PixelatedScatter: Arbitrary-level Visual Abstraction for Large-scale Multiclass Scatterplots

2025-11-26

AI Summary

To address feature loss in medium- and low-density regions of large-scale multi-class scatterplots caused by overplotting, this paper proposes a density-aware pixel-level abstraction method. The approach jointly preserves global structure and local discriminability across arbitrary abstraction levels through four core components: (1) equal-density region partitioning, (2) visual density equalization, (3) cross-class adaptive pixel allocation, and (4) pixel-based data distribution reconstruction. It is especially effective for ultra-high dynamic range data. Compared to state-of-the-art techniques, the method significantly improves feature fidelity in medium- and low-density regions. User studies and quantitative evaluations demonstrate superior feature retention performance in complex, multi-class distributions—outperforming mainstream approaches in both perceptual accuracy and analytical utility.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Computer Vision: Low Level & Physics-based Vision
• Data Mining & Knowledge Management: Data Visualization & Summarization

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Overdraw is inevitable in large-scale scatterplots. Current scatterplot abstraction methods lose features in medium-to-low density regions. We propose a visual abstraction method designed to provide better feature preservation across arbitrary abstraction levels for large-scale scatterplots, particularly in medium-to-low density regions. The method consists of three closely interconnected steps: first, we partition the scatterplot into iso-density regions and equalize visual density; then, we allocate pixels for different classes within each region; finally, we reconstruct the data distribution based on pixels. User studies, quantitative and qualitative evaluations demonstrate that, compared to previous methods, our approach better preserves features and exhibits a special advantage when handling ultra-high dynamic range data distributions.

Problem

• Addresses overdraw in large-scale scatterplots
• Preserves features in medium-to-low density regions
• Handles arbitrary abstraction levels for multiclass data

Innovation

• Partition scatterplot into iso-density regions
• Allocate pixels for classes within regions
• Reconstruct data distribution based on pixels