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/yueming6568/deltaedit
공식 코드DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation
https://github.com/yueyang1996/z-lavi
공식 코드Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination
https://github.com/yuhuayc/da-faster-rcnn
공식 코드Domain Adaptive Faster R-CNN for Object Detection in the Wild
https://github.com/yuhui-zh15/c3
공식 코드Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data
https://github.com/yuhuustc/debias
공식 코드https://github.com/yujielu10/llmscore
공식 코드LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation
https://github.com/yujielu10/mpp
공식 코드Multimodal Procedural Planning via Dual Text-Image Prompting
https://github.com/yumingj/Text2Human
공식 코드https://github.com/yumingj/deepfashion-multimodal
공식 코드https://github.com/yunqing-me/AdAM
공식 코드Few-shot Image Generation via Adaptation-Aware Kernel Modulation
https://github.com/yunyanxing/pairwise_xray_augmentation
공식 코드Adversarial Pulmonary Pathology Translation for Pairwise Chest X-ray Data Augmentation
https://github.com/yunyikristy/skipNet
공식 코드Unpaired Image-to-Speech Synthesis with Multimodal Information Bottleneck
https://github.com/yuqiao0303/pointdreamer
공식 코드PointDreamer: Zero-shot 3D Textured Mesh Reconstruction from Colored Point Cloud
https://github.com/yuqifan1117/labal-anything-pipeline
공식 코드Interactive Data Synthesis for Systematic Vision Adaptation via LLMs-AIGCs Collaboration
https://github.com/yutong-zhou-cv/awesome-text-to-image
공식 코드https://github.com/yuval-alaluf/SAM
공식 코드Only a Matter of Style: Age Transformation Using a Style-Based Regression Model
https://github.com/yuval-alaluf/restyle-encoder
공식 코드ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement
https://github.com/yuval-alaluf/stylegan3-editing
공식 코드Third Time's the Charm? Image and Video Editing with StyleGAN3
https://github.com/yuvalkirstain/pickscore
공식 코드Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation
https://github.com/yuxie11/R2D2
공식 코드https://github.com/yuxinn-j/scenimefy
공식 코드Scenimefy: Learning to Craft Anime Scene via Semi-Supervised Image-to-Image Translation
https://github.com/yuxinwenrick/diffusion_memorization
공식 코드Detecting, Explaining, and Mitigating Memorization in Diffusion Models
https://github.com/yuyangxueed/reconunlearning
공식 코드Erase to Enhance: Data-Efficient Machine Unlearning in MRI Reconstruction
https://github.com/yuzhenyulindy/yuan
공식 코드https://github.com/yxgong0/STIG
공식 코드https://github.com/yxymessi/dtc123
공식 코드Diffusion Time-step Curriculum for One Image to 3D Generation
https://github.com/yylgoodlucky/hdtr
공식 코드https://github.com/yymgch/cycle-chaos-gan
공식 코드https://github.com/yzou2/CBST
공식 코드Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training
https://github.com/yzou2/CRST
공식 코드https://github.com/z-fabian/dirac-diffusion
공식 코드DiracDiffusion: Denoising and Incremental Reconstruction with Assured Data-Consistency
https://github.com/z-fabian/flash-diffusion
공식 코드Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models
https://github.com/z-x-yang/NS-Outpainting
공식 코드https://github.com/zaiweizhang/Joint-Learning-of-NN
공식 코드Joint Learning of Neural Networks via Iterative Reweighted Least Squares
https://github.com/zalandoresearch/first_order_gan
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.