Point Cloud Compression and Objective Quality Assessment: A Survey
Not on the map. Why?
Abstract (arXiv)
The rapid growth of 3D point cloud data, driven by applications in autonomous driving, robotics, and immersive environments, has led to criticals demand for efficient compression and quality assessment techniques. Unlike traditional 2D media, point clouds present unique challenges due to their irregular structure, high data volume, and complex attributes. This paper provides a comprehensive survey of recent advances in point cloud compression (PCC) and point cloud quality assessment (PCQA), emphasizing their significance for real-time and perceptually relevant applications. We analyze a wide range of handcrafted and learning-based PCC algorithms, along with objective PCQA metrics. By benchmarking representative methods on emerging datasets, we offer detailed comparisons and practical insights into their strengths and limitations. Despite notable progress, challenges such as enhancing visual fidelity, reducing latency, and supporting multimodal data remain. This survey outlines future directions, including hybrid compression frameworks and advanced feature extraction strategies, to enable more efficient, immersive, and intelligent 3D applications.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 84 of its 209 references that are in the map. First posted on arXiv 28 Jun 2025.
Builds on
84 of 209 references.
References · 84
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
- 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
- 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
- 2018Variational image compression with a scale hyperpriorcited by 935
- 2016End-to-end Optimized Image Compressioncited by 696
- 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 664
- 2025Improving Video Generation with Human Feedbackcited by 284
- 2021Checkerboard Context Model for Efficient Learned Image Compressioncited by 202
- 2024GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generationcited by 153
- 2019Morphing and Sampling Network for Dense Point Cloud Completioncited by 132
38 more
- 2020Multiscale Point Cloud Geometry Compressioncited by 74
- 2020OctSqueeze: Octree-Structured Entropy Model for LiDAR Compressioncited by 73
- 2021Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compressioncited by 70
- 2021VoxelContext-Net: An Octree based Framework for Point Cloud Compressioncited by 61
- 2019Learned Point Cloud Geometry Compressioncited by 58
- 2020Inferring Point Cloud Quality via Graph Similaritycited by 58
- 2022OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compressioncited by 58
- 2023T3Bench: Benchmarking Current Progress in Text-to-3D Generationcited by 57
- 2024DreamReward: Text-to-3D Generation with Human Preferencecited by 56
- 2019Learning Convolutional Transforms for Lossy Point Cloud Geometry Compressioncited by 54
- 2020Point Cloud Quality Assessment: Dataset Construction and Learning-based No-Reference Metriccited by 53
- 2021No-Reference Quality Assessment for 3D Colored Point Cloud and Mesh Modelscited by 50
- 2021Perceptual Quality Assessment of Colored 3D Point Cloudscited by 49
- 2020Improved Deep Point Cloud Geometry Compressioncited by 43
- 2022MM-PCQA: Multi-Modal Learning for No-reference Point Cloud Quality Assessmentcited by 39
- 2021No-Reference Point Cloud Quality Assessment via Domain Adaptationcited by 38
- 2023Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generationcited by 32
- 2019Deep AutoEncoder-based Lossy Geometry Compression for Point Cloudscited by 29
- 2021MPED: Quantifying Point Cloud Distortion based on Multiscale Potential Energy Discrepancycited by 28
- 2024A Comprehensive Survey on 3D Content Generationcited by 28
- 2025DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimizationcited by 27
- 2022Sparse Tensor-based Point Cloud Attribute Compressioncited by 25
- 2023Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Modelcited by 25
- 2022A No-reference Quality Assessment Metric for Point Cloud Based on Captured Video Sequencescited by 24
- 2020DPDist : Comparing Point Clouds Using Deep Point Cloud Distancecited by 22
- 2022Evaluating Point Cloud from Moving Camera Videos: A No-Reference Metriccited by 22
- 2022GPA-Net:No-Reference Point Cloud Quality Assessment with Multi-task Graph Convolutional Networkcited by 22
- 2022Inter-Frame Compression for Dynamic Point Cloud Geometry Codingcited by 21
- 2023GMS-3DQA: Projection-based Grid Mini-patch Sampling for 3D Model Quality Assessmentcited by 21
- 2023BASICS: Broad quality Assessment of Static point clouds In Compression Scenarioscited by 20
- 2024LMM-PCQA: Assisting Point Cloud Quality Assessment with LMMcited by 19
- 2022D-DPCC: Deep Dynamic Point Cloud Compression via 3D Motion Predictioncited by 18
- 2022GRASP-Net: Geometric Residual Analysis and Synthesis for Point Cloud Compressioncited by 17
- 2020A generalized Hausdorff distance based quality metric for point cloud geometrycited by 15
- 2020Real-Time Spatio-Temporal LiDAR Point Cloud Compressioncited by 15
- 2021Patch-Based Deep Autoencoder for Point Cloud Geometry Compressioncited by 15
- 2024Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessmentcited by 14
- 2017Attribute Compression of 3D Point Clouds Using Laplacian Sparsity Optimized Graph Transformcited by 12
50 most cited of 84 All 84 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.