Awesome-Synthetic-Data-for-Perception-Task

This repository contains a collection of resources and papers on Awesome-Synthetic-Data-for-Perception-Task.

(Source: Virtual kitti 2, DiffuMask)

🖌️ Table of Contents

• Survey
• 3D Virtual Engine
• Classification Task
• Face Recognition
• Scene Text Detection & Recognition
• Semantic Segmentation
• Instance Segmentation
• Object Detection
• 3D Human Pose
• Pose
• Depth Estimation Task
• Open Pose Task
• Referring Segmentation Task
• Medical Image

Survey

• A survey on generative adversarial networks for imbalance problems in computer vision tasks(Journal of Big Data 2021)

Classification Task

• Training on Thin Air: Improve Image Classification with Generated Data(May 2023)

• Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation(May 2023)

• Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion(IJCAI 2022)

• RareGAN: Generating Samples for Rare Classes(AAAI 2022)

• Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder(TPAMI 2022)

• Deep Generative Mixture Model for Robust Imbalance Classification(TPAMI 2022)

• Do Deep Networks Transfer Invariances Across Classes?(ICLR 2022)

• BAGAN: Data Augmentation with Balancing GAN(Mar 2018)

• Deep Synthetic Noise Generation for RGB-D Data Augmentation(Mar 2019)

• Efficient Augmentation for Imbalanced Deep Learning(Mon, 2022)

• A data augmentation perspective on diffusion models and retrieva(Apr, 2023)

• Synthetic Data from Diffusion Models Improves ImageNet Classification(Apr, 2023)

• Is synthetic data from generative models ready for image recognition?(ICLR 2023, Spotlight)

• Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable Diffusion(Apr 2023)

• Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels(Apr 2023)

• Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable Diffusion(Apr 2023)

• Exploring Incompatible Knowledge Transfer in Few-shot Image Generation(CVPR 2023)

• Accelerating dataset distillation via model augmentation(December 2022)

3D Human Pose

• Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial Sports Field Registration(CVPR 2023) []

Semantic Segmentation

• DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models(Mar 2023)

• Guiding Text-to-Image Diffusion Model Towards Grounded Generation(Jan 2023) []

• HandsOff: Labeled Dataset Generation With No Additional Human Annotations(NeurIPS 2022 Workshop)

• DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort(CVPR 2021 oral) []

Instance Segmentation

• BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations(CVPR 2022)

Object Detection

• CrowdSim2: an Open Synthetic Benchmark for Object Detectors(the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2023)

• X-Paste: Revisit Copy-Paste at Scale with CLIP and StableDiffusion(Dec, 2022)

• DALL-E for Detection: Language-driven Compositional Image Synthesis for Object Detection(Dec, 2022)

• Neural-Sim: Learning to Generate Training Data with NeRF(ECCV, 2022)

• EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance Segmentation(Dec, 2022)

Face Recognition

• DCFace: Synthetic Face Generation with Dual Condition Diffusion Model(CVPR 2023) []

• SynthASpoof: Developing Face Presentation Attack Detection Based on Privacy-friendly Synthetic Data(CVPR 2023 workshop)

Instance Segmentation

• HaDR: Applying Domain Randomization for Generating Synthetic Multimodal Dataset for Hand Instance Segmentation in Cluttered Industrial Environments(April 2023)

3D Virtual Engine

• Virtual kitti 2(Apr., 2023)
  

Medical Image

• Brain PET Synthesis from MRI Using Joint Probability Distribution of Diffusion Model at Ultrahigh Fields(November 2022)

• Distributed Conditional GAN (discGAN) For Synthetic Healthcare Data Generation(April 2023)

• MedGen3D: A Deep Generative Framework for Paired 3D Image and Mask Generation(MICCAI 2023)

• Zero-shot CT Field-of-view Completion with Unconditional Generative Diffusion Prior(MIDL 2023)

Pose

• Pose Augmentation: Class-agnostic Object Pose Transformation for Object Recognition(ECCV 2020)

• StyleGAN-Human: A Data-Centric Odyssey of Human Generation(ECCV 2020)

🖌️ Others for Diffusion Model

• Image Generation
• 3D Generation
• 3D Editing
• Reinforcement Learning with Human Feedback
• Conditional Generation

3D Editing

• SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fields(CVPR 2022)

Reinforcement Learning with Human Feedback

• Better Aligning Text-to-Image Models with Human Preference(Mar 2023)

• RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment(Apr 2023)

• Aligning Text-to-Image Models using Human Feedback(Apr 2023)

• ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation(Thu 2023)

Conditional Generation

• MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation(ICML 2023)