Research map / Point clouds / Shape and surface completion
AdaPoinTr: Diverse Point Cloud Completion With Adaptive Geometry-Aware Transformers
Xumin Yu, Yongming Rao, Ziyi Wang, Jiwen Lu, Jie Zhou
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 query generator between encoder and decoder (ablation) | vanilla Transformer completion model · PCN | CD-l1: 9.43 -> 9.09 | Improved |
| add DGCNN feature extractor for point proxies (ablation) | Transformer with query generator · PCN | CD-l1: 9.09 -> 8.69 | Improved |
| add geometric block to all Transformer blocks (ablation) | Transformer with DGCNN · PCN | CD-l1: 8.69 -> 8.44 | Improved |
| add geometric block to only the first block of encoder and decoder instead of all (ablation) | PoinTr · PCN | CD-l1: 8.44 -> 8.38 | Improved |
| add adaptive query generation (ablation) | PoinTr · PCN | CD-l1: 8.38 -> 7.06 | Improved |
| add dynamic query selection (ablation) | PoinTr with adaptive queries · PCN | CD-l1: 7.06 -> 6.92 | Improved |
| add auxiliary denoising task (ablation) | AdaPoinTr · PCN | CD-l1: 6.92 -> 6.53 | Improved |
| add adaptive queries, selection and denoising to PoinTr | PoinTr · ShapeNet-55 | CD-l2 avg (x1000): 1.09 -> 0.81 | Improved |
| add adaptive queries, selection and denoising to PoinTr | PoinTr · ShapeNet-34 (unseen 21 categories) | CD-l2 avg (x1000): 2.05 -> 1.23 | Improved |
| add adaptive queries, selection and denoising to PoinTr | PoinTr · Projected-ShapeNet-55 | CD-l1 (x1000): 10.68 -> 9.58 | Improved |
| add adaptive components to PoinTr | PoinTr · MVP validation (2048 points) | CD-l2 (x10000): 6.15 -> 4.71 | Improved |
| use PoinTr (depth only) geometry-enhanced Sketch-GE vs Sketch | Sketch · NYUCAD semantic scene completion | mIoU: 55.2 -> 56.1 | No clear effect |
Later papers that compared with this method
16 later accepted papers report AdaPoinTr as a baseline in their results tables; 12 of them report a better number on most of the results they share with it.
- PQDT: Pseudo-Query Dual Transformer for Robust Point Cloud Restoration (CVPR 2026 · better on 8 of 9 shared results)
- Hyper-PCN: Hypergraph-Based Point Cloud Completion via High-Order Correlation Modeling (CVPR 2026 · better on 7 of 7 shared results)
- SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion (ICML 2026 · better on 4 of 4 shared results)
- Simba: Towards High-Fidelity and Geometrically-Consistent Point Cloud Completion via Transformation Diffusion (AAAI 2026 · better on 3 of 4 shared results)
- Semantic Guided Part Relation-aware Network for Point Cloud Completion (AAAI 2026 · better on 3 of 3 shared results)
- PointCFormer: A Relation-Based Progressive Feature Extraction Network for Point Cloud Completion (AAAI 2025 · better on 6 of 8 shared results)
- PointSea: Point Cloud Completion via Self-structure Augmentation (IJCV 2025 · better on 5 of 5 shared results)
- DC-PCN: Point Cloud Completion Network with Dual-Codebook Guided Quantization (AAAI 2025 · better on 3 of 3 shared results)
8 more not listed.
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 on most shared results.
- PoinTr — PoinTr: Diverse Point Cloud Completion With Geometry-Aware Transformers (ICCV 2021) · better on 9 of 9 shared results
- SeedFormer — SeedFormer: Patch Seeds Based Point Cloud Completion with Upsample Transformer (ECCV 2022) · better on 5 of 5 shared results
- SnowflakeNet — SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution With Skip-Transformer (ICCV 2021) · better on 3 of 3 shared results
- GRNet — GRNet: Gridding Residual Network for Dense Point Cloud Completion (ECCV 2020) · better on 2 of 2 shared results
- FoldingNet — FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation (CVPR 2018) · better on 1 of 1 shared result
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
- PoinTr: Diverse Point Cloud Completion With Geometry-Aware Transformers (ICCV 2021 · similarity 0.97)
- PointCFormer: A Relation-Based Progressive Feature Extraction Network for Point Cloud Completion (AAAI 2025 · similarity 0.90)
- SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance (AAAI 2025 · similarity 0.90)
- DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion (AAAI 2025 · similarity 0.90)
- Point-based Instance Completion with Scene Constraints (ICLR 2025 · similarity 0.90)
- Position-Aware Guided Point Cloud Completion with CLIP Model (AAAI 2025 · similarity 0.89)
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.
