Layered Image Vectorization via Semantic Simplification

Zhenyu Wang, Jianxi Huang, Zhida Sun, Yuanhao Gong, Daniel Cohen-Or, and and Min Lu*

CVPR Conference on Computer Vision and Pattern Recognition, 2025.
[Paper (41.8 MB)] [Project Homepage]

We present a layered image vectorization technique with image simplification, that reconstructs the raster image as layer-wise vectors from semantic-aligned macro structures to finer details.

A Versatile Collage Visualization Technique

Zhenyu Wang and Min Lu*

Arxiv 2025
[Paper (4.6 MB)] [Project Homepage]

We introduce a versatile image-space collage technique designed to pack geometric elements into a given shape, and demonstrate its diverse visual expressiveness in various applications.

Creative Blends of Visual Concepts

Zhida Sun, Zhenyao Zhang, Yue Zhang, Min Lu*, Dani Lischinski, Daniel Cohen-Or, and Hui Huang

CHI Proceedings of the 2025 CHI conference on human factors in computing systems, 2025.
[Paper (25.3 MB)]

We Creative Blends, an AI-assisted design system that leverages metaphors to visually symbolize abstract concepts by blending elements from two distinct visual concepts into a single

Sticky Links: Encoding Quantitative Data of Graph Edges

Min Lu*, Xiangfang Zeng, Joel Lanir, Xiaoqin Sun, Guozheng Li, Daniel Cohen-Or, and Hui Huang

PacificVisTVCGIEEE Transactions on Visualization and Computer Graphics, 2024.
[Paper (0.4 MB)] [Source Code (Python)] [My Talk at PacificVis 2024 (32.4 MB)]

In this work we propose a new edge drawing for node-link diagram, Sticky Links. Using the metaphor of stickiness, sticky links can be used for expressive edge quantatitive encoding.

Enhancing Static Charts with Data-driven Animations

Min Lu*, Noa Fish, Shuaiqi Wang, Joel Lanir, Daniel Cohen-Or and Hui Huang

TVCGIEEE Transactions on Visualization and Computer Graphics, 2022.
[Paper (1.82 MB)] [Project Homepage ] [Source Code (Javascript)]

In this work we propose data-driven animation to bring static charts to life, with the purpose of encoding and emphasizing certain attributes of data, specifically of non-temporal data.

Modeling Just Noticeable Differences in Charts

Min Lu*, Joel Lanir, Chufeng Wang, Yucong Yao, Wen Zhang, Oliver Deussen and Hui Huang

InfoVisTVCGIEEE Transactions on Visualization and Computer Graphics, 2021.
[Paper (2.1 MB)] [Experiment Data ] [My Talk at VIS 2021 ]

In this work, we model the perception of Just Noticeable Differences (JNDs) in charts with two variables (intensity and distance) and find that JND grows as the exponential function.

Exploring Visual Information Flows in Infographics

Min Lu*, Chufeng Wang, Joel Lanir, Nanxuan Zhao, Hanspeter Pfister, Daniel Cohen-Or and Hui Huang

CHI Proceedings of the 2020 CHI conference on human factors in computing systems, 2020.
[Paper (2.0 MB) ] [ InfoVIF dataset ] [Demo Video (MP4, 21.1 MB) ] [My Talk at CHI 2020 ]

In this work, we propose Visual Information Flow (VIF) in infographics and present an framework to extract it in a wild dataset InfoVIF, by which the VIF design patterns are explored.

Winglets: Visualizing Association with Uncertainty in Multi-class Scatterplots

Min Lu*, Shuaiqi Wang, Joel Lanir, Noa Fish, Yang Yue, Daniel Cohen-Or and Hui Huang

InfoVisTVCGIEEE Transactions on Visualization and Computer Graphics, 2019.
[Paper (2.7 MB) ] [Source Code (Python) ] [My Talk at VIS 2019 ]

In this work, we present Winglets, which are designed as a pair of dual-sided strokes, leveraging the Gestalt principle of Closure to shape the perception of the form of the clusters.

Visual Analysis of Multiple Route Choices based on General GPS Trajectories

Min Lu*, Chufan Lai, Tangzhi Ye, Jie Liang, and Xiaoru Yuan

IEEE Transactions on Big Data, 2017.
[Paper (1.2 MB) ] [MP4 (6.1MB)]

In this work, we present a visual analytic system, to help users interact with the large-scale trajectory data, compare different route choices, and explore the underlying reasons.

Interaction+: Interaction Enhancement for Web-based Visualizations

Min Lu*, Jie Liang, Yu Zhang, Guozheng Li, Siming Chen, Zongru Li and Xiaoru Yuan

PacificVisProceedings of IEEE Pacific Visualization Symposium, 2017.
[PDF (1.5 MB) ] [MP4 (14.9 MB)]

In this work, we present Interaction+, an application-independent tool that enhances the interactive capability of existing web-based visualizations without accessing its data.

TrajRank: Exploring Taxi Travel Behaviour on a Route by Trajectory Ranking

Min Lu*, Zuchao Wang and Xiaoru Yuan

PacificVisProceedings of IEEE Pacific Visualization Symposium, 2015.
[PDF (1.9 MB) ] [MP4 (3.6 MB)]

In this work, we present a visual analytic system TrajRank, based on the design of parallel coordinates, that supports to interactively study the travel pattern of single route.

OD-Wheel: Visual Design to Explore OD Patterns of a Central Region

Min Lu*, Zuchao Wang, Jie Liang and Xiaoru Yuan

PacificVisProceedings of IEEE Pacific Visualization Symposium, 2015.
[PDF (1.2 MB)] [MP4 (14.9 MB)]

In this work, we present a visual analytic design OD-Wheel, that supports users to interactively filter trajectories and understand the Origin-Destination (OD) patterns of a city.

Visual Exploration of Sparse Traffic Trajectory Data

Zuchao Wang, Tangzhi Ye, Min Lu*, Xiaoru Yuan, Huamin Qu, Jacky Yuan, and Qianliang Wu

VISTVCGIEEE Transactions on Visualization and Computer Graphics, 2014.
[PDF (1.5 MB)]

In this work, we present a visual analytic system to interactively explore a special kind of transportation data, i.e. sparse traffic trajectory data, collected by transportation cells.

Visual Traffic Jam Analysis Based on Trajectory Data

Zuchao Wang, Min Lu*, Xiaoru Yuan, Zuchao Wang, Min Lu, Junping Zhang, and Huub van de Wetering

VISIEEE Visualization 2013.
[PDF (1.5 MB)] [MP4 (18.3 MB)]

In this work, we present a visual analytic system that can extract urban traffic congestion from taxi GPS trajectories and explore their propergations in spatio-temporal space.