AI-Generated Images as Data Source: The Dawn of Synthetic Era
cs.CV
Submitted: 2023-10-03
Updated: 2026-11-08
Code: https://github.com/mwxely/AIGS
Terminology
Sources
- DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models
- StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners
- Image retrieval outperforms diffusion models on data augmentation
- ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation
- Machine Learning for Synthetic Data Generation: A Review
- Synthetic Data in Human Analysis: A Survey
- Virtual KITTI 2
- UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World
- Multimodal Image Synthesis and Editing: The Generative AI Era
- GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation
- DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models
- MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation
- Data Augmentation Generative Adversarial Networks
- GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks
- 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
- Generalizable Pose Estimation Using Implicit Scene Representations
- 3D Data Augmentation for Driving Scenes on Camera
- Benchmarking and Analyzing Generative Data for Visual Recognition
- Auto-Encoding Variational Bayes
- TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs