Research map / Point clouds / Shape and surface completion
VAPCNet: Viewpoint-Aware 3D Point Cloud Completion
Zhiheng Fu, Longguang Wang, Lian Xu, Zhiyong Wang, Hamid Laga, Yulan Guo, Farid Boussaid, Mohammed Bennamoun
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 viewpoint-aware (VA) module with both kernel and modulated self-attention, replacing MLPs (ablation) | VAPCNet · MVP (2048 points) | Chamfer distance L2 x10^4: 7.12 -> 5.40 | Improved |
| add convolutional kernel from viewpoint representation to VA module (ablation) | VAPCNet · MVP (2048 points) | Chamfer distance L2 x10^4: 7.12 -> 5.53 | Improved |
| add modulated self-attention to VA module (ablation) | VAPCNet · MVP (2048 points) | Chamfer distance L2 x10^4: 7.12 -> 5.54 | Improved |
| combine kernel and modulated self-attention versus either alone (ablation) | VAPCNet · MVP (2048 points) | Chamfer distance L2 x10^4: 5.53 -> 5.40 | Improved |
| use unsupervised learned viewpoint representation instead of ground-truth viewpoint input | VAPCNet vs Zhang et al. · MVP (16384 points) | Chamfer distance L2 x10^4: 2.42 -> 2.40 | Improved |
| apply VAPCNet to PCN dataset versus SnowflakeNet | VAPCNet · PCN | L1 Chamfer distance x10^3: 7.21 -> 7.02 | Improved |
| VAPCNet versus SnowflakeNet on cabinet and car categories | VAPCNet · PCN cabinet/car | L1 Chamfer distance x10^3: cabinet 9.16 -> 9.28; car 8.08 -> 8.15 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- SnowflakeNet — SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution With Skip-Transformer (ICCV 2021) · better on 4 of 4 shared results
- PoinTr — PoinTr: Diverse Point Cloud Completion With Geometry-Aware Transformers (ICCV 2021) · better on 2 of 2 shared results
- GRNet — GRNet: Gridding Residual Network for Dense Point Cloud Completion (ECCV 2020) · 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
- View-Guided Point Cloud Completion (CVPR 2021 · similarity 0.89)
- DANCE: Density-agnostic and Class-aware Network for Point Cloud Completion (AAAI 2026 · similarity 0.89)
- Position-Aware Guided Point Cloud Completion with CLIP Model (AAAI 2025 · similarity 0.89)
- DC-PCN: Point Cloud Completion Network with Dual-Codebook Guided Quantization (AAAI 2025 · similarity 0.88)
- AEDNet: Adaptive Embedding and Multiview-Aware Disentanglement for Point Cloud Completion (ECCV 2024 · similarity 0.88)
- GenPC: Zero-shot Point Cloud Completion via 3D Generative Priors (CVPR 2025 · 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.
