Browse State-of-the-Art › Point Cloud Quality Assessment
Point Cloud Quality Assessment
20 papers with code · 3 benchmarks · 2 datasets archive 2025-07-28
Background
A large and dense collection of points in three-dimensional space, collected by sensors such as LiDAR, is known as a point cloud. Points in the point cloud consist of geometric properties, such as three-dimensional spatial coordinates (x, y, z), and other attributes like color, reflectance, opacity, etc., represented by feature vectors. Since point clouds can directly represent the 3D world, they are widely employed in various fields, such as photogrammetry, power monitoring, architectural surveying, digital manufacturing, autonomous driving, gaming, cultural heritage reservation, and more.
Significance
Interactive point clouds typically contain millions of colored points and may possess complex attributes. To address the substantial transmission bandwidth and storage space required by point clouds, esearchers have developed various point cloud compression (PCC) techniques. However, point cloud compression may introduce significant visual distortions. In addition, deformations and distortions frequently occur during the acquisition, processing, transmission, rendering, and interaction of point clouds, all of which degrade the visual quality of the point cloud, ultimately impacting the application’s user experience. Therefore, effective methods for quantifying the quality of compressed point clouds are needed. More generally, point cloud quality assessment (PCQA) is crucial for optimizing and evaluating point cloud processing algorithms, such as encoding, denoising, and super-resolution.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): WPC (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| WPC (5 rows) | COPP-Net | No-Reference Point Cloud Quality Assessment via Weighted Patch... | code | — | Compare |
| M-PCCD (1 row) | - | Joint Geometry and Color Projection-based Point Cloud Quality Metric | code | — | Compare |
| SJTU-PCQA (1 row) | MM-PCQA | MM-PCQA: Multi-Modal Learning for No-reference Point Cloud Quality... | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
2 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 40 · with a code link: 20 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran: none of the 40 tagged papers has a Syntology run on record
Page 1 of 1: papers 1 to 40 of 40, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
13 Jul 2024 2 repositories listedRecent years have witnessed the success of the deep learning-based technique in research of no-reference point cloud quality assessment (NR-PCQA).
-
5 Jul 2021 2 repositories listedTherefore, many related studies such as point cloud quality assessment (PCQA) and mesh quality assessment (MQA) have been carried out to measure the visual quality degradations of 3D models.
-
17 Feb 2025 1 repository listedThen, the GQANet is designed to capture intrinsic multi-scale patch-wise geometric features in order to predict a quality index for each point cloud.
-
17 Feb 2025 1 repository listedInspired by the "wooden barrel theory", given the default content-independent viewpoints of existing projection-related PCQA approaches, this paper presents a novel content-aware viewpoint generation network (CAVGN) to…
-
17 Jan 2025 1 repository listedIn recent years, No-Reference Point Cloud Quality Assessment (NR-PCQA) research has achieved significant progress.
-
12 Nov 2024 1 repository listedFinally, reasoning on the constructed graph is performed by GCN to characterize the mutual dependencies and interactions between different projected images, and aggregate feature information of multi-view projected…
-
9 Oct 2024 1 repository listedIn addition, this work establishes a database named WPC6.
-
4 Jul 2024 1 repository listedTo bridge the gap, in this paper, we propose a perception-guided hybrid metric (PHM) that adaptively leverages two visual strategies with respect to distortion degree to predict point cloud quality: to measure visible…
-
15 Jun 2024 1 repository listedThus, establishing reliable point cloud quality assessment (PCQA) methods is essential as a benchmark to develop efficient compression methods.
-
28 Apr 2024 1 repository listedAlthough large multi-modality models (LMMs) have seen extensive exploration and application in various quality assessment studies, their integration into Point Cloud Quality Assessment (PCQA) remains unexplored.
-
10 Dec 2023 1 repository listedDeep learning-based quality assessments have significantly enhanced perceptual multimedia quality assessment, however it is still in the early stages for 3D visual data such as 3D point clouds (PCs).
-
9 Jun 2023 1 repository listedModel-based 3DQA methods extract features directly from the 3D models, which are characterized by their high degree of complexity.
-
13 May 2023 1 repository listedThen, we gather the features of all the patches of a point cloud for correlation analysis, to obtain the correlation weights.
-
10 Oct 2022 1 repository listedThe goal of objective point cloud quality assessment (PCQA) research is to develop quantitative metrics that measure point cloud quality in a perceptually consistent manner.
-
1 Sep 2022 1 repository listedIn specific, we split the point clouds into sub-models to represent local geometry distortions such as point shift and down-sampling.
-
30 Aug 2022 1 repository listedTo tackle the challenge of point cloud quality assessment (PCQA), many PCQA methods have been proposed to evaluate the visual quality levels of point clouds by assessing the rendered static 2D projections.
-
6 Dec 2021 1 repository listedWe present a novel no-reference quality assessment metric, the image transferred point cloud quality assessment (IT-PCQA), for 3D point clouds.
-
10 Nov 2021 1 repository listedIn this work, we first build a large 3D point cloud database for subjective and objective quality assessment of point clouds.
-
5 Aug 2021 1 repository listedMoreover, the proposed point cloud quality metric exploits the best performing 2D quality metrics in the literature to assess the quality of the projected images.
-
22 Dec 2020 1 repository listedFull-reference (FR) point cloud quality assessment (PCQA) has achieved impressive progress in recent years.
-
Point Cloud Compression and Objective Quality Assessment: A Survey28 Jun 2025 0 repositories listedThe 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.
-
DPCD: A Quality Assessment Database for Dynamic Point Clouds18 May 2025 0 repositories listedRecently, the advancements in Virtual/Augmented Reality (VR/AR) have driven the demand for Dynamic Point Clouds (DPC).
-
From Images to Point Clouds: An Efficient Solution for Cross-media Blind Quality Assessment without Annotated Training23 Jan 2025 0 repositories listedWe present a novel quality assessment method which can predict the perceptual quality of point clouds from new scenes without available annotations by leveraging the rich prior knowledge in images, called the…
-
Learning Disentangled Representations for Perceptual Point Cloud Quality Assessment via Mutual Information Minimization12 Nov 2024 0 repositories listedNo-Reference Point Cloud Quality Assessment (NR-PCQA) aims to objectively assess the human perceptual quality of point clouds without relying on pristine-quality point clouds for reference.
-
Image-Guided Outdoor LiDAR Perception Quality Assessment for Autonomous Driving25 Jun 2024 0 repositories listedLiDAR is one of the most crucial sensors for autonomous vehicle perception.
-
Full-reference Point Cloud Quality Assessment Using Spectral Graph Wavelets14 Jun 2024 0 repositories listedPoint clouds in 3D applications frequently experience quality degradation during processing, e.g., scanning and compression.
-
Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment15 Mar 2024 0 repositories listedNo-reference point cloud quality assessment (NR-PCQA) aims to automatically evaluate the perceptual quality of distorted point clouds without available reference, which have achieved tremendous improvements due to the…
-
PAME: Self-Supervised Masked Autoencoder for No-Reference Point Cloud Quality Assessment15 Mar 2024 0 repositories listedNo-reference point cloud quality assessment (NR-PCQA) aims to automatically predict the perceptual quality of point clouds without reference, which has achieved remarkable performance due to the utilization of deep…
-
Stochasticity-aware No-Reference Point Cloud Quality Assessment17 Jan 2024 0 repositories listedThe evolution of point cloud processing algorithms necessitates an accurate assessment for their quality.
-
PointPCA+: Extending PointPCA objective quality assessment metric23 Nov 2023 0 repositories listedA computationally-simplified and descriptor-richer Point Cloud Quality Assessment (PCQA) metric, namely PointPCA+, is proposed in this paper, which is an extension of PointPCA.
-
Simple Baselines for Projection-based Full-reference and No-reference Point Cloud Quality Assessment26 Oct 2023 0 repositories listed
-
Once-Training-All-Fine: No-Reference Point Cloud Quality Assessment via Domain-relevance Degradation Description4 Jul 2023 0 repositories listed
-
Reduced Reference Quality Assessment for Point Cloud Compression3 Jan 2023 0 repositories listed
-
PCQA-GRAPHPOINT: Efficients Deep-Based Graph Metric For Point Cloud Quality Assessment4 Nov 2022 0 repositories listed
-
GPA-Net:No-Reference Point Cloud Quality Assessment with Multi-task Graph Convolutional Network29 Oct 2022 0 repositories listed
-
Point Cloud Quality Assessment using 3D Saliency Maps30 Sep 2022 0 repositories listed
-
A No-reference Quality Assessment Metric for Point Cloud Based on Captured Video Sequences9 Jun 2022 0 repositories listed
-
Quantifying point cloud realism through adversarially learned latent representations24 Sep 2021 0 repositories listed
-
Which One is Better: Assessing Objective Metrics for Point Cloud Compression15 Sep 2021 0 repositories listed
-
Subjective Quality Database and Objective Study of Compressed Point Clouds With 6DoF Head-Mounted Display6 Aug 2020 0 repositories listed
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections