{"total":296,"rows":[{"id":"2302.03027","title":"Zero-shot Image-to-Image Translation","created":"2023-02-06","cited_by_count":505,"area":null},{"id":"2303.05511","title":"Scaling up GANs for Text-to-Image Synthesis","created":"2023-03-09","cited_by_count":492,"area":null},{"id":"2101.05278","title":"GAN Inversion: A Survey","created":"2021-01-14","cited_by_count":367,"area":null},{"id":"2103.15597","title":"RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening","created":"2021-03-29","cited_by_count":215,"area":null},{"id":"2104.07452","title":"Audio-Driven Emotional Video Portraits","created":"2021-04-15","cited_by_count":180,"area":null},{"id":"2207.06635","title":"EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations","created":"2022-07-14","cited_by_count":172,"area":"diffusion"},{"id":"2307.14126","title":"Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling","created":"2023-07-26","cited_by_count":163,"area":null},{"id":"2308.07863","title":"StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models","created":"2023-08-15","cited_by_count":155,"area":"diffusion"},{"id":"2104.05358","title":"UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models","created":"2021-04-12","cited_by_count":133,"area":"diffusion"},{"id":"2207.00050","title":"Semantic Image Synthesis via Diffusion Models","created":"2022-06-30","cited_by_count":132,"area":"diffusion"},{"id":"2111.15246","title":"Hallucinated Neural Radiance Fields in the Wild","created":"2021-11-30","cited_by_count":130,"area":null},{"id":"2107.01372","title":"Learning Debiased Representation via Disentangled Feature Augmentation","created":"2021-07-03","cited_by_count":116,"area":null},{"id":"2403.12036","title":"One-Step Image Translation with Text-to-Image Models","created":"2024-03-18","cited_by_count":116,"area":"diffusion"},{"id":"2211.11695","title":"Disentangled Representation Learning","created":"2022-11-21","cited_by_count":112,"area":null},{"id":"2205.01491","title":"A Comprehensive Survey of Image Augmentation Techniques for Deep Learning","created":"2022-05-03","cited_by_count":97,"area":null},{"id":"2305.03374","title":"DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generation","created":"2023-05-05","cited_by_count":75,"area":null},{"id":"2105.04619","title":"Enhancing Photorealism Enhancement","created":"2021-05-10","cited_by_count":74,"area":null},{"id":"2104.07689","title":"Dual Contrastive Learning for Unsupervised Image-to-Image Translation","created":"2021-04-15","cited_by_count":66,"area":null},{"id":"2204.12997","title":"DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers","created":"2022-04-27","cited_by_count":65,"area":"distill"},{"id":"2105.09188","title":"High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network","created":"2021-05-19","cited_by_count":61,"area":null},{"id":"2104.00675","title":"In&Out : Diverse Image Outpainting via GAN Inversion","created":"2021-04-01","cited_by_count":55,"area":null},{"id":"2203.04121","title":"Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment","created":"2022-03-06","cited_by_count":54,"area":null},{"id":"2111.06849","title":"Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data","created":"2021-11-12","cited_by_count":53,"area":null},{"id":"2203.09065","title":"STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset","created":"2022-03-17","cited_by_count":53,"area":null},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2303.17132","title":"C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation","created":"2023-03-30","cited_by_count":50,"area":null},{"id":"2108.06685","title":"Vector-Decomposed Disentanglement for Domain-Invariant Object Detection","created":"2021-08-15","cited_by_count":47,"area":null},{"id":"2110.11728","title":"BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation","created":"2021-10-22","cited_by_count":47,"area":null},{"id":"2207.02127","title":"A survey of multimodal deep generative models","created":"2022-07-05","cited_by_count":47,"area":null},{"id":"2101.00588","title":"Style Normalization and Restitution for Domain Generalization and Adaptation","created":"2021-01-03","cited_by_count":46,"area":null},{"id":"2108.12043","title":"Learning Disentangled Representations in the Imaging Domain","created":"2021-08-26","cited_by_count":46,"area":null},{"id":"2207.04808","title":"CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer","created":"2022-07-11","cited_by_count":46,"area":null},{"id":"2104.12753","title":"Vision Transformers with Patch Diversification","created":"2021-04-26","cited_by_count":45,"area":null},{"id":"2108.04547","title":"Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation","created":"2021-08-10","cited_by_count":45,"area":null},{"id":"2109.06166","title":"Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN","created":"2021-09-13","cited_by_count":45,"area":null},{"id":"2203.02557","title":"UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation","created":"2022-03-04","cited_by_count":42,"area":null},{"id":"2208.12675","title":"Adaptively-Realistic Image Generation from Stroke and Sketch with Diffusion Model","created":"2022-08-26","cited_by_count":39,"area":"diffusion"},{"id":"2206.09479","title":"StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis","created":"2022-06-19","cited_by_count":38,"area":null},{"id":"2311.18832","title":"Exploiting Diffusion Prior for Generalizable Dense Prediction","created":"2023-11-30","cited_by_count":38,"area":"diffusion"},{"id":"2106.07115","title":"Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspective","created":"2021-06-14","cited_by_count":37,"area":null},{"id":"2106.09016","title":"Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation","created":"2021-06-16","cited_by_count":35,"area":null},{"id":"2203.04946","title":"Do better ImageNet classifiers assess perceptual similarity better?","created":"2022-03-09","cited_by_count":34,"area":null},{"id":"2203.10339","title":"Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation","created":"2022-03-19","cited_by_count":34,"area":null},{"id":"2302.06826","title":"DiffFashion: Reference-based Fashion Design with Structure-aware Transfer by Diffusion Models","created":"2023-02-14","cited_by_count":33,"area":"diffusion"},{"id":"2108.03553","title":"Self-Adversarial Disentangling for Specific Domain Adaptation","created":"2021-08-08","cited_by_count":29,"area":null},{"id":"2107.07437","title":"StyleFusion: A Generative Model for Disentangling Spatial Segments","created":"2021-07-15","cited_by_count":28,"area":null},{"id":"2306.11087","title":"Primitive Generation and Semantic-related Alignment for Universal Zero-Shot Segmentation","created":"2023-06-19","cited_by_count":28,"area":null},{"id":"2303.16976","title":"MaLP: Manipulation Localization Using a Proactive Scheme","created":"2023-03-29","cited_by_count":26,"area":null},{"id":"2104.05703","title":"Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis","created":"2021-04-12","cited_by_count":24,"area":null},{"id":"2105.02104","title":"Conditional Invertible Neural Networks for Diverse Image-to-Image Translation","created":"2021-05-05","cited_by_count":24,"area":null},{"id":"2110.04111","title":"Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation","created":"2021-10-08","cited_by_count":24,"area":null},{"id":"2112.03631","title":"SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal","created":"2021-12-07","cited_by_count":22,"area":null},{"id":"2104.05170","title":"Memory-guided Unsupervised Image-to-image Translation","created":"2021-04-12","cited_by_count":21,"area":null},{"id":"2104.03821","title":"Robust Differentiable SVD","created":"2021-04-08","cited_by_count":19,"area":null},{"id":"2207.11025","title":"Custom Structure Preservation in Face Aging","created":"2022-07-22","cited_by_count":19,"area":null},{"id":"2205.03742","title":"Decoupled-and-Coupled Networks: Self-Supervised Hyperspectral Image Super-Resolution with Subpixel Fusion","created":"2022-05-07","cited_by_count":18,"area":null},{"id":"2208.08605","title":"Contrastive Semi-supervised Learning for Domain Adaptive Segmentation Across Similar Anatomical Structures","created":"2022-08-18","cited_by_count":18,"area":null},{"id":"2212.10431","title":"QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity","created":"2022-12-20","cited_by_count":18,"area":null},{"id":"2303.12649","title":"MI-SegNet: Mutual Information-Based US Segmentation for Unseen Domain Generalization","created":"2023-03-22","cited_by_count":18,"area":null},{"id":"2308.04733","title":"TextPainter: Multimodal Text Image Generation with Visual-harmony and Text-comprehension for Poster Design","created":"2023-08-09","cited_by_count":18,"area":null},{"id":"2403.20142","title":"StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation","created":"2024-03-29","cited_by_count":18,"area":null},{"id":"2105.12324","title":"PSGAN++: Robust Detail-Preserving Makeup Transfer and Removal","created":"2021-05-26","cited_by_count":17,"area":null},{"id":"2207.03411","title":"VecGAN: Image-to-Image Translation with Interpretable Latent Directions","created":"2022-07-07","cited_by_count":17,"area":null},{"id":"2207.13286","title":"Vector Quantized Image-to-Image Translation","created":"2022-07-27","cited_by_count":16,"area":null},{"id":"2210.12683","title":"GAN-based Facial Attribute Manipulation","created":"2022-10-23","cited_by_count":16,"area":null},{"id":"2503.19012","title":"DiffV2IR: Visible-to-Infrared Diffusion Model via Vision-Language Understanding","created":"2025-03-24","cited_by_count":16,"area":"diffusion"},{"id":"2306.10511","title":"Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning","created":"2023-06-18","cited_by_count":15,"area":null},{"id":"2312.00739","title":"Adversarial Score Distillation: When score distillation meets GAN","created":"2023-12-01","cited_by_count":15,"area":null},{"id":"2111.01619","title":"StyleGAN of All Trades: Image Manipulation with Only Pretrained StyleGAN","created":"2021-11-02","cited_by_count":14,"area":null},{"id":"2202.13562","title":"Name Your Style: An Arbitrary Artist-aware Image Style Transfer","created":"2022-02-28","cited_by_count":14,"area":null},{"id":"2308.02154","title":"SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image Translation","created":"2023-08-04","cited_by_count":14,"area":"diffusion"},{"id":"1909.12971","title":"Zero-shot Imitation Learning from Demonstrations for Legged Robot Visual Navigation","created":"2019-09-27","cited_by_count":13,"area":"offlinerl"},{"id":"2112.04163","title":"Assessing a Single Image in Reference-Guided Image Synthesis","created":"2021-12-08","cited_by_count":13,"area":null},{"id":"2112.10082","title":"MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networks","created":"2021-12-19","cited_by_count":13,"area":null},{"id":"2301.04628","title":"Image-to-Image Translation with Disentangled Latent Vectors for Face Editing","created":"2023-01-11","cited_by_count":13,"area":null},{"id":"2303.14453","title":"Federated Learning without Full Labels: A Survey","created":"2023-03-25","cited_by_count":13,"area":null},{"id":"2310.19559","title":"Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning","created":"2023-10-30","cited_by_count":13,"area":"lr"},{"id":"2104.05077","title":"CoPE: Conditional image generation using Polynomial Expansions","created":"2021-04-11","cited_by_count":12,"area":null},{"id":"2110.00041","title":"Learning Multi-Site Harmonization of Magnetic Resonance Images Without Traveling Human Phantoms","created":"2021-09-30","cited_by_count":12,"area":null},{"id":"2210.15194","title":"Few-shot Image Generation via Masked Discrimination","created":"2022-10-27","cited_by_count":12,"area":null},{"id":"2510.15710","title":"UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysis","created":"2025-10-17","cited_by_count":12,"area":null},{"id":"2103.17104","title":"Deep Image Harmonization by Bridging the Reality Gap","created":"2021-03-31","cited_by_count":11,"area":null},{"id":"2107.07260","title":"MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators","created":"2021-07-15","cited_by_count":11,"area":null},{"id":"2203.10474","title":"Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Data","created":"2022-03-20","cited_by_count":11,"area":null},{"id":"2302.00517","title":"Synthesis-based Imaging-Differentiation Representation Learning for Multi-Sequence 3D/4D MRI","created":"2023-02-01","cited_by_count":11,"area":null},{"id":"2303.13062","title":"SIEDOB: Semantic Image Editing by Disentangling Object and Background","created":"2023-03-23","cited_by_count":11,"area":null},{"id":"2312.00548","title":"Domain Adaptive Imitation Learning with Visual Observation","created":"2023-12-01","cited_by_count":11,"area":"offlinerl"},{"id":"2108.07979","title":"A New Bidirectional Unsupervised Domain Adaptation Segmentation Framework","created":"2021-08-18","cited_by_count":10,"area":null},{"id":"2108.09977","title":"Exploring the Quality of GAN Generated Images for Person Re-Identification","created":"2021-08-23","cited_by_count":10,"area":null},{"id":"2112.01766","title":"Unsupervised Low-Light Image Enhancement via Histogram Equalization Prior","created":"2021-12-03","cited_by_count":10,"area":null},{"id":"2201.04812","title":"Unsupervised Domain Adaptation for Cross-Modality Retinal Vessel Segmentation via Disentangling Representation Style Transfer and Collaborative Consistency Learning","created":"2022-01-13","cited_by_count":10,"area":null},{"id":"2203.06811","title":"ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation","created":"2022-03-14","cited_by_count":10,"area":null},{"id":"2210.07181","title":"MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Pose","created":"2022-10-13","cited_by_count":10,"area":null},{"id":"2212.03651","title":"Cyclically Disentangled Feature Translation for Face Anti-spoofing","created":"2022-12-07","cited_by_count":10,"area":null},{"id":"2302.09795","title":"Simple Disentanglement of Style and Content in Visual Representations","created":"2023-02-20","cited_by_count":10,"area":null},{"id":"2407.18999","title":"Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models","created":"2024-07-26","cited_by_count":10,"area":"mllm"},{"id":"2412.10651","title":"LAN: Learning to Adapt Noise for Image Denoising","created":"2024-12-14","cited_by_count":10,"area":null},{"id":"2103.16262","title":"Is Image-to-Image Translation the Panacea for Multimodal Image Registration? A Comparative Study","created":"2021-03-30","cited_by_count":9,"area":null},{"id":"2109.12492","title":"ISF-GAN: An Implicit Style Function for High-Resolution Image-to-Image Translation","created":"2021-09-26","cited_by_count":9,"area":null},{"id":"2110.07375","title":"Multiple Style Transfer via Variational AutoEncoder","created":"2021-10-13","cited_by_count":9,"area":null}],"next_cursor":"100"}