Art

Follow this topic Ask about this topic

Momentum

10 papers in the last four weeks, down 17% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 79

All topics

TextSculptor: Training and Benchmarking Scene Text Editing
May 20, 2026Yiheng Lin, Siyu Jiao, Xiaohan Lan +12Text-To-Image Art
Beijing Jiaotong University · Bytedance
PaintCopilot: Modeling Painting as Autonomous Artistic Continuation
May 20, 2026Yunge Wen, Yuancheng Shen, Paul Pu LiangArt
MIT Media Lab, United States · New York University, United States
Preferences Order, Ratings Anchor: From Fused Expert Aesthetic Ground Truth to Self-Distillation
May 19, 2026Yuanpei Zhao, Jie Lin, Chao Zhang +5Aesthetics Large-Scale Image Datasets
1Sichuan University · 2NetEase Fuxi AI Lab · †Work done during an internship at NetEase Fuxi AI Lab. +1
Harnessing Self-Supervised Features for Art Classification
May 18, 2026Federico Melis, Davide Bilardello, Emanuele Prato +2Image Classification Art
University of Modena and Reggio Emilia, Modena, Italy
ArtMesh: Part-Aware Articulated Mesh Fields with Motion-Consistent Dynamics
May 15, 2026Sylvia Yuan, Dan Wang, Ravi Ramamoorthi +1Meshes 3D Models
University of California San Diego · University of North Texas
MorphoHELM: A Comprehensive Benchmark for Evaluating Representations for Microscopy-Based Morphology Assays
May 14, 2026Emre Hayir, Lorin Crawford, Alex X. LuArt
Microsoft Research New England
AI-assisted cultural heritage dissemination: Comparing NMT and glossary-augmented LLM translation in rock art documents
May 14, 2026Vicent Briva-Iglesias, María Ferre-FernándezNeural Machine Translation Cultural Heritage
SALIS, CTTS, ADAPT Centre · Dublin City University · Universidad de Almer´ıa
The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security Beyond Binary Scoring
May 9, 2026Ismail Hossain, Tanzim Ahad, Md Jahangir Alam +3Jailbreak Attacks Jailbreaks
Department of Computer Science, University of Texas at El Paso, TX, USA 79902 · School of Computing, Southern Illinois University Carbondale, IL, USA 62901 · University of Illinois Urbana-Champaign, IL, USA
AniMatrix: An Anime Video Generation Model that Thinks in Art, Not Physics
May 5, 2026Tencent HY TeamGenerative Video Models Video Generation
Tencent HY Team
Alter-Art: Exploring Embodied Artistic Creation through a Robot Avatar
Apr 29, 2026Do Won Park, Samuele Bordini, Giorgio Grioli +2Artistic Ownership Robot Autonomy
Soft Robotics for Human Cooperation and Rehabilitation, Istituto Italiano di Tecnologia, via Morego, 30, Genoa, 16163, Liguria, Italy. · Centro di Ricerca “E.Piaggio”, Universita’ di Pisa, Largo Lucio Lazzarino, 1, Pisa, 56122, Tuscany, Italy. · Dipartimento di Ingegneria dell’Informazione, Universita’ di Pisa, Via Girolamo Caruso, 16, Pisa, 56122, Tuscany, Italy.
Progressing beyond Art Masterpieces or Touristic Clichés: how to assess your LLMs for cultural alignment?
Apr 28, 2026António Branco, João Silva, Nuno Marques +10Cultural Awareness Large Language Model Alignment
†University of Lisbon · ‡University of Beira Interior
MIRAGE: A Micro-Interaction Relational Architecture for Grounded Exploration in Multi-Figure Artworks
Apr 26, 2026Jui-Cheng Chiu, Yu-Chao Wang, Shengyang Luo +4Video Storytelling Art
Purdue University
Auto-ART: Structured Literature Synthesis and Automated Adversarial Robustness Testing
Apr 22, 2026Abhijit TalluriAdversarial Evaluation Art
Independent Researcher
A-MAR: Agent-based Multimodal Art Retrieval for Fine-Grained Artwork Understanding
Apr 21, 2026Shuai Wang, Hongyi Zhu, Jia-Hong Huang +6Multimodal Reasoning Multimodal Understanding
University of Amsterdam · Part of this work was done during interning at Amazon. · Also with Amazon AGI. +2
MESA: A Training-Free Multi-Exemplar Deep Framework for Restoring Ancient Inscription Textures
Apr 19, 2026Vasileios Toulatzis, Sofia Theodoridou, Ioannis FudosImage Restoration Historical Manuscripts
University of Ioannina, Greece
Allure of Craquelure: A Variational-Generative Approach to Crack Detection in Paintings
Feb 10, 2026Laura Paul, Holger Rauhut, Martin Burger +2Art Variational
Dept. of Mathematics, LMU Munich, Germany · Munich Center for Machine Learning, Germany · Helmholtz Imaging, Deutsches Elektronen-Synchrotron DESY, Germany +2
ART-TEB: Adaptive Trajectory Planning for Mobile Robots in Cluttered Environments
Oct 30, 2025Hahjin Lee, Young J. KimMobile Robots Collision Prediction
Department of Computer Science and Engineering at Ewha Womans University in Korea
CompArt: Operationalizing Aesthetic Alignment in Text-to-Image Generation via Principles of Art
Mar 15, 2025Zhe Jin, Tat-Seng ChuaArt Value Alignment
National University of Singapore Singapore
ArtNVG: Content-Style Separated Artistic Neighboring-View Gaussian Stylization
Dec 25, 2024Zixiao Gu, Mengtian Li, Ruhua Chen +5Stylization 3D Gaussian
Fudan University · Shanghai University · Shanghai Theatre Academy

May 20, 2026, cs.CVJ/K move · Enter open · S save

TextSculptor: Training and Benchmarking Scene Text Editing

Yiheng Lin, Siyu Jiao, Xiaohan Lan, Wei Zhou+11

Beijing Jiaotong University · Bytedance

Text-To-Image Art

Open paper AskPDF arXiv

Recent advances in Multimodal Large Language Models (MLLMs) and diffusion-based generative models have substantially improved prompt-driven image editing. However, scene text editing remains challenging, as it requires models to precisely modify textual content while preserving visual realism and non-target regions. Current open-source models still lag behind proprietary systems, largely due to the scarcity of high-quality training data and the lack of standardized benchmarks tailored to text editing. To address these challenges, we present TextSculptor, a comprehensive framework for data construction and evaluation of scene text editing. We first develop an automated data construction pipeline that combines text-aware image synthesis with programmatic text rendering and compositing. Based on this pipeline, we build TextSculpt-Data, a large-scale dataset containing 3.2M training samples, including 1.2M OCR-verified text-to-image samples and 2M paired text editing samples with naturally aligned source-target images and strong background consistency. We further introduce TextSculpt-Bench, a benchmark covering four fundamental text editing tasks: text addition, text replacement, text removal, and hybrid editing. To support reliable evaluation, we design a tailored protocol that measures text accuracy, visual quality, and background preservation through OCR-based text alignment, multimodal judgment, and background-region similarity. Extensive experiments show that TextSculptor improves open-source text editing performance and narrows the gap to proprietary models. The data and benchmark are available at https://github.com/linyiheng123/TextSculptor.

Momentum

Related topics

Latest papers 79