Research map / Point clouds / Point cloud classification
Omni-scene Perception-oriented Point Cloud Geometry Enhancement for Coordinate Quantization
Wang Liu, Wei Gao
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 rooting step (ablation) | rooting-growing-pruning network · ModelNet40 r1 | CD (x1e-2): 7.64 -> 4.47 | Improved |
| add growing step (ablation) | rooting-growing-pruning network · ModelNet40 r1 | CD (x1e-2): 4.54 -> 4.47 | Improved |
| add pruning step (ablation) | rooting-growing-pruning network · ModelNet40 r1 | CD (x1e-2): 6.57 -> 4.47 | Improved |
| add rooting step (ablation) | rooting-growing-pruning network · ModelNet40 r1 | D1 PSNR (dB): 30.00 -> 36.86 | Improved |
| add rooting step (ablation) | rooting-growing-pruning network · 8iVFB redandblack r1 | delta D1 PSNR (dB): 8.07 -> 10.39 | Improved |
| add pruning step (ablation) | rooting-growing-pruning network · 8iVFB redandblack r1 | delta D1 PSNR (dB): 9.11 -> 10.39 | Improved |
| add pruning step (ablation) | rooting-growing-pruning network · 8iVFB redandblack r1 | delta D2 PSNR (dB): 9.44 -> 8.74 | Hurt |
| add quantization-step loss Lq (ablation) | rooting-growing-pruning network · ModelNet40 severe distortion | delta CD (x1e-2): 4.38 -> 4.49 | Improved |
| add quantization-step loss Lq (ablation) | rooting-growing-pruning network · ShapeNet severe distortion | delta CD (x1e-2): 3.85 -> 4.02 | Improved |
| add quantization-step loss Lq (ablation) | rooting-growing-pruning network · ScanObject severe distortion | delta CD (x1e-2): 3.49 -> 3.75 | Improved |
| add quantization-step loss Lq (ablation) | rooting-growing-pruning network · 8iVFB soldier severe distortion | delta CD (x1e-2): 4.59 -> 4.73 | Improved |
| enhance G-PCC point clouds before DGCNN classification | DGCNN · ModelNet40 r1 classification | accuracy (%): 9.44 -> 78.57 | Improved |
Closest papers by meaning
- Point Cloud Quality Assessment via Multi-View Structure-Aware Feature Fusion (AAAI 2026 · similarity 0.86)
- Learning Disentangled Representations for Perceptual Point Cloud Quality Assessment via Mutual Information Minimization (NeurIPS 2024 · similarity 0.85)
- Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment (CVPR 2024 · similarity 0.85)
- 3DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering (AAAI 2025 · similarity 0.83)
- Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer (NeurIPS 2026 · similarity 0.83)
- LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection (ICLR 2024 · similarity 0.83)
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.
