CVPR 2025 Past Computer vision
Synthetic Data for Computer Vision Workshop @ CVPR 2025
SynData4CV
- Submission deadline
- Apr 5, 2025, 00:00 UTC imported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Auto-imported from the OpenReview venue record on 2026-06-10 — please verify and enrich (topics are keyword-guessed).
Accepted papers (63)
Fetched from OpenReview (v2) on 2026-06-10.
-
ACTUPose: Active Curriculum Training for Unsupervised Domain Adaptation in Pose Estimation
-
Analyze, Generate, Improve: Failure-Based Data Generation for Large Multimodal Models
-
Ano-Skin: Clinical Feature-Aware Diffusion Model for Dermatological Image Anonymization
-
Applying Longitudinal Augmentation and Data Generation (LAUGEN) in Medical Imaging
-
Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
-
Ask, Pose, Unite: Scaling Data Acquisition for Close Interaction Meshes with Vision Language Models
-
BLIP3-KALE: Knowledge Augmented Large-Scale Dense Captions
-
Boosting Synthetic Data for VLMs via Diffusion Noise Optimization
-
Bounding Box-Guided Diffusion for Synthesizing Industrial Images and Segmentation Maps
-
BRADD: Balancing Representations with Anomaly Detection and Diffusion
-
Bridging the Domain Gap: Enhancing Underwater Laser Stripe Segmentation with Synthetic Data
-
Buildee: A 3D Simulation Framework for Scene Exploration and Reconstruction with Understanding
-
Challenges in 3D Data Synthesis for Training Neural Networks on Topological Features
-
COMPACT: COMPositional Atomic-to-Complex Visual Capability Tuning
-
Concept-as-Tree: Synthetic Data is All You Need for VLM Personalization
-
Corner Cases: How Size and Position of Objects Challenge ImageNet-Trained Models
-
DemoGen: Synthetic Demonstration Generation for Data-Efficient Visuomotor Policy Learning
-
Diffusion Deepfake
-
DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions
-
DocGenie: A Framework for High-Fidelity Synthetic Document Generation via Seed-Guided Multimodal LLM and Document-Aware Evaluation
-
Does Feasibility Matter? Understanding the Impact of Feasibility on Synthetic Training Data
-
Evaluating Text-to-Image Diffusion Models for Texturing Synthetic Data
-
GASR: Generated Artwork dataset for Image Super-Resolution
-
Generate Any Scene: Evaluating and Improving Text-to-Vision Generation with Scene Graph Programming
-
Generating Synthetic Data via Augmentations for Improved Facial Resemblance in DreamBooth and InstantID
-
Generating Synthetic Stereo Datasets using 3D Gaussian Splatting and Expert Knowledge Transfer
-
GIMO: Generative Image Outpainting for Early Smoke Segmentation
-
H2R: A Human-to-Robot Data Augmentation for Robot Pre-training from Videos
-
Harnessing Diffusion-Generated Synthetic Images for Fair Image Classification
-
Improving Physical Object State Representation in Text-to-Image Generative Systems
-
Instant Particle Size Distribution Measurement Using CNNs Trained on Synthetic Data
-
Investigating the Influence of Image Augmentations on the Sim-to-Real Generalization of Deep Learning Perception Models
-
Investigating the Scaling Effect of Instruction Templates for Training Multimodal Language Model
-
Latent Video Dataset Distillation
-
LATTE: Learning to Reason with Vision Specialists
-
Learning 3D Representations from Procedural 3D Programs
-
Learning from Synthetic Data for Visual Grounding
-
Learning to Blur is Learning to Deblur: Realistic Synthetic UHD Blurred Image via Diffusion
-
Leveraging Automatic CAD Annotations for Supervised Learning in 3D Scene Understanding
-
LFQUIAD: Lookup-Free Quantized autoencoder for few-shot Unsupervised Industrial Anomaly Detection via Synthetic Diffusion Inpainting
-
LiveVQA: Assessing Models with Live Visual Knowledge
-
Minimizing Data, Maximizing Performance: Generative Examples for Continual Task Learning
-
MirrorVerse: Pushing Diffusion Models to Realistically Reflect the World
-
MoireDB: A Formula-driven Image Dataset for Robustness Enhancement
-
MultiRef: Controllable Image Generation with Multiple Visual References
-
Not All Samples Should Be Utilized Equally: Towards Understanding and Improving Dataset Distillation
-
Point Cloud Segmentation of Agricultural Vehicles using 3D Gaussian Splatting
-
Quo Vadis Handwritten Text Generation for Handwritten Text Recognition?
-
R3ST: A Synthetic Dataset with Real Trajectories for Urban Traffic Analysis
-
RAFT: Robust Augmentation of FeaTures for Image Segmentation
-
ReSIT: A more Realistic Synthetic Driving Dataset for Multi-Domain Image-to-Image Translation
-
RoadSocial: A Diverse VideoQA Dataset and Benchmark for Road Event Understanding from Social Video Narratives
-
SDI-Paste: Synthetic Dynamic Instance Copy-Paste
-
Stable Bidirectional Graph Convolutional Networks for Label-Frugal Skeleton-based Recognition
-
SynSHRP2: A Synthetic Multimodal Benchmark for Driving Safety-critical Events Derived from Real-world Driving Data
-
SynTable: A Synthetic Data Generation Pipeline for Unseen Object Amodal Instance Segmentation of Cluttered Tabletop Scenes
-
Synthesizing 3D Abstractions by Inverting Procedural Buildings with Transformers
-
Synthetic Data Generation for Demonstrating Noise Reduction in Facial Depth Imaging
-
Synthetic Generation and Latent Projection Denoising of Rim Lesions in Multiple Sclerosis
-
Synthetic Human Action Video Data Generation with Pose Transfer
-
Synthetically Trained Music-to-Pose Encoder Diffusion for Automated Choreography Generation
-
Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding
-
You Are Your Best Teacher: Semi-Supervised Surgical Point Tracking with Cycle-Consistent Self-Distillation