAP@0.5: 33.5 -> 41.6 | Helped |
| Add AShapeFormer to GroupFree3D | GroupFree3D · ScanNet V2 validation | mAP@0.25: 69.1 -> 70.4 | Helped |
| Add naive shape encoding (ablation) | VoteNet · SUN RGB-D | mAP@0.25: 57.7 -> 58.9 | Helped |
| Add SGM to naive shape encoding (ablation) | VoteNet with naive shape encoding · SUN RGB-D | mAP@0.25: 58.9 -> 59.5 | Helped |
| Use ShapeFormer instead of naive shape encoding, without SGM (ablation) | VoteNet · SUN RGB-D | mAP@0.25: 58.9 -> 59.9 | Helped |
| Add SGM to ShapeFormer (ablation) | VoteNet with ShapeFormer · SUN RGB-D | mAP@0.25: 59.9 -> 61.2 | Helped |
Closest papers by meaning
- Straight to Shapes: Real-Time Detection of Encoded Shapes (CVPR 2017 · similarity 0.89)
- SEFormer: Structure Embedding Transformer for 3D Object Detection (AAAI 2023 · similarity 0.87)
- Point2Seq: Detecting 3D Objects As Sequences (CVPR 2022 · similarity 0.87)
- DOPS: Learning to Detect 3D Objects and Predict Their 3D Shapes (CVPR 2020 · similarity 0.87)
- Cubify Anything: Scaling Indoor 3D Object Detection (CVPR 2025 · similarity 0.86)
- ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images (NeurIPS 2024 · 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.