Home

Awesome

Guided Image-to-Image Translation papers

Feel free to send a PR or issue. (constantly updating)

Class Label Guided

ModelPaperConferenceArxivCode
IcGANInvertible Conditional GANs for image editingNeurIPSW 20161611.06355Guim3/IcGAN
Conditional CycleGANConditional CycleGAN for Attribute Guided Face Image GenerationECCV 20181705.09966
StarGANStarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image TranslationCVPR 20181711.09020yunjey/StarGAN
AGUITAttribute Guided Unpaired Image-to-Image Translation with Semi-supervised Learning1904.12428imlixinyang/AGUIT
AttGANAttGAN: Facial Attribute Editing by Only Changing What You WantTIP 20191711.10678LynnHo/AttGAN-Tensorflow
SGGANSparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute ManipulationMM 20181805.07509zhangqianhui/Sparsely-Grouped-GAN
RelGANRelGAN: Multi-Domain Image-to-Image Translation via Relative AttributesICCV 20191908.07269elvisyjlin/RelGAN-PyTorch, willylulu/RelGAN

Action Unit Guided

ModelPaperConferenceArxivCode
GANimationGANimation: Anatomically-aware Facial Animation from a Single ImageECCV 20181807.09251albertpumarola/GANimation

Facial Landmark Guided

ModelPaperConferenceArxivCode
G2GANGeometry Guided Adversarial Facial Expression SynthesisMM 20181712.03474
CMM-NetEvery Smile is Unique: Landmark-Guided Diverse Smile GenerationCVPR 20181802.01873
C2GANCycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image GenerationMM 20191908.00999Ha0Tang/C2GAN
Few-Shot Adversarial Learning of Realistic Neural Talking Head ModelsICCV 20191905.08233grey-eye/talking-heads

Pose Guided Person Image Generation

ModelPaperConferenceArxivCode
PG2Pose Guided Person Image GenerationNeurIPS 20171705.09368charliememory/Pose-Guided-Person-Image-Generation
PoseGANDeformable GANs for Pose-Based Human Image GenerationCVPR 20181801.00055AliaksandrSiarohin/pose-gan
VUnetA Variational U-Net for Conditional Appearance and Shape GenerationCVPR 20181804.04694CompVis/vunet
PoseWarpSynthesizing Images of Humans in Unseen PosesCVPR 20181804.07739posewarp-cvpr2018
DPIGDisentangled Person Image GenerationCVPR 20181712.02621charliememory/Disentangled-Person-Image-Generation
FD-GANFD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identificationNeurIPS 20181810.02936yxgeee/FD-GAN
PN-GANPose-Normalized Image Generation for Person Re-identificationECCV 20181712.02225naiq/PN_GAN
GestureGANGestureGAN for Hand Gesture-to-Gesture Translation in the WildMM 20181808.04859Ha0Tang/GestureGAN
PATNProgressive Pose Attention for Person Image GenerationCVPR 20191904.03349tengteng95/Pose-Transfer
SPTUnsupervised Person Image Generation with Semantic Parsing TransformationCVPR 20191904.03379SijieSong/person_generation_spt
Coordinate-based Texture Inpainting for Pose-Guided Human Image GenerationCVPR 20191811.11459project
IntrinsicFlowDense intrinsic appearance flow for human pose transferCVPR 20191903.11326ly015/intrinsic_flow
TriangleGANGesture-to-Gesture Translation in the Wild via Category-Independent Conditional MapsMM 20191907.05916yhlleo/TriangleGAN
Pix2pixHD + Temporal Smoothing + FaceGANEverybody Dance NowICCV 20191808.07371project
LiquidWarpingGANLiquid warping gan: A unified framework for human motion imitation, appearance transfer and novel view synthesisICCV 20191909.12224svip-lab/impersonator
Global-Flow-Local-AttentionDeep Image Spatial Transformation for Person Image GenerationCVPR 20202003.00696RenYurui/Global-Flow-Local-Attention
ADGANControllable Person Image Synthesis With Attribute-Decomposed GANCVPR 20202003.12267menyifang/ADGAN
CoCosNetCross-domain Correspondence Learning for Exemplar-based Image TranslationCVPR 20202004.05571microsoft/CoCosNet
SMISSemantically Multi-modal Image SynthesisCVPR 20202003.12697Seanseattle/SMIS
MISCMISC: Multi-Condition Injection and Spatially-Adaptive Compositing for Conditional Person Image SynthesisCVPR 2020cvpr20
Warp3d_ReposingReposing Humans by Warping 3D FeaturesCVPR 2020 Workshop2006.04898MKnoche/warp3d_reposing
Wish You Were Here: Context-Aware Human GenerationCVPR 20202005.10663
PoseStylizerGenerating Person Images with Appearance-aware Pose StylizerIJCAI 20202007.09077siyuhuang/PoseStylizer
XingGANXingGAN for Person Image GenerationECCV 20202007.09278Ha0Tang/XingGAN

Segmentation Map Guided Scene Image Generation

ModelPaperConferenceArxivCode
CRNPhotographic Image Synthesis with Cascaded Refinement NetworksICCV 20171707.09405CQFIO/PhotographicImageSynthesis
CrossNetPredicting Ground-Level Scene Layout from Aerial ImageryCVPR 20171612.02709viibridges/crossnet
SIMSSemi-parametric Image SynthesisCVPR 20181804.10992xjqicuhk/SIMS
Pix2PixHDHigh-Resolution Image Synthesis and Semantic Manipulation with Conditional GANsCVPR 20181711.11585NVIDIA/pix2pixHD
X-Fork & X-SeqCross-View Image Synthesis using Conditional GANsCVPR 20181803.03396kregmi/cross-view-image-synthesis
Vid2VidVideo-to-Video SynthesisNeurIPS 20181808.06601NVIDIA/vid2vid
SPADESemantic Image Synthesis with Spatially-Adaptive NormalizationCVPR 20191903.07291NVlabs/SPADE
SelectionGANMulti-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image TranslationCVPR 20191904.06807Ha0Tang/SelectionGAN
Art2RealArt2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-to-Image TranslationCVPR 20191811.10666aimagelab/art2real
Mask-Guided Portrait Editing with Conditional GANsCVPR 20191905.10346cientgu/Mask_Guided_Portrait_Editing
Seg2VidVideo Generation from Single Semantic Label MapCVPR 20191903.04480junting/seg2vid
Semantic Bottleneck Scene Generation1911.11357
Few-shot Vid2VidFew-shot Video-to-Video SynthesisNeurIPS 20191910.12713NVlabs/few-shot-vid2vid
CC-FPSELearning to Predict Layout-to-image Conditional Convolutions for Semantic Image SynthesisNeurIPS 20191910.06809xh-liu/CC-FPSE
SEANSEAN: Image Synthesis with Semantic Region-Adaptive NormalizationCVPR 20201911.12861ZPdesu/SEAN
BachGANBachGAN: High-Resolution Image Synthesis from Salient Object LayoutCVPR 20202003.11690Cold-Winter/BachGAN
Panoptic-based Image SynthesisCVPR 20202004.10289
SMISSemantically Multi-modal Image SynthesisCVPR 20202003.12697Seanseattle/SMIS
GAN CompressionGAN Compression: Efficient Architectures for Interactive Conditional GANsCVPR 20202003.08936mit-han-lab/gan-compression
LGGANLocal Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene GenerationCVPR 20201912.12215Ha0Tang/LGGAN
TSITTSIT: A Simple and Versatile Framework for Image-to-Image TranslationECCV 20202007.12072EndlessSora/TSIT
SegVAEControllable Image Synthesis via SegVAEECCV 20202007.08397yccyenchicheng/SegVAE
SESAMESESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing ObjectsECCV 20202004.04977
Style SemanticsControlling Style and Semantics in Weakly-Supervised Image GenerationECCV 20201912.03161dariopavllo/style-semantics

Texture Patch Guided

ModelPaperConferenceArxivCode
TextureGANTextureGAN: Controlling Deep Image Synthesis with Texture PatchesCVPR 20181706.02823janesjanes/Pytorch-TextureGAN
Guided-pix2pixGuided Image-to-Image Translation with Bi-Directional Feature TransformationICCV 20191910.11328vt-vl-lab/Guided-pix2pix

Example Guided

ModelPaperConferenceArxivCode
EG-UNITExemplar Guided Unsupervised Image-to-Image TranslationICLR 20191805.11145charliememory/EGSC-IT
Pix2pixSCExample-Guided Style-Consistent Image Synthesis from Semantic LabelingCVPR 20191906.01314cxjyxxme/pix2pixSC

Attention Guided

ModelPaperConferenceArxivCode
DA-GANDA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial NetworksCVPR 20181802.06454
Attention-GANAttention-GAN for Object Transfiguration in Wild ImagesECCV 20181803.06798
UAITUnsupervised Attention-guided Image to Image TranslationNeurIPS 20181806.02311AlamiMejjati/Unsupervised-Attention-guided-Image-to-Image-Translation
Show, Attend and Translate: Unsupervised Image Translation with Self-Regularization and AttentionTIP 20191806.06195
AttentionGANAttention-Guided Generative Adversarial Networks for Unsupervised Image-to-Image TranslationIJCNN 20191903.12296Ha0Tang/AttentionGAN
U-GAT-ITU-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image TranslationICLR 20201907.10830taki0112/UGATIT, znxlwm/UGATIT-pytorch

Mask Guided

ModelPaperConferenceArxivCode
ContrastGANGenerative Semantic Manipulation with Mask-Contrasting GANECCV 20181708.00315
InstaGANInstance-aware image-to-image translationICLR 20191812.10889sangwoomo/instagan
INITTowards Instance-level Image-to-Image TranslationCVPR 20191905.01744project

Text Guided

ModelPaperConferenceArxivCode
ControlGANControllable Text-to-Image GenerationNeurIPS 20191909.07083mrlibw/ControlGAN
DMITMulti-mapping Image-to-Image Translation via Learning DisentanglementNeurIPS 20191909.07877Xiaoming-Yu/DMIT
ManiGANManiGAN: Text-Guided Image Manipulation1912.06203
RefinedGANImage-to-Image Translation with Text Guidance2002.05235

Audio Guided

ModelPaperConferenceArxivCode
X2FaceX2Face: A Network for Controlling Face Generation using Images, Audio, and Pose CodesECCV 20181807.10550oawiles/X2Face