Research map / Point clouds / Point cloud classification
Density-Preserving Deep Point Cloud Compression
Check 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 dynamic upsampling factor (ablation) | Point cloud compression autoencoder · SemanticKITTI, 2.1 Bpp | CD ($10^{-2}$): 2.61 -> 2.29 | Helped |
| Add local position embedding (ablation) | Point cloud compression autoencoder · SemanticKITTI, 2.1 Bpp | CD ($10^{-2}$): 2.29 -> 1.67 | Helped |
| Add density embedding (ablation) | Point cloud compression autoencoder · SemanticKITTI, 2.1 Bpp | CD ($10^{-2}$): 1.67 -> 1.32 | Helped |
| Add adaptive-scale upsampling block (ablation) | Point cloud compression autoencoder · SemanticKITTI, 2.1 Bpp | CD ($10^{-2}$): 1.32 -> 0.98 | Helped |
| Add sub-point convolution (ablation) | Point cloud compression autoencoder · SemanticKITTI, 2.1 Bpp | CD ($10^{-2}$): 0.98 -> 0.45 | Helped |
| Add upsampling refinement layer (ablation) | Point cloud compression autoencoder · SemanticKITTI, 2.1 Bpp | CD ($10^{-2}$): 0.45 -> 0.36 | Helped |
| Replace FPS with random downsampling (ablation) | Density-preserving point cloud compression · SemanticKITTI, 2.1 Bpp | CD ($10^{-2}$): 0.36 -> 1.29 | Hurt |
| Replace FPS with grid downsampling (ablation) | Density-preserving point cloud compression · SemanticKITTI, 2.1 Bpp | CD ($10^{-2}$): 0.36 -> 0.62 | Hurt |
| Remove cardinality loss (ablation) | Density-preserving point cloud compression · SemanticKITTI, 2.1 Bpp | CD ($10^{-2}$): 0.36 -> 0.47 | Hurt |
| Remove density loss (ablation) | Density-preserving point cloud compression · SemanticKITTI, 2.1 Bpp | DM: 1.98 -> 3.59 | Hurt |
| Replace the proposed decoder with Yu et al.'s decoder (ablation) | Density-preserving encoder and decoder · SemanticKITTI, 2.1 Bpp | CD ($10^{-2}$): 0.36 -> 1.25 | Hurt |
| Replace the proposed decoder with Wang et al.'s decoder (ablation) | Density-preserving encoder and decoder · SemanticKITTI, 2.1 Bpp | CD ($10^{-2}$): 0.36 -> 1.03 | Hurt |
Closest papers by meaning
- SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Network (AAAI 2025 · similarity 0.88)
- patchDPCC: A Patchwise Deep Compression Framework for Dynamic Point Clouds (AAAI 2024 · similarity 0.88)
- UniPCGC: Towards Practical Point Cloud Geometry Compression via an Efficient Unified Approach (AAAI 2025 · similarity 0.88)
- msLPCC: A Multimodal-Driven Scalable Framework for Deep LiDAR Point Cloud Compression (AAAI 2024 · similarity 0.88)
- A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM) (ICML 2024 · similarity 0.87)
- LinNet: Linear Network for Efficient Point Cloud Representation Learning (NeurIPS 2024 · 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.