Overview

The workshop aims to explore the use of synthetic data in training and evaluating computer vision models, as well as in other related domains. During the last decade, advancements in computer vision were catalyzed by the release of painstakingly curated human-labeled datasets. Recently, people have increasingly resorted to synthetic data as an alternative to labor-intensive human-labeled datasets for its scalability, customizability, and cost-effectiveness. Synthetic data offers the potential to generate large volumes of diverse and high-quality vision data, tailored to specific scenarios and edge cases that are hard to capture in real-world data. However, challenges such as the domain gap between synthetic and real-world data, potential biases in synthetic generation, and ensuring the generalizability of models trained on synthetic data remain. We hope the workshop can provide a forum to discuss and encourage further exploration in these areas.

Invited Speakers

Angela Dai
Angela Dai
Technical University of Munich
Bharath Hariharan
Bharath Hariharan
Cornell University
Bolei Zhou
Bolei Zhou
University of California, Los Angeles
Jia Deng
Jia Deng
Princeton University
Kiana Ehsani
Kiana Ehsani
Vercept
Yael Vinker
Yael Vinker
Massachusetts Institute of Technology

Schedule

Date: June 11, 2025 · Full day Talks: Grand C2 Posters: Exhall D
  1. 09:00 – 09:20 Opening (Jieyu Zhang) Opening
  2. 09:20 – 10:00 Talk by Yael Vinker Talk
  3. 10:00 – 10:40 Talk by Kiana Ehsani Talk
  4. 10:40 – 11:00 Break Break
  5. 11:00 – 11:40 Talk by Jia Deng Talk
  6. 11:40 – 13:00 Lunch Break
  7. 13:00 – 14:00 Poster Session (Exhall D) Poster
  8. 14:30 – 15:10 Talk by Bolei Zhou Talk
  9. 15:10 – 15:50 Talk by Bharath Hariharan Talk
  10. 15:50 – 16:10 Break Break
  11. 16:10 – 16:50 Talk by Angela Dai Talk
  12. 16:50 – 17:20 Closing (Zixian Ma) Closing

Poster Session

Poster requirements: please follow the CVPR 2025 main conference poster requirements.

Awards

Best Long Paper
DemoGen: Synthetic Demonstration Generation for Data-Efficient Visuomotor Policy Learning
Zhengrong Xue, Shuying Deng, Zhenyang Chen, Yixuan Wang, Zhecheng Yuan, Huazhe Xu
Best Long Paper Runner-up
Buildee: A 3D Simulation Framework for Scene Exploration and Reconstruction with Understanding
Clémentin Boittiaux, Vincent Lepetit
Best Short Paper
BLIP3-KALE: Knowledge Augmented Large-Scale Dense Captions
Anas Awadalla, Le Xue, Manli Shu, An Yan, Jun Wang, Senthil Purushwalkam, Sheng Shen, Hannah Lee, Oscar Lo, Jae Sung Park, Etash Kumar Guha, Silvio Savarese, Ludwig Schmidt, Yejin Choi, Caiming Xiong, +1 more author
Best Short Paper Runner-up
Learning to Blur is Learning to Deblur: Realistic Synthetic UHD Blurred Image via Diffusion
Xin Su, Xiuyi Jia, Chen Wu, Dianjie Lu, Guijuan Zhang, Yang Wen, Zhuoran Zheng

Accepted Papers · 63 papers, sorted alphabetically

  1. ACTUPose: Active Curriculum Training for Unsupervised Domain Adaptation in Pose Estimation#208
    Isha Dua, Arjun Sharma, Shuaib Ahmed, Rahul Tallamraju
  2. Analyze, Generate, Improve: Failure-Based Data Generation for Large Multimodal Models#209
    Gabriela Ben-Melech Stan, Estelle Aflalo, Avinash Madasu, Vasudev Lal, Phillip Howard
  3. Ano-Skin: Clinical Feature-Aware Diffusion Model for Dermatological Image Anonymization#210
    YeonGyu Han, Jung Im Na, Seong Hwan Kim, Dongheon Lee
  4. Applying Longitudinal Augmentation and Data Generation (LAUGEN) in Medical Imaging#211
    Nico Disch, Balint Kovacs, Constantin Ulrich, Robin Peretzke, Saikat Roy, Maximilian Rouven Rokuss, Yannick Kirchhoff, David Zimmerer, Klaus Maier-Hein
  5. Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?#212
    Shashank Agnihotri, David Schader, Nico Sharei, Mehmet Ege Kaçar, Margret Keuper
  6. Ask, Pose, Unite: Scaling Data Acquisition for Close Interaction Meshes with Vision Language Models#213
    Laura Bravo-Sánchez, Jaewoo Heo, Zhenzhen Weng, Kuan-Chieh Wang
  7. BLIP3-KALE: Knowledge Augmented Large-Scale Dense Captions#214
    Anas Awadalla, Le Xue, Manli Shu, An Yan, Jun Wang, Senthil Purushwalkam, Sheng Shen, Hannah Lee, Oscar Lo, Jae Sung Park, Etash Kumar Guha, Silvio Savarese, Ludwig Schmidt, Yejin Choi, Caiming Xiong, +1 more author
  8. Boosting Synthetic Data for VLMs via Diffusion Noise Optimization#215
    Ren Ohkubo, Rintaro Yanagi, Hirokatsu Kataoka, Yutaka Satoh
  9. Bounding Box-Guided Diffusion for Synthesizing Industrial Images and Segmentation Maps#216
    Alessandro Simoni, Francesco Pelosin
  10. BRADD: Balancing Representations with Anomaly Detection and Diffusion#217
    Filipe Laitenberger, Nesta Midavaine, Ioana Simion, Stefan Vasilev, Hirokatsu Kataoka, Cees G. M. Snoek, Yuki M Asano, Mohammadreza Salehi
  11. Bridging the Domain Gap: Enhancing Underwater Laser Stripe Segmentation with Synthetic Data#218
    Javiera Fuentes-Guíñez, Giancarlo Troni
  12. Buildee: A 3D Simulation Framework for Scene Exploration and Reconstruction with Understanding#219
    Clémentin Boittiaux, Vincent Lepetit
  13. Challenges in 3D Data Synthesis for Training Neural Networks on Topological Features#220
    Dylan Peek, Matthew P. Skerritt, Siddharth Pritam, Stephan Chalup
  14. COMPACT: COMPositional Atomic-to-Complex Visual Capability Tuning#221
    Xindi Wu, Hee Seung Hwang, Polina Kirichenko, Olga Russakovsky
  15. Concept-as-Tree: Synthetic Data is All You Need for VLM Personalization#222
    Ruichuan An, Kai Zeng, Ming Lu, Sihan Yang, Renrui Zhang, Huitong Ji, Qizhe Zhang, Yulin Luo, Hao Liang, Wentao Zhang
  16. Corner Cases: How Size and Position of Objects Challenge ImageNet-Trained Models#223
    Mishal Fatima, Steffen Jung, Margret Keuper
  17. DemoGen: Synthetic Demonstration Generation for Data-Efficient Visuomotor Policy Learning#224
    Zhengrong Xue, Shuying Deng, Zhenyang Chen, Yixuan Wang, Zhecheng Yuan, Huazhe Xu
  18. Diffusion Deepfake#225
    Chaitali Bhattacharyya, Hanxiao Wang, Feng Zhang, Sungho Kim, Xiatian Zhu
  19. DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions#226
    Shashank Agnihotri, Amaan Ansari, Annika Dackermann, Fabian Rösch, Margret Keuper
  20. DocGenie: A Framework for High-Fidelity Synthetic Document Generation via Seed-Guided Multimodal LLM and Document-Aware Evaluation#227
    Harikrishnan P M, SIDDARTHA REDDY, Goutham Vignesh, Rohit Agrawal, Vishal Vaddina
  21. Does Feasibility Matter? Understanding the Impact of Feasibility on Synthetic Training Data#228
    Yiwen Liu, Jessica Bader, Jae Myung Kim
  22. Evaluating Text-to-Image Diffusion Models for Texturing Synthetic Data#229
    Thomas Lips, Francis Wyffels
  23. GASR: Generated Artwork dataset for Image Super-Resolution#230
    Noritake Kodama, Go Ohtani, Yuto Matsuo, Rintaro Yanagi, Nakamasa Inoue, Yoshimitsu Aoki, Hirokatsu Kataoka
  24. Generate Any Scene: Evaluating and Improving Text-to-Vision Generation with Scene Graph Programming
    Ziqi Gao, Weikai Huang, Jieyu Zhang, Aniruddha Kembhavi, Ranjay Krishna
  25. Generating Synthetic Data via Augmentations for Improved Facial Resemblance in DreamBooth and InstantID#231
    Koray Ulusan, Benjamin Kiefer
  26. Generating Synthetic Stereo Datasets using 3D Gaussian Splatting and Expert Knowledge Transfer#232
    Filip Slezák, Magnus Kaufmann Gjerde, Joakim Bruslund Haurum, Ivan Nikolov, Morten Stigaard Laursen, Thomas B. Moeslund
  27. GIMO: Generative Image Outpainting for Early Smoke Segmentation#233
    Sahir Shrestha, Weihao Li, Gao Zhu, Nick Barnes
  28. H2R: A Human-to-Robot Data Augmentation for Robot Pre-training from Videos#234
    Guangrun Li, Yaoxu Lyu, Zhuoyang Liu, Chengkai Hou, Yinda Xu, Jieyu Zhang, Shanghang Zhang
  29. Harnessing Diffusion-Generated Synthetic Images for Fair Image Classification#235
    Abhipsa Basu, Aviral Gupta, Abhijnya Bhat, Venkatesh Babu Radhakrishnan
  30. Improving Physical Object State Representation in Text-to-Image Generative Systems#236
    Tianle Chen, Chaitanya Chakka, Deepti Ghadiyaram
  31. Instant Particle Size Distribution Measurement Using CNNs Trained on Synthetic Data#237
    Yasser El Jarida, Youssef Iraqi, Loubna Mekouar
  32. Investigating the Influence of Image Augmentations on the Sim-to-Real Generalization of Deep Learning Perception Models#238
    Joachim Rüter, Umut Durak, Johann C. Dauer
  33. Investigating the Scaling Effect of Instruction Templates for Training Multimodal Language Model
    Shijian Wang, Linxin Song, Jieyu Zhang, Ryotaro Shimizu, Jiarui Jin, Ao Luo, Yuan Lu, Li Yao, Cunjian Chen, Julian McAuley, Wentao Zhang, Hanqian Wu
  34. Latent Video Dataset Distillation#239
    Ning Li, Antai Andy Liu, Jingran Zhang, Justin Cui
  35. LATTE: Learning to Reason with Vision Specialists#240
    Zixian Ma, Jianguo Zhang, Zhiwei Liu, Jieyu Zhang, Juntao Tan, Manli Shu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Caiming Xiong, Ranjay Krishna, silvio savarese
  36. Learning 3D Representations from Procedural 3D Programs#241
    Xuweiyi Chen, Zezhou Cheng
  37. Learning from Synthetic Data for Visual Grounding#242
    Ruozhen He, Ziyan Yang, Paola Cascante-Bonilla, Alexander C. Berg, Vicente Ordonez
  38. Learning to Blur is Learning to Deblur: Realistic Synthetic UHD Blurred Image via Diffusion#243
    Xin Su, Xiuyi Jia, Chen Wu, Dianjie Lu, Guijuan Zhang, Yang Wen, Zhuoran Zheng
  39. Leveraging Automatic CAD Annotations for Supervised Learning in 3D Scene Understanding#244
    Yuchen Rao, Stefan Ainetter, Sinisa Stekovic, Vincent Lepetit, Friedrich Fraundorfer
  40. LFQUIAD: Lookup-Free Quantized autoencoder for few-shot Unsupervised Industrial Anomaly Detection via Synthetic Diffusion Inpainting#245
    SHIH-CHIH LIN, Shang-Hong Lai
  41. LiveVQA: Assessing Models with Live Visual Knowledge#246
    Mingyang Fu, Yuyang Peng, Benlin Liu, Yao Wan, Dongping Chen
  42. Minimizing Data, Maximizing Performance: Generative Examples for Continual Task Learning#247
    Mahsa Mozafarinia, Joshua Andle, Santhosh Karnik, Daniel Goldfarb, PAul HAnd, Salimeh Sekeh
  43. MirrorVerse: Pushing Diffusion Models to Realistically Reflect the World#248
    Ankit Dhiman, Manan Shah, Venkatesh Babu Radhakrishnan
  44. MoireDB: A Formula-driven Image Dataset for Robustness Enhancement#249
    Yuto Matsuo, Yoshihiro Fukuhara, Yuki M Asano, Hirokatsu Kataoka, Akio Nakamura
  45. MultiRef: Controllable Image Generation with Multiple Visual References#250
    Ruoxi Chen, Siyuan Wu, Dongping Chen, Shiyun Lang, Petr Sushko, Gaoyang Jiang, Sinan Wang, Yao Wan, Ranjay Krishna
  46. Not All Samples Should Be Utilized Equally: Towards Understanding and Improving Dataset Distillation#251
    Shaobo Wang, Yantai Yang, Qilong Wang, Kaixin Li, Linfeng Zhang, Junchi Yan
  47. Point Cloud Segmentation of Agricultural Vehicles using 3D Gaussian Splatting#252
    Alfred T. Christiansen, Andreas H. Højrup, Morten K. Stephansen, Md Ibtihaj Amin, Taman S. Poojary, Filip Slezák, Morten Stigaard Laursen, Thomas B. Moeslund, Joakim Bruslund Haurum
  48. Quo Vadis Handwritten Text Generation for Handwritten Text Recognition?#253
    Konstantina Nikolaidou, Vittorio Pippi, Silvia Cascianelli, Marcus Liwicki, Rita Cucchiara
  49. R3ST: A Synthetic Dataset with Real Trajectories for Urban Traffic Analysis#254
    Simone Teglia, Claudia Melis Tonti, Francesco Pro, Leonardo Russo, Andrea Alfarano, Matteo Pentassuglia, Irene Amerini
  50. RAFT: Robust Augmentation of FeaTures for Image Segmentation#255
    Edward Steven Humes, Xiaomin Lin, Utteja Kallakuri, Tinoosh Mohsenin
  51. ReSIT: A more Realistic Synthetic Driving Dataset for Multi-Domain Image-to-Image Translation#256
    Joonhyung Park, Yeong-Seok Kim, HeonJeong Chu, Hye-Rin Kim, Seungryong Kim
  52. RoadSocial: A Diverse VideoQA Dataset and Benchmark for Road Event Understanding from Social Video Narratives#257
    Chirag Parikh, Deepti Rawat, Rakshitha R. T., Tathagata Ghosh, Ravi Kiran Sarvadevabhatla
  53. Stable Bidirectional Graph Convolutional Networks for Label-Frugal Skeleton-based Recognition#258
    Hichem Sahbi
  54. STM2PE-Diff : Synthetically Trained Music-to-Pose Encoder Diffusion for Automated Choreography Generation#259
    Nokap Tony Park
  55. SVI-Paste: Synthetic Dynamic Instance Copy-Paste#260
    Sahir Shrestha, Weihao Li, Gao Zhu, Nick Barnes
  56. SynSHRP2: A Synthetic Multimodal Benchmark for Driving Safety-critical Events Derived from Real-world Driving Data#261
    Liang Shi, Boyu Jiang, Zhenyuan Yuan, Miguel A. Perez, Feng Guo
  57. SynTable: A Synthetic Data Generation Pipeline for Unseen Object Amodal Instance Segmentation of Cluttered Tabletop Scenes#262
    Zhili Ng, Haozhe Wang, Zhengshen Zhang, Francis E. H. Tay, Marcelo H Ang Jr
  58. Synthesizing 3D Abstractions by Inverting Procedural Buildings with Transformers#263
    Maximilian Dax, Jordi Serrano Berbel, Jan Stria, Leonidas Guibas, Urs M Bergmann
  59. Synthetic Data Generation for Demonstrating Noise Reduction in Facial Depth Imaging#264
    Connah Kendrick, Moi Hoon Yap, Kevin Tan
  60. Synthetic Generation and Latent Projection Denoising of Rim Lesions in Multiple Sclerosis#265
    Alexandra Grace Roberts, Ha Manh Luu, Mert Sisman, Alexey V. Dimov, Ceren Tozlu, Ilhami Kovanlikaya, Susan Gauthier, Thanh D. Nguyen, Yi Wang
  61. Synthetic Human Action Video Data Generation with Pose Transfer#266
    Václav Knapp, Maty Bohacek
  62. Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding#267
    Kohei Torimi, Ryosuke Yamada, Daichi Otsuka, Kensho Hara, Yuki M Asano, Hirokatsu Kataoka, Yoshimitsu Aoki
  63. You Are Your Best Teacher: Semi-Supervised Surgical Point Tracking with Cycle-Consistent Self-Distillation#268
    Valay Bundele, Mehran Hosseinzadeh, Hendrik Lensch

Sponsorship

If you are interested in sponsoring the SynData4CV workshop @ CVPR 2025, please reach out to Jieyu Zhang (jieyuz2@cs.washington.edu).

Important Workshop Dates

Organizers

Jieyu Zhang
Jieyu Zhang
University of Washington
Weikai Huang
Weikai Huang
University of Washington
Cheng-Yu Hsieh
Cheng-Yu Hsieh
University of Washington
Zixian Ma
Zixian Ma
University of Washington
Rundong Luo
Rundong Luo
Cornell University
Shobhita Sundaram
Shobhita Sundaram
Massachusetts Institute of Technology
Wei-Chiu Ma
Wei-Chiu Ma
Cornell University
Ranjay Krishna
Ranjay Krishna
University of Washington