activity
20242026
most citedFontCLIP: A Semantic Typography Visual-Language Model for Multilingual Font Applications

13 citations · 30 across the 12 of their papers we have counts for

collaborators
Showing 2025Show all

8 papers · 1 filter

cs.GR2025★ 4 cited

Neural Image Abstraction Using Long Smoothing B-Splines

Daniel Berio, Michael Stroh, Sylvain Calinon +3

We integrate smoothing B-splines into a standard differentiable vector graphics (DiffVG) pipeline through linear mapping, and show how this can be used to generate smooth and arbit…

cs.GR2025

MiGumi: Making Tightly Coupled Integral Joints Millable

Aditya Ganeshan, Kurt Fleischer, Wenzel Jakob +4

Traditional integral wood joints, despite their strength, durability, and elegance, remain rare in modern workflows due to the cost and difficulty of manual fabrication. CNC millin…

cs.GR2025

LayoutRectifier: An Optimization-based Post-processing for Graphic Design Layout Generation

I-Chao Shen, Ariel Shamir, Takeo Igarashi

Recent deep learning methods can generate diverse graphic design layouts efficiently. However, these methods often create layouts with flaws, such as misalignment, unwanted overlap…

cs.HC2025★ 2 cited

VeasyGuide: Personalized Visual Guidance for Low-vision Learners on Instructor Actions in Presentation Videos

Yotam Sechayk, Ariel Shamir, Amy Pavel +1

Instructors often rely on visual actions such as pointing, marking, and sketching to convey information in educational presentation videos. These subtle visual cues often lack verb…

cs.CV2025★ 5 cited

LightLab: Controlling Light Sources in Images with Diffusion Models

Nadav Magar, Amir Hertz, Eric Tabellion +4

We present a simple, yet effective diffusion-based method for fine-grained, parametric control over light sources in an image. Existing relighting methods either rely on multiple i…

cs.CV2025

MASH: Masked Anchored SpHerical Distances for 3D Shape Representation and Generation

Changhao Li, Yu Xin, Xiaowei Zhou +4

We introduce Masked Anchored SpHerical Distances (MASH), a novel multi-view and parametrized representation of 3D shapes. Inspired by multi-view geometry and motivated by the impor…