Skip to content

Latest commit

 

History

History
144 lines (115 loc) · 23.1 KB

README.md

File metadata and controls

144 lines (115 loc) · 23.1 KB

👉 3DQA Databases (update)

If you want to add PCQA papers and codes to this list, feel free to start a pull request.

We are happy to see your contribution!

Overview of the databases

Database Format Attributes Rated Models
M-PCCD Point cloud Colored 232
IRPC Point cloud Colorless & Colored 54 & 54
WPC Point cloud Colored 740
WPC2.0 Point cloud Colored 400
WPC3.0 Point cloud Colored 350
ICIP2020 Point cloud Colored 96
SJTU-PCQA Point cloud Colored 378
SIAT-PCQD Point cloud Colored 340
LS-PCQA Point cloud Colored 1,080
BASICS Point cloud Colored 1,494
CMDM Mesh Colored 480
TMQA Mesh Textured 3,000
Geo-Metric Mesh Geometry Faces 2,450
DHHQA Mesh Textured human heads 1,540
DDH-QA FBX/MP4 Dynamic Digital Humans 800
SJTU-H3D Mesh Full-body Digital Humans 1,120

PCQA databases

# Database Name Title & Link Database Link
1 SJTU-PCQA Predicting the Perceptual Quality of Point Cloud: A 3D-to-2D Projection-Based Exploration Link
2 WPC Perceptual Quality Assessment of Colored 3D Point Clouds Link
3 LS-PCQA Point Cloud Quality Assessment: Dataset Construction and Learning-based No-Reference Approach Link
4 WPC2.0(Compression) Reduced Reference Perceptual Quality Model with Application to Rate Control for Video-based Point Cloud Compression Link
5 WPC3.0(Compression) No-reference Bitstream-layer Model for Perceptual Quality Assessment of V-PCC Encoded Point Clouds Link
6 CPCD2.0(Compression & Noise) TGP-PCQA: Texture and geometry projection based quality assessment for colored point clouds Link
7 ICIP2020 Quality Evaluation Of Static Point Clouds Encoded Using MPEG Codecs
8 M-PCCD A comprehensive study of the rate-distortion performance in MPEG point cloud compression
9 IRPC Point Cloud Rendering after Coding : Impacts on Subjective and Objective Quality.
10 SIAT-PCQD Subjective Quality Database and Objective Study of Compressed Point Clouds With 6DoF Head-Mounted Display Link
11 vsenseVVDB (Volumetric Video Quality Database #1) Subjective and Objective Quality Assessment for Volumetric Video Compression Link
12 vsenseVVDB2 (Volumetric Video Quality Database #2) Textured mesh vs coloured point cloud: A subjective study for volumetric video compression Link
13 BASICS BASICS: Broad quality Assessment of Static point clouds In Compression Scenarios

MQA (mesh quality assessment) database

# Database Name Title & Link Database Link
1 CMDM Visual Quality of 3D Meshes With Diffuse Colors in Virtual Reality: Subjective and Objective Evaluation Link
2 TMQA Textured Mesh Quality Assessment: Large-Scale Dataset and Deep Learning-based Quality Metric Link
3 - Geo-Metric: A Perceptual Dataset of Distortions on Faces link
4 SJTU-TMQA SJTU-TMQA: A quality assessment database for static mesh with texture map link

Digital human quality assessment database

# Database Name Title & Link Database Link
1 DHHQA Perceptual Quality Assessment for Digital Human Heads Link
2 DDH-QA DDH-QA: A DYNAMIC DIGITAL HUMANS QUALITY ASSESSMENT DATABASE Link
3 SJTU-H3D Advancing Zero-Shot Digital Human Quality Assessment through Text-Prompted Evaluation Link

👉 3DQA methods

Basic FR-PCQA

Basic full-reference quality assessment metrics implemented by Python.

I try to implement the p2point, p2plane, and PSNR_yuv with python. The original algorithms come from "Evaluation criteria for PCC (Point Cloud Compression)","Dynamic Polygon Clouds: Representation and Compression for VR/AR", and "Geometric Distortion Metrics for Point Cloud Compression".

FR-PCQA metrics

# Metric Name Title & Link Code Link
1 PointSSIM "Towards a Point Cloud Structural Similarity Metric" Code
2 GraphSIM "Inferring Point Cloud Quality via Graph Similarity" Code
3 PCQM "PCQM: A Full-Reference Quality Metric for Colored 3D Point Clouds" Code

RR-PCQA metrics

# Metric Name Title & Link Code Link
1 PCMrr "A Reduced Reference Metric for Visual Quality Evaluation of Point Cloud Contents" Code
2 - "Reduced Reference Quality Assessment for Point Cloud Compression" -
3 - "Reduced-Reference Quality Assessment of Point Clouds via Content-Oriented Saliency Projection" Code
4 - "Support Vector Regression-based Reduced-Reference Perceptual Quality Model for Compressed Point Clouds"

NR-PCQA metrics

# Metric Name Title & Link Code Link
1 3D-NSS "No-Reference Quality Assessment for 3D Colored Point Cloud and Mesh Models" [Arxiv] Code
2 ResSCNN "Point Cloud Quality Assessment: Dataset Construction and Learning-based No-Reference Approach" Code
3 IT-PCQA "No-Reference Point Cloud Quality Assessment via Domain Adaptation" Code
4 3D-CNN-PCQA "A No-reference Quality Assessment Metric for Point Cloud Based on Captured Video Sequences" -
5 VQA-PC "Evaluating Point Cloud from Moving Camera Videos: A No-Reference Metric" Code
6 - "Blind Quality Assessment of 3D Dense Point Clouds with Structure Guided Resampling" -
7 MM-PCQA "MM-PCQA: Multi-Modal Learning for No-reference Point Cloud Quality Assessment" Code
8 - "V-PCC Projection Based Blind Point Cloud Quality Assessment for Compression Distortion" -
9 - "GPA-Net: No-Reference Point Cloud Quality Assessment with Multi-task Graph Convolutional Network" Code
10 - "PQA-Net: Deep No Reference Point Cloud Quality Assessment via Multi-View Projection" Code
11 - "Progressive Knowledge Transfer Based on Human Visual Perception Mechanism for Perceptual Quality Assessment of Point Clouds" -
12 - "Bitstream-based Perceptual Quality Assessment of Compressed 3D Point Clouds" -
13 - "GMS-3DQA: Projection-based Grid Mini-patch Sampling for 3D Model Quality Assessment" Code
14 - "Once-Training-All-Fine: No-Reference Point Cloud Quality Assessment via Domain-relevance Degradation Description" -
15 - "Pseudo-Reference Point Cloud Quality Measurement Based on Joint 2-D and 3-D Distortion Description" -
16 - "pmBQA: Projection-based Blind Point Cloud Quality Assessment via Multimodal Learning" -
17 - "Non-Local Geometry and Color Gradient Aggregation Graph Model for No-Reference Point Cloud Quality Assessment" -
18 - "Simple Baselines for Projection-based Full-reference and No-reference Point Cloud Quality Assessment" -
19 - "Plain-PCQA: No-Reference Point Cloud Quality Assessment by Analysis of Plain Visual and Geometrical Components" -
20 - "Zoom to Perceive Better: No-reference Point Cloud Quality Assessment via Exploring Effective Multiscale Feature" Code
21 - "PAME: SELF-SUPERVISED MASKED AUTOENCODER FOR NO-REFERENCE POINT CLOUD QUALITY ASSESSMENT" -
22 - "Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment" -
23 - "MFT-PCQA: Multi-Modal Fusion Transformer for No-Reference Point Cloud Quality Assessment" -
24 - "Rating-Augmented No-Reference Point Cloud Quality Assessment Using Multi-Task Learning" -
25 - "3DTA: No-Reference 3D Point Cloud Quality Assessment with Twin Attention" Code
26 - "Compressed Point Cloud Quality Index by Combining Global Appearance and Local Details" -
27 - "Asynchronous Feedback Network for Perceptual Point Cloud Quality Assessment" Code
28 - "TCDM: Transformational Complexity Based Distortion Metric for Perceptual Point Cloud Quality Assessment Code
29 ACM MM Best Paper Nomination "LMM-PCQA: Assisting Point Cloud Quality Assessment with LMM" Code
30 - "LLM-guided Cross-Modal Point Cloud Quality Assessment: A Graph Learning Approach" -
31 - "Visual-Saliency Guided Multi-modal Learning for No Reference Point Cloud Quality Assessment" -
32 - "Perceptual Quality Assessment of Trisoup-Lifting Encoded 3D Point Clouds" -
33 - "No-Reference Point Cloud Quality Assessment Through Structure Sampling and Clustering Based on Graph" -
34 - "No-reference point cloud quality assessment via graph convolutional network" -
35 - "CLIP-PCQA: Exploring Subjective-Aligned Vision-Language Modeling for Point Cloud Quality Assessment" -
36 - "Information Exploration of Projected Views for Point Cloud Quality Measurement" -
37 - "CMDC-PCQA: No-Reference Point Cloud Quality Assessment via a Cross-Modal Deep-Coupling Framework" -
38 - "No-reference geometry quality assessment for colorless point clouds via list-wise rank learning" -

Mesh QA metrics

  1. "Surface-Sampling Based Objective Quality Assessment Metrics for Meshes" [ICASSP]

Contact Information

😎 If you want to make contributions, include your works, or simply make discussions, feel free to e-mail me at zzc1998@sjtu.edu.cn 😎

💖 If you find this collection helpful, please star this project! Thank you! 💖