Research map / Point clouds / Shape and surface completion
SVDFormer: Complementing Point Cloud via Self-view Augmentation and Self-structure Dual-generator
Zhe Zhu, Honghua Chen, Xing He, Weiming Wang, Jing Qin, Mingqiang Wei
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 |
|---|---|---|---|
| use 3 depth-map views instead of 1 (ablation) | SVDFormer · PCN | F1-Score@1%: 0.835 -> 0.841 | Improved |
| use 6 views instead of 3 (ablation) | SVDFormer · PCN | CD x10^3: 6.54 -> 6.55 | No clear effect |
| random projection offsets at inference (ablation) | SVDFormer · PCN | CD x10^3: 6.54 -> 6.58 | No clear effect |
| use SVFNet self-view fusion encoder instead of SpareNet encoder (ablation) | SVDFormer · PCN | CD x10^3: 6.66 -> 6.54 | Improved |
| use ResNet-50 instead of ResNet18 as 2D backbone (ablation) | SVDFormer · PCN | CD x10^3: 6.54 -> 6.52 | Improved |
| use ViT-B/16 instead of ResNet18 as 2D backbone (ablation) | SVDFormer · PCN | DCD: 0.536 -> 0.543 | Hurt |
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.
- Seedformer — SeedFormer: Patch Seeds Based Point Cloud Completion with Upsample Transformer (ECCV 2022) · better on 2 of 2 shared results
- PMP-Net++ — PMP-Net: Point Cloud Completion by Learning Multi-Step Point Moving Paths (CVPR 2021) · better on 2 of 2 shared results
- SnowflakeNet — SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution With Skip-Transformer (ICCV 2021) · better on 2 of 2 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 2 of 2 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
- PointSea: Point Cloud Completion via Self-structure Augmentation (IJCV 2025 · similarity 0.84)
- Sonata: Self-Supervised Learning of Reliable Point Representations (CVPR 2025 · similarity 0.83)
- Learning Point Cloud Completion without Complete Point Clouds: A Pose-Aware Approach (ICCV 2023 · similarity 0.83)
- LPCG: A Self-conditional Architecture for Labeled Point Cloud Generation (AAAI 2025 · similarity 0.81)
- Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange (CVPR 2024 · similarity 0.81)
- Point Transformer V3: Simpler Faster Stronger (CVPR 2024 · similarity 0.81)
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.
