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/tigvarts/ucm
공식 코드https://github.com/tigvarts/vaeac
공식 코드https://github.com/tiktok/fast_prompt_alignment
공식 코드https://github.com/tillmannohm/fruit-SALAD
공식 코드fruit-SALAD: A Style Aligned Artwork Dataset to reveal similarity perception in image embeddings
https://github.com/timcjanke/igc
공식 코드https://github.com/timothybrooks/instruct-pix2pix
공식 코드InstructPix2Pix: Learning to Follow Image Editing Instructions
https://github.com/tinysqua/uwafa-gan
공식 코드https://github.com/tirer-lab/cm4ir
공식 코드Zero-Shot Image Restoration Using Few-Step Guidance of Consistency Models (and Beyond)
https://github.com/tirthajit/LoRAE_WACV24
공식 코드https://github.com/tkarras/progressive_growing_of_gans
공식 코드Progressive Growing of GANs for Improved Quality, Stability, and Variation
https://github.com/tldrafael/facereconstructionwithvaeandfacemasks
공식 코드Face Reconstruction with Variational Autoencoder and Face Masks
https://github.com/tmilne5/trust-the-critics
공식 코드Trust the Critics: Generatorless and Multipurpose WGANs with Initial Convergence Guarantees
https://github.com/tml-tuebingen/pags
공식 코드Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness
https://github.com/tntrung/gan
공식 코드https://github.com/tntrung/msgan
공식 코드Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Game
https://github.com/tobran/DF-GAN
공식 코드DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis
https://github.com/tobran/de-net
공식 코드DE-Net: Dynamic Text-guided Image Editing Adversarial Networks
https://github.com/tobran/galip
공식 코드GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis
https://github.com/tobran/storyimager
공식 코드StoryImager: A Unified and Efficient Framework for Coherent Story Visualization and Completion
https://github.com/tobyclh/microglam
공식 코드https://github.com/tohinz/ConSinGAN
공식 코드https://github.com/tohinz/multiple-objects-gan
공식 코드https://github.com/tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis
공식 코드Semantic Object Accuracy for Generative Text-to-Image Synthesis
https://github.com/tokeron/lens
공식 코드Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models
https://github.com/tom919654/C3G-NeRF
공식 코드Class-Continuous Conditional Generative Neural Radiance Field
https://github.com/tomeramit/SegDiff
공식 코드SegDiff: Image Segmentation with Diffusion Probabilistic Models
https://github.com/tommy-bie/mica
공식 코드MICA: Towards Explainable Skin Lesion Diagnosis via Multi-Level Image-Concept Alignment
https://github.com/tomtirer/IDBP
공식 코드Image Restoration by Iterative Denoising and Backward Projections
https://github.com/tomtom1103/compose-and-conquer
공식 코드Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image Synthesis
https://github.com/top34051/colorswap
공식 코드ColorSwap: A Color and Word Order Dataset for Multimodal Evaluation
https://github.com/torchddm/ddm
공식 코드Diffusion Deformable Model for 4D Temporal Medical Image Generation
https://github.com/torchgan/torchgan
공식 코드TorchGAN: A Flexible Framework for GAN Training and Evaluation
https://github.com/torchrwkv/flash-linear-attention
공식 코드https://github.com/toshas/sttp
공식 코드Spectral Tensor Train Parameterization of Deep Learning Layers
https://github.com/tothebeginning/pulid
공식 코드PuLID: Pure and Lightning ID Customization via Contrastive Alignment
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.