Overview

Welcome to The 3rd Workshop on Synthetic Data for Computer Vision (SynData4CV) at CVPR 2026! During the last decade, advances in computer vision have been catalyzed by the release of meticulously 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 the generalizability of models trained on synthetic data remain. This workshop aims to provide a forum for discussion and encouragement of further exploration in these areas. Topics of interest include, but are not limited to:

• Effectiveness: What is the most effective way to generate and leverage synthetic data? Does synthetic data need to "look" realistic?
• Efficiency and scalability: Can we make synthetic data generation more efficient and scalable without much sacrifice on the quality?
• Benchmark and evaluation: What benchmark and evaluation methods are needed to assess the efficacy of synthetic data for computer vision?
• Risks and ethical considerations: How can we mitigate the risks of generating and using synthetic data? How do we address relevant ethical questions, such as bias amplification in synthetic datasets?
• Applications: What are other tasks in computer vision or other related fields (e.g., robotics, NLP) that could benefit from synthetic data?
• Other open problems: How do we decide which type of data to use, synthetic or real-world data? What is the optimal way to combine both if both are available?

Invited Speakers

Jia Deng

Princeton University

Georgia Gkioxari

Caltech

Nupur Kumari

Carnegie Mellon University

Manling Li

Northwestern University

Andrew Owens

Cornell Tech

Schedule

Date: June 4, 2026 · Afternoon (Half day) Location: Room 607

1. 1:00 – 1:10 PM Opening Remarks Opening
2. 1:10 – 1:45 PM Invited Talk · Manling Li Talk
3. 1:45 – 2:20 PM Invited Talk · Jia Deng Talk
4. 2:20 – 2:55 PM Invited Talk · Georgia Gkioxari Talk
5. 2:55 – 3:10 PM Break Break
6. 3:10 – 3:45 PM Invited Talk · Andrew Owens Talk
7. 3:45 – 4:20 PM Invited Talk · Nupur Kumari Talk
8. 4:20 – 4:30 PM Closing Remarks Closing
9. 4:30 – 5:30 PM Poster Session · Boards 203–232 Poster

Awards

Best Long Paper

Winner

Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification

William Yang, Xindi Wu, Zhiwei Deng, Esin Tureci, Olga Russakovsky

Princeton University

Runner-up

Sequential Dataset for Satellite Pose Estimation and a Frequency-Space Neural Operator for HIL-Free Generalization Benchmarking

Woojin Cho, Junghwan Park, Steve Andreas Immanuel, Junmin Park, Seokhyun Chin, Jiayun Wang

TelePIX, California Institute of Technology, Georgia Institute of Technology

Best Short Paper

Winner

Beyond Raw Signals: Undecoded Generative Latents as Privileged Synthetic Data

Cristian Sbrolli, Nicolas Michel, Matteo Matteucci, Toshihiko Yamasaki

Politecnico di Milano & The University of Tokyo

Runner-up

WireSeg-32K: A Physics-Grounded Synthetic Dataset for Wire Instance Segmentation

Zilin Dai, Lehong Wang, Yi Yang, Xiang Fei

Northeastern University

Accepted Papers · 54 papers, sorted alphabetically · poster boards 203–232

OpenReview: Accepted papers are also available on the SynData4CV 2026 OpenReview accepted papers page.

Poster assignment: Posters are assigned alphabetically, two papers per board. Please use the board number shown next to your paper title.

Board-by-board poster assignments

Board 203

1. Addressing Data Scarcity in Depth-Based Human Action Recognition via Zero-Shot Depth Estimation
   Rebeka Angyal, Pedro Hermosilla, Martin Kampel, Irene Ballester
2. AfriST-VQA: Benchmarking MLLMs for Scene-Text Visual Question Answering for African Languages
   Henry Gagnier

Board 204

1. Appreciate the View: A Task-Aware Evaluation Framework for Novel View Synthesis
   Saar Stern, Ido Sobol, Or Litany
2. Assessing the Predictive Value of Physics-Grounded Synthetic Data for Computer Vision in Space Environments
   Arianna Issitt, Emily Happy, Elijah Clark, Mackenzie J. Meni, Ryan T. White

Board 205

1. Auto-Comp: Scalable Controlled Synthetic Benchmarks for VL Compositionality
   Cristian Sbrolli, Toshihiko Yamasaki, Matteo Matteucci
2. Avatar4D: Synthesizing Domain-Specific 4D Humans for Real-World Pose Estimation
   Jerrin Bright, Zhibo Wang, Dmytro Klepachevskyi, Yuhao Chen, Sirisha Rambhatla, David A. Clausi, John S. Zelek

Board 206

1. Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification
   William Yang, Xindi Wu, Zhiwei Deng, Esin Tureci, Olga Russakovsky
2. Beyond Photorealism: Counterfactual Synthetic Bundles for Invariant Sim-to-Real Vision
   Murari Ambati

Board 207

1. Beyond Raw Signals: Undecoded Generative Latents as Privileged Synthetic Data
   Cristian Sbrolli, Nicolas Michel, Matteo Matteucci, Toshihiko Yamasaki
2. Completing Missing Modalities: Synthetic Data for RGB–Infrared–Thermal–Text Person Re-Identification
   Muhammad Umair, Muhammad Hammad Musaddiq, Jun Zhou, Ahmad Muhammad

Board 208

1. CryoDiff: Cryo-EM Synthesis via Biophysics and Cycle-Consistent Diffusion
   Genpei Zhang, Yuntian Yang, Siqi Wu, Ningyan Zhang, Seonghui Min, Jie Wu, Christopher Braxton Owens, Minhao Wu, Wanyue Feng, Gus LW Hart, Runmin Jiang, Min Xu
2. Diffusion-Augmented Coreset Expansion for Scalable Dataset Distillation
   Ali Abbasi, Shima Imani, Chenyang An, Gayathri Mahalingam, Harsh Shrivastava, Maurice Diesendruck, Hamed Pirsiavash, Pramod Sharma, Soheil Kolouri

Board 209

1. Disentangled Anatomy-Disease Diffusion (DADD) for Controllable Ulcerative Colitis Progression Synthesis
   Umut Dundar, Alptekin Temizel
2. Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer
   Hyunsoo Cha, Byungjun Kim, Hanbyul Joo

Board 210

1. Evaluating the Trade-offs of MDL-to-UsdPreviewSurface Material Simplification in NVIDIA Isaac Sim: Visual Quality, Feature Preservation, and AI Task Performance
   Zihou Zhu, Mei Haitao, Haolong Zheng, Zhou Zhang
2. Few-Shot Synthetic Data Generation with Diffusion Models for Downstream Vision Tasks
   Daniil Dushenev, Nazariy Karpov, Daniil Zinovjev, Alexander Gorin, Konstantin Kulikov

Board 211

1. Fréchet Inception Distance is Failing to Preserve Rank Consistency for Synthetic Out-of-Distribution Samples
   Linghui Liu, Henrike Stephani, Janis Keuper
2. Generating Synthetic Illumination Variation with Co-Located Relighting
   Yash Turkar, Karthik K Dantu

Board 212

1. Grounding Synthetic Data Generation With Vision and Language Models
   Ümit Mert Çağlar, Alptekin Temizel
2. How Far Can We Go With Synthetic Data for Audio-Visual Sound Source Localization?
   Arda Senocak, Sooyoung Park, Tae-Hyun Oh, Joon Son Chung

Board 213

1. Hybrid Rendering for Multimodal Autonomous Driving: Merging Neural and Physics-Based Simulation
   Máté Tóth, Péter Kovács, Réka Bencses, Zoltan Bendefy, Zoltan Hortsin, Balázs Teréki, Tamas Matuszka
2. iARCS: Iterative Agentic RL for Controllable 3D Scene Generation
   Saugat Adhikari, Ashok Prasad Neupane, Pramish Paudel, Ajad Chhatkuli, Danda Pani Paudel

Board 214

1. Masked Language Prompting for Generative Data Augmentation in Few-shot Fashion Style Recognition
   Yuki Hirakawa, Ryotaro Shimizu
2. Multi-Objective Photoreal Simulation (MOPS) Dataset for Computer Vision in Robot Manipulation
   Maximilian Xiling Li, Paul Mattes, Nils Blank, Rudolf Lioutikov

Board 215

1. Narrowing the Performance Gap in Synthetic VLM Pre-training via Multi-Generator Ensembles
   Leonardo Brusini, Cristian Sbrolli, Eugenio Lomurno, Toshihiko Yamasaki, Matteo Matteucci
2. Object-Centric Data Synthesis for Category-level Object Detection
   Vikhyat Agarwal, Jiayi Cora Guo, Declan Hoban, Sissi Yuxi Zhang, Nick Moran, Peter Cho, Srilakshmi Pattabiraman, Shantanu H. Joshi

Board 216

1. One Category One Prompt: Dataset Distillation using Diffusion Models
   Ali Abbasi, Ashkan Shahbazi, Hamed Pirsiavash, Soheil Kolouri
2. OrbitArch
   I-Ting Tsai, Bharath Hariharan

Board 217

1. Personalized Generative Models for Contextual Debiasing
   Xinran Liang, Esin Tureci, Prachi Sinha, Ye Zhu, Vikram V. Ramaswamy, Olga Russakovsky
2. PLLM: Pseudo-Labeling Large Language Models for CAD Program Synthesis
   Yuanbo Li, Dule Shu, Yan-Ying Chen, Matthew Klenk, Daniel Ritchie

Board 218

1. Privacy-Aware Synthetic Video Benchmarking and Relational Evaluation for Worker-Under-Suspended-Load Detection
   Anshu Singh, Alejandro Seif
2. ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL
   Mukund Khanna, Raj Singh Yadav, Kunal Singh

Board 219

1. RareCrafter: Controllable Generative Augmentation for Rare Object Detection in Driving Scenes
   Mohadeseh Ghafoori, Danielle Lee, Kurt Hammen, Collin Meese, Mark Nejad
2. Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning
   Ido Sobol, Kihyuk Sohn, Yoav Blum, Egor Zakharov, Max Bluvstein, Andrea Vedaldi, Or Litany

Board 220

1. Representation-Conditioned Diffusion Models for Guided Training Data Generation
   Nithesh Chandher Karthikeyan, Jonas Unger, Gabriel Eilertsen
2. Restereo: Unifying diffusion stereo video generation and restoration
   Xingchang Huang, Ashish Kumar Singh, Florian Dubost, Cristina Nader Vasconcelos, Sakar Khattar, Liang Shi, Christian Theobalt, Cengiz Oztireli, Gurprit Singh

Board 221

1. SAIL: Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense Video Captioning
   Ye-Chan Kim, SeungJu Cha, Si-Woo Kim, MinJu Jeon, HyunGee Kim, Dong-Jin Kim
2. Scaling Up 3D Forest Vision with Synthetic LiDAR
   Yihang She, Andrew Blake, David Coomes, Srinivasan Keshav

Board 222

1. Sea-Mie: Physically-Based Synthetic Fog for Maritime Image Defogging via Curriculum Learning
   Stelios Avlakiotis, Peter Ter Heerdt, Thomas De Kerf, Steve Vanlanduit
2. Sequential Dataset for Satellite Pose Estimation and a Frequency-Space Neural Operator for HIL-Free Generalization Benchmarking
   Woojin Cho, Junghwan Park, Steve Andreas Immanuel, Junmin Park, Seokhyun Chin, Jiayun Wang

Board 223

1. Sim-to-Real Metrology: Calibrated Digital Twins for Fringe Projection Profilometry
   NOBLE AUSTINE, Vuppu Eshwar Sai, Vaishnavi Ravi, Madhu S. Nair, Gorthi Rama Krishna Sai Subrahmanyam
2. SJEPA: Joint Embedding Predictive Architecture for Synthetic-to-Real Alignment
   Shentong Mo

Board 224

1. Structure-Consistent Joint Image-Mask Synthesis for Data-Scarce Medical Image Segmentation
   Ningyan Zhang, Weiyi Zhang, Mostofa Rafid Uddin, Xingjian Li, Min Xu
2. Structure-retained low-rank adapters for weather synthesis
   Shunxin Wang, Alexandros Stergiou, Luuk Spreeuwers, Estefania Talavera, Nicola Strisciuglio

Board 225

1. StyleText: A Large-Scale Dataset and Benchmark for Stylized Scene Text Inpainting
   Aleksandr Simonyan, Nipun Jindal
2. Synthetic Data Generation for Long-Tail Medical Image Classification: A Case Study in Skin Lesions
   Jiaxiang Jiang, Mahesh Subedar, Omesh Tickoo

Board 226

1. Synthetic Designed Experiments for Diagnosing Vision Model Failures
   Krisanu Sarkar
2. Theory of Space: Evaluating Active Spatial Belief Construction in Foundation Models with Synthetic 3D Environments
   Pingyue Zhang, Zihan Huang, Yue Wang, Jieyu Zhang, Letian Xue, Zihan Wang, Qineng Wang, Keshigeyan Chandrasegaran, Ruohan Zhang, Yejin Choi, Ranjay Krishna, Jiajun Wu, Li Fei-Fei, Manling Li

Board 227

1. Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision
   Hyunsoo Cha, Wonjung Woo, Byungjun Kim, Hanbyul Joo
2. Video-Consistent Synthetic Skiing Trajectories
   M'Saydez Campbell, Rémi Emonet, Damien Muselet, Christophe Ducottet

Board 228

1. WaterGen: Decoupling Scene and Medium in Underwater Image Generation
   Jiayi Wu, Tianfu Wang, Tianyi Xiong, Dehao Yuan, Xiaomin Lin, Md Jahidul Islam, Cornelia Fermuller, Christopher Metzler, Yiannis Aloimonos
2. When Does Synthetic Data Help? A Spectral Theory of Task-Relevant Domain Gap with Applications to Guided Generation and Bias Auditing
   Kaustubh S. Bukkapatnam, Rayan Malik

Board 229

1. Why Training with Synthetic Data Fails for OOD: Distribution Gap Amplifies Noise Misalignment in Diffusion Models
   Ying Hua, Jessica Bader, Jae Myung Kim, Zeynep Akata
2. WireSeg-32K: A Physics-Grounded Synthetic Dataset for Wire Instance Segmentation
   Zilin Dai, Lehong Wang, Yi Yang, Xiang Fei

Board 230

Reserved / overflow

Board 231

Reserved / overflow

Board 232

Reserved / overflow

1. Addressing Data Scarcity in Depth-Based Human Action Recognition via Zero-Shot Depth Estimation#203
   Rebeka Angyal, Pedro Hermosilla, Martin Kampel, Irene Ballester
2. AfriST-VQA: Benchmarking MLLMs for Scene-Text Visual Question Answering for African Languages#203
   Henry Gagnier
3. Appreciate the View: A Task-Aware Evaluation Framework for Novel View Synthesis#204
   Saar Stern, Ido Sobol, Or Litany
4. Assessing the Predictive Value of Physics-Grounded Synthetic Data for Computer Vision in Space Environments#204
   Arianna Issitt, Emily Happy, Elijah Clark, Mackenzie J. Meni, Ryan T. White
5. Auto-Comp: Scalable Controlled Synthetic Benchmarks for VL Compositionality#205
   Cristian Sbrolli, Toshihiko Yamasaki, Matteo Matteucci
6. Avatar4D: Synthesizing Domain-Specific 4D Humans for Real-World Pose Estimation#205
   Jerrin Bright, Zhibo Wang, Dmytro Klepachevskyi, Yuhao Chen, Sirisha Rambhatla, David A. Clausi, John S. Zelek
7. Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification#206
   William Yang, Xindi Wu, Zhiwei Deng, Esin Tureci, Olga Russakovsky
8. Beyond Photorealism: Counterfactual Synthetic Bundles for Invariant Sim-to-Real Vision#206
   Murari Ambati
9. Beyond Raw Signals: Undecoded Generative Latents as Privileged Synthetic Data#207
   Cristian Sbrolli, Nicolas Michel, Matteo Matteucci, Toshihiko Yamasaki
10. Completing Missing Modalities: Synthetic Data for RGB–Infrared–Thermal–Text Person Re-Identification#207
    Muhammad Umair, Muhammad Hammad Musaddiq, Jun Zhou, Ahmad Muhammad
11. CryoDiff: Cryo-EM Synthesis via Biophysics and Cycle-Consistent Diffusion#208
    Genpei Zhang, Yuntian Yang, Siqi Wu, Ningyan Zhang, Seonghui Min, Jie Wu, Christopher Braxton Owens, Minhao Wu, Wanyue Feng, Gus LW Hart, Runmin Jiang, Min Xu
12. Diffusion-Augmented Coreset Expansion for Scalable Dataset Distillation#208
    Ali Abbasi, Shima Imani, Chenyang An, Gayathri Mahalingam, Harsh Shrivastava, Maurice Diesendruck, Hamed Pirsiavash, Pramod Sharma, Soheil Kolouri
13. Disentangled Anatomy-Disease Diffusion (DADD) for Controllable Ulcerative Colitis Progression Synthesis#209
    Umut Dundar, Alptekin Temizel
14. Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer#209
    Hyunsoo Cha, Byungjun Kim, Hanbyul Joo
15. Evaluating the Trade-offs of MDL-to-UsdPreviewSurface Material Simplification in NVIDIA Isaac Sim: Visual Quality, Feature Preservation, and AI Task Performance#210
    Zihou Zhu, Mei Haitao, Haolong Zheng, Zhou Zhang
16. Few-Shot Synthetic Data Generation with Diffusion Models for Downstream Vision Tasks#210
    Daniil Dushenev, Nazariy Karpov, Daniil Zinovjev, Alexander Gorin, Konstantin Kulikov
17. Fréchet Inception Distance is Failing to Preserve Rank Consistency for Synthetic Out-of-Distribution Samples#211
    Linghui Liu, Henrike Stephani, Janis Keuper
18. Generating Synthetic Illumination Variation with Co-Located Relighting#211
    Yash Turkar, Karthik K Dantu
19. Grounding Synthetic Data Generation With Vision and Language Models#212
    Ümit Mert Çağlar, Alptekin Temizel
20. How Far Can We Go With Synthetic Data for Audio-Visual Sound Source Localization?#212
    Arda Senocak, Sooyoung Park, Tae-Hyun Oh, Joon Son Chung
21. Hybrid Rendering for Multimodal Autonomous Driving: Merging Neural and Physics-Based Simulation#213
    Máté Tóth, Péter Kovács, Réka Bencses, Zoltan Bendefy, Zoltan Hortsin, Balázs Teréki, Tamas Matuszka
22. iARCS: Iterative Agentic RL for Controllable 3D Scene Generation#213
    Saugat Adhikari, Ashok Prasad Neupane, Pramish Paudel, Ajad Chhatkuli, Danda Pani Paudel
23. Masked Language Prompting for Generative Data Augmentation in Few-shot Fashion Style Recognition#214
    Yuki Hirakawa, Ryotaro Shimizu
24. Multi-Objective Photoreal Simulation (MOPS) Dataset for Computer Vision in Robot Manipulation#214
    Maximilian Xiling Li, Paul Mattes, Nils Blank, Rudolf Lioutikov
25. Narrowing the Performance Gap in Synthetic VLM Pre-training via Multi-Generator Ensembles#215
    Leonardo Brusini, Cristian Sbrolli, Eugenio Lomurno, Toshihiko Yamasaki, Matteo Matteucci
26. Object-Centric Data Synthesis for Category-level Object Detection#215
    Vikhyat Agarwal, Jiayi Cora Guo, Declan Hoban, Sissi Yuxi Zhang, Nick Moran, Peter Cho, Srilakshmi Pattabiraman, Shantanu H. Joshi
27. One Category One Prompt: Dataset Distillation using Diffusion Models#216
    Ali Abbasi, Ashkan Shahbazi, Hamed Pirsiavash, Soheil Kolouri
28. OrbitArch#216
    I-Ting Tsai, Bharath Hariharan
29. Personalized Generative Models for Contextual Debiasing#217
    Xinran Liang, Esin Tureci, Prachi Sinha, Ye Zhu, Vikram V. Ramaswamy, Olga Russakovsky
30. PLLM: Pseudo-Labeling Large Language Models for CAD Program Synthesis#217
    Yuanbo Li, Dule Shu, Yan-Ying Chen, Matthew Klenk, Daniel Ritchie
31. Privacy-Aware Synthetic Video Benchmarking and Relational Evaluation for Worker-Under-Suspended-Load Detection#218
    Anshu Singh, Alejandro Seif
32. ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL#218
    Mukund Khanna, Raj Singh Yadav, Kunal Singh
33. RareCrafter: Controllable Generative Augmentation for Rare Object Detection in Driving Scenes#219
    Mohadeseh Ghafoori, Danielle Lee, Kurt Hammen, Collin Meese, Mark Nejad
34. Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning#219
    Ido Sobol, Kihyuk Sohn, Yoav Blum, Egor Zakharov, Max Bluvstein, Andrea Vedaldi, Or Litany
35. Representation-Conditioned Diffusion Models for Guided Training Data Generation#220
    Nithesh Chandher Karthikeyan, Jonas Unger, Gabriel Eilertsen
36. Restereo: Unifying diffusion stereo video generation and restoration#220
    Xingchang Huang, Ashish Kumar Singh, Florian Dubost, Cristina Nader Vasconcelos, Sakar Khattar, Liang Shi, Christian Theobalt, Cengiz Oztireli, Gurprit Singh
37. SAIL: Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense Video Captioning#221
    Ye-Chan Kim, SeungJu Cha, Si-Woo Kim, MinJu Jeon, HyunGee Kim, Dong-Jin Kim
38. Scaling Up 3D Forest Vision with Synthetic LiDAR#221
    Yihang She, Andrew Blake, David Coomes, Srinivasan Keshav
39. Sea-Mie: Physically-Based Synthetic Fog for Maritime Image Defogging via Curriculum Learning#222
    Stelios Avlakiotis, Peter Ter Heerdt, Thomas De Kerf, Steve Vanlanduit
40. Sequential Dataset for Satellite Pose Estimation and a Frequency-Space Neural Operator for HIL-Free Generalization Benchmarking#222
    Woojin Cho, Junghwan Park, Steve Andreas Immanuel, Junmin Park, Seokhyun Chin, Jiayun Wang
41. Sim-to-Real Metrology: Calibrated Digital Twins for Fringe Projection Profilometry#223
    NOBLE AUSTINE, Vuppu Eshwar Sai, Vaishnavi Ravi, Madhu S. Nair, Gorthi Rama Krishna Sai Subrahmanyam
42. SJEPA: Joint Embedding Predictive Architecture for Synthetic-to-Real Alignment#223
    Shentong Mo
43. Structure-Consistent Joint Image-Mask Synthesis for Data-Scarce Medical Image Segmentation#224
    Ningyan Zhang, Weiyi Zhang, Mostofa Rafid Uddin, Xingjian Li, Min Xu
44. Structure-retained low-rank adapters for weather synthesis#224
    Shunxin Wang, Alexandros Stergiou, Luuk Spreeuwers, Estefania Talavera, Nicola Strisciuglio
45. StyleText: A Large-Scale Dataset and Benchmark for Stylized Scene Text Inpainting#225
    Aleksandr Simonyan, Nipun Jindal
46. Synthetic Data Generation for Long-Tail Medical Image Classification: A Case Study in Skin Lesions#225
    Jiaxiang Jiang, Mahesh Subedar, Omesh Tickoo
47. Synthetic Designed Experiments for Diagnosing Vision Model Failures#226
    Krisanu Sarkar
48. Theory of Space: Evaluating Active Spatial Belief Construction in Foundation Models with Synthetic 3D Environments#226
    Pingyue Zhang, Zihan Huang, Yue Wang, Jieyu Zhang, Letian Xue, Zihan Wang, Qineng Wang, Keshigeyan Chandrasegaran, Ruohan Zhang, Yejin Choi, Ranjay Krishna, Jiajun Wu, Li Fei-Fei, Manling Li
49. Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision#227
    Hyunsoo Cha, Wonjung Woo, Byungjun Kim, Hanbyul Joo
50. Video-Consistent Synthetic Skiing Trajectories#227
    M'Saydez Campbell, Rémi Emonet, Damien Muselet, Christophe Ducottet
51. WaterGen: Decoupling Scene and Medium in Underwater Image Generation#228
    Jiayi Wu, Tianfu Wang, Tianyi Xiong, Dehao Yuan, Xiaomin Lin, Md Jahidul Islam, Cornelia Fermuller, Christopher Metzler, Yiannis Aloimonos
52. When Does Synthetic Data Help? A Spectral Theory of Task-Relevant Domain Gap with Applications to Guided Generation and Bias Auditing#228
    Kaustubh S. Bukkapatnam, Rayan Malik
53. Why Training with Synthetic Data Fails for OOD: Distribution Gap Amplifies Noise Misalignment in Diffusion Models#229
    Ying Hua, Jessica Bader, Jae Myung Kim, Zeynep Akata
54. WireSeg-32K: A Physics-Grounded Synthetic Dataset for Wire Instance Segmentation#229
    Zilin Dai, Lehong Wang, Yi Yang, Xiang Fei

Call for Papers

We invite submissions on topics related to synthetic data for computer vision, including but not limited to:

• Novel methods for generating synthetic data
• Techniques for bridging the domain gap between synthetic and real data
• Benchmarks and evaluation metrics for synthetic data
• Applications of synthetic data in various computer vision tasks
• Ethical considerations and bias mitigation in synthetic data generation
• Efficient and scalable synthetic data generation pipelines

Submission Guidelines:

• Papers should be formatted according to the CVPR 2026 template
• Short papers: 4 pages (excluding references); Long papers: 8 pages (excluding references)
• Submissions should be made through OpenReview
• All submissions will be double-blind reviewed
• Accepted papers will NOT be included in CVPR proceedings, so there are no double submission concerns.

Important Workshop Dates

• Submission Opens
  February 25, 2026
• Submission Deadline
  March 17, 2026 · 11:59 AM UTC
• Notification
  TBD
• Camera Ready
  TBD
• Workshop Date
  June 4, 2026 · Room 607

Related Workshops

• Synthetic Data for Computer Vision @ CVPR 2025
• Synthetic Data for Computer Vision @ CVPR 2024
• Machine Learning with Synthetic Data @ CVPR 2022
• Synthetic Data for Autonomous Systems @ CVPR 2023
• Synthetic Data Generation with Generative AI @ NeurIPS 2023

Organizers

Jieyu Zhang

University of Washington

Weikai Huang

University of Washington

Zixian Ma

University of Washington

Rundong Luo

Cornell University

Shobhita Sundaram

Massachusetts Institute of Technology

Wei-Chiu Ma

Cornell University

Ranjay Krishna

University of Washington