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/mhabijan/medical_images_generation
공식 코드Generation of Artificial CT Images using Patch-based Conditional Generative Adversarial Networks
https://github.com/miccunifi/EmoVOCA
공식 코드https://github.com/microsoft/AcousticScatteringData
공식 코드Fast acoustic scattering using convolutional neural networks
https://github.com/microsoft/CoCosNet-v2
공식 코드CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation
https://github.com/microsoft/ConfigNet
공식 코드https://github.com/microsoft/DeepSpeed
공식 코드ZeRO: Memory Optimizations Toward Training Trillion Parameter Models
https://github.com/microsoft/DisentangledFaceGAN
공식 코드Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
https://github.com/microsoft/ProDA
공식 코드https://github.com/microsoft/ProphetNet
공식 코드AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation
https://github.com/microsoft/StyleSwin
공식 코드StyleSwin: Transformer-based GAN for High-resolution Image Generation
https://github.com/microsoft/VISOR
공식 코드Benchmarking Spatial Relationships in Text-to-Image Generation
https://github.com/microsoft/dki_llm
공식 코드RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning
https://github.com/microsoft/dpsda
공식 코드Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Model
https://github.com/microsoft/lmops
공식 코드https://github.com/microsoft/nuwa
공식 코드NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis
https://github.com/microsoft/unilm/tree/master/LatentLM
공식 코드Multimodal Latent Language Modeling with Next-Token Diffusion
https://github.com/microsoft/unilm/tree/master/kosmos-g
공식 코드Kosmos-G: Generating Images in Context with Multimodal Large Language Models
https://github.com/microsoft/vq-diffusion
공식 코드https://github.com/mid-push/irwgan
공식 코드Unaligned Image-to-Image Translation by Learning to Reweight
https://github.com/midisec/sccdm
공식 코드Skeleton-Guided Diffusion Model for Accurate Foot X-ray Synthesis in Hallux Valgus Diagnosis
https://github.com/miemieyanga/ResiDualGAN-DRDG
공식 코드ResiDualGAN: Resize-Residual DualGAN for Cross-Domain Remote Sensing Images Semantic Segmentation
https://github.com/migs2021/migs
공식 코드https://github.com/mihirp1998/alignprop
공식 코드Aligning Text-to-Image Diffusion Models with Reward Backpropagation
https://github.com/mikecheninoulu/cgt
공식 코드Geometry-Contrastive Transformer for Generalized 3D Pose Transfer
https://github.com/mikecheninoulu/unsupervised_iepgan
공식 코드Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer
https://github.com/mil-tokyo/FSDDIM
공식 코드https://github.com/mil-tokyo/MCD_DA
공식 코드Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
https://github.com/milad1378yz/motfm
공식 코드Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality
https://github.com/milmor/LadaGAN-pytorch
공식 코드Efficient generative adversarial networks using linear additive-attention Transformers
https://github.com/milmor/ladagan
공식 코드Efficient generative adversarial networks using linear additive-attention Transformers
https://github.com/mindflow-institue/dermosegdiff
공식 코드DermoSegDiff: A Boundary-aware Segmentation Diffusion Model for Skin Lesion Delineation
https://github.com/mindspore-ai/models/tree/master/research/cv/TokenFusion
공식 코드https://github.com/mindspore-lab/mindediting
공식 코드Tunable Convolutions with Parametric Multi-Loss Optimization
https://github.com/ming1993li/instant3dcodes
공식 코드https://github.com/minghangz/resvg
공식 코드ResVG: Enhancing Relation and Semantic Understanding in Multiple Instances for Visual Grounding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.