https://github.com/boschresearch/OASIS
공식 코드You Only Need Adversarial Supervision for Semantic Image Synthesis
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/boschresearch/PA-GAN
공식 코드https://github.com/boschresearch/aldm
공식 코드Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive
https://github.com/boschresearch/one-shot-synthesis
공식 코드Generating Novel Scene Compositions from Single Images and Videos
https://github.com/boschresearch/unetgan
공식 코드A U-Net Based Discriminator for Generative Adversarial Networks
https://github.com/boyiliee/sitta
공식 코드SITTA: Single Image Texture Translation for Data Augmentation
https://github.com/brain-research/self-attention-gan
공식 코드https://github.com/brambozz/medical-diffusion-on-a-budget
공식 코드Medical diffusion on a budget: Textual Inversion for medical image generation
https://github.com/breezeyuner/diffcdr
공식 코드https://github.com/brinnaebent/semantic-consistency-score
공식 코드Semantic Approach to Quantifying the Consistency of Diffusion Model Image Generation
https://github.com/brownvc/ganimorph
공식 코드Improving Shape Deformation in Unsupervised Image-to-Image Translation
https://github.com/brownvc/r3gan
공식 코드https://github.com/buaacyw/it3d-text-to-3d
공식 코드IT3D: Improved Text-to-3D Generation with Explicit View Synthesis
https://github.com/buds-lab/filling-time-series-gaps-using-image-techniques
공식 코드https://github.com/budui/Control-Units-in-StyleGAN2
공식 코드Attribute-specific Control Units in StyleGAN for Fine-grained Image Manipulation
https://github.com/buggyyang/rvd
공식 코드https://github.com/bupt-ai-cz/BCI
공식 코드BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pix
https://github.com/bupt-ai-cz/IAST-ECCV2020
공식 코드Instance Adaptive Self-Training for Unsupervised Domain Adaptation
https://github.com/bupt-ai-cz/LLVIP
공식 코드LLVIP: A Visible-infrared Paired Dataset for Low-light Vision
https://github.com/bupt-ai-cz/hiast
공식 코드Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation
https://github.com/buxiangzhiren/asymmetric_vqgan
공식 코드https://github.com/buxiangzhiren/ddcap
공식 코드https://github.com/bw-park/DBFS
공식 코드Stochastic Optimal Control for Diffusion Bridges in Function Spaces
https://github.com/byeonghu-na/INDM
공식 코드Maximum Likelihood Training of Implicit Nonlinear Diffusion Models
https://github.com/byeongjun-park/HarmonyView
공식 코드HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D
https://github.com/byliutao/1prompt1story
공식 코드One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt
https://github.com/bytedance/1d-tokenizer
공식 코드An Image is Worth 32 Tokens for Reconstruction and Generation
https://github.com/bytedance/GR-MG
공식 코드GR-MG: Leveraging Partially Annotated Data via Multi-Modal Goal-Conditioned Policy
https://github.com/bytedance/MoMA
공식 코드MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation
https://github.com/bytedance/infiniteyou
공식 코드InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
https://github.com/bytedance/latentunfold
공식 코드Flux Already Knows -- Activating Subject-Driven Image Generation without Training
https://github.com/bytedance/res-adapter
공식 코드ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models
https://github.com/bytedance/uno
공식 코드Less-to-More Generalization: Unlocking More Controllability by In-Context Generation
https://github.com/bytedance/xverse
공식 코드XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation
https://github.com/byteflow-ai/detailflow
공식 코드DetailFlow: 1D Coarse-to-Fine Autoregressive Image Generation via Next-Detail Prediction
https://github.com/c-he/perm
공식 코드Perm: A Parametric Representation for Multi-Style 3D Hair Modeling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.