Papers with Code 아카이브
Image Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 23
- 평가표
- 93
- 보존된 평가 기록
- 870
Image Generation (synthesis) is the task of generating new images from an existing dataset.
- Unconditional generation refers to generating samples unconditionally from the dataset, i.e. $p(y)$
- Conditional image generation (subtask) refers to generating samples conditionally from the dataset, based on a label, i.e. $p(y|x)$.
In this section, you can find state-of-the-art leaderboards for unconditional generation. For conditional generation, and other types of image generations, refer to the subtasks.
<span style="color:grey; opacity: 0.6">( Image credit: StyleGAN )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/ai-forever/ruscode
공식 코드RusCode: Russian Cultural Code Benchmark for Text-to-Image Generation
https://github.com/ai-med/stablepose
공식 코드Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation
https://github.com/ai4science-westlakeu/flow_guidance
공식 코드https://github.com/aiart-hdu/matebit
공식 코드Masked and Adaptive Transformer for Exemplar Based Image Translation
https://github.com/aiart-hdu/sage
공식 코드https://github.com/aidc-ai/awesome-unified-multimodal-models
공식 코드Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities
https://github.com/aidc-ai/ovis-u1
공식 코드https://github.com/aigagror/wasserstein-style-transfer
공식 코드https://github.com/aigc-apps/easyanimate
공식 코드EasyAnimate: A High-Performance Long Video Generation Method based on Transformer Architecture
https://github.com/aihao2000/stable-diffusion-reference-only
공식 코드https://github.com/aiiu-lab/DemonSampling
공식 코드Training-free Diffusion Model Alignment with Sampling Demons
https://github.com/aiiu-lab/backdoorimageediting
공식 코드Invisible Backdoor Triggers in Image Editing Model via Deep Watermarking
https://github.com/aiiu-lab/blenda
공식 코드BlenDA: Domain Adaptive Object Detection through diffusion-based blending
https://github.com/ailab-cvc/seed
공식 코드https://github.com/ailab-cvc/seed-bench
공식 코드https://github.com/ailab-cvc/seed-x
공식 코드SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation
https://github.com/ailab-cvc/vl-gpt
공식 코드VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation
https://github.com/aim-uofa/AutoStory
공식 코드AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort
https://github.com/aim-uofa/Diception
공식 코드DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks
https://github.com/aim-uofa/FreeCompose
공식 코드FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior
https://github.com/aim-uofa/diffews
공식 코드Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation
https://github.com/aim-uofa/freecustom
공식 코드FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition
https://github.com/aimagelab/alfie
공식 코드https://github.com/aimagelab/art2real
공식 코드Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-to-Image Translation
https://github.com/aimagelab/hwd
공식 코드HWD: A Novel Evaluation Score for Styled Handwritten Text Generation
https://github.com/aimagelab/mad
공식 코드Merging and Splitting Diffusion Paths for Semantically Coherent Panoramas
https://github.com/aimagelab/safe-clip
공식 코드Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models
https://github.com/aimagelab/unveiling-the-truth
공식 코드Unveiling the Truth: Exploring Human Gaze Patterns in Fake Images
https://github.com/aircarlo/bin2bin-gan-plc
공식 코드A Time-Frequency Generative Adversarial based method for Audio Packet Loss Concealment
https://github.com/airi-institute/styledomain
공식 코드https://github.com/ajayjain/lmconv
공식 코드https://github.com/ajbrock/Neural-Photo-Editor
공식 코드Neural Photo Editing with Introspective Adversarial Networks
https://github.com/ajiljalal/code-cs-fairness
공식 코드Fairness for Image Generation with Uncertain Sensitive Attributes
https://github.com/ajrheng/fdrl
공식 코드https://github.com/ajsvb/rl_path_tracing
공식 코드RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.