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/mowenyii/uniform-attention-maps
공식 코드Uniform Attention Maps: Boosting Image Fidelity in Reconstruction and Editing
https://github.com/mozhdehrouhsedaghat/magic
공식 코드MAGIC: Mask-Guided Image Synthesis by Inverting a Quasi-Robust Classifier
https://github.com/mpatacchiola/Y-AE
공식 코드Y-Autoencoders: disentangling latent representations via sequential-encoding
https://github.com/mprzewie/dmfa_inpainting
공식 코드https://github.com/mrlibw/ControlGAN
공식 코드https://github.com/mrlibw/ManiGAN
공식 코드https://github.com/ms-synthetic-satellite-image/synthetic-satellite-imagery
공식 코드https://github.com/mshahbazi72/cGANTransfer
공식 코드Efficient Conditional GAN Transfer with Knowledge Propagation across Classes
https://github.com/mshahbazi72/nerf-gan-distillation
공식 코드NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutions
https://github.com/mshaikh2/MMRL
공식 코드https://github.com/mshenoda/diffugen
공식 코드DiffuGen: Adaptable Approach for Generating Labeled Image Datasets using Stable Diffusion Models
https://github.com/msseibel/accut
공식 코드https://github.com/msu-video-group/msu_vqm_compression_benchmark
공식 코드AIM 2024 Challenge on Compressed Video Quality Assessment: Methods and Results
https://github.com/mti-lab/HF-ADB
공식 코드High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image Synthesis
https://github.com/mtkresearch/latent-flow-transformer
공식 코드https://github.com/mtkresearch/shortest-path-diffusion
공식 코드https://github.com/mu-cai/frequency-domain-image-translation
공식 코드Frequency Domain Image Translation: More Photo-realistic, Better Identity-preserving
https://github.com/mu-cai/frl
공식 코드Out-of-distribution Detection via Frequency-regularized Generative Models
https://github.com/mueller-franzes/medfusion
공식 코드https://github.com/mukulkhanna/fhdr
공식 코드FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network
https://github.com/murray-wang/characonsist
공식 코드https://github.com/musikisomorphie/swd
공식 코드https://github.com/muzishen/imagdressing
공식 코드https://github.com/mv-lab/AISP
공식 코드Model-Based Image Signal Processors via Learnable Dictionaries
https://github.com/mvrl/geosynth
공식 코드GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesis
https://github.com/mwbini/ether
공식 코드ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections
https://github.com/mycfhs/dreammix
공식 코드DreamMix: Decoupling Object Attributes for Enhanced Editability in Customized Image Inpainting
https://github.com/nachifur/rddm
공식 코드https://github.com/nadeemlab/CEP
공식 코드Visualizing Missing Surfaces In Colonoscopy Videos using Shared Latent Space Representations
https://github.com/nahyeonkaty/textboost
공식 코드TextBoost: Towards One-Shot Personalization of Text-to-Image Models via Fine-tuning Text Encoder
https://github.com/naiq/PN_GAN
공식 코드Pose-Normalized Image Generation for Person Re-identification
https://github.com/namecantbenull/srudc
공식 코드Under-Display Camera Image Restoration with Scattering Effect
https://github.com/nanboy-ronan/backdoor-fedgan
공식 코드Backdoor Attack is a Devil in Federated GAN-based Medical Image Synthesis
https://github.com/nanjingxiaobawang/SieNet-Image-extrapolation
공식 코드https://github.com/nannanli999/airr
공식 코드Supervised Attribute Information Removal and Reconstruction for Image Manipulation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.