{"total":483,"rows":[{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611,"area":"diffusion"},{"id":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337,"area":null},{"id":"2503.21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","created":"2025-03-27","cited_by_count":315,"area":"wm"},{"id":"2304.14772","title":"Multisample Flow Matching: Straightening Flows with Minibatch Couplings","created":"2023-04-28","cited_by_count":278,"area":"diffusion"},{"id":"2308.14469","title":"Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization","created":"2023-08-28","cited_by_count":254,"area":"diffusion"},{"id":"2112.01554","title":"Neural Head Avatars from Monocular RGB Videos","created":"2021-12-02","cited_by_count":213,"area":null},{"id":"2306.00983","title":"StyleDrop: Text-to-Image Generation in Any Style","created":"2023-06-01","cited_by_count":199,"area":null},{"id":"2106.14843","title":"CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders","created":"2021-06-28","cited_by_count":187,"area":null},{"id":"2504.00983","title":"WorldScore: A Unified Evaluation Benchmark for World Generation","created":"2025-04-01","cited_by_count":156,"area":null},{"id":"2403.14468","title":"AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks","created":"2024-03-21","cited_by_count":154,"area":null},{"id":"2205.12183","title":"StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learning","created":"2022-05-24","cited_by_count":140,"area":null},{"id":"2311.03335","title":"Cross-Image Attention for Zero-Shot Appearance Transfer","created":"2023-11-06","cited_by_count":136,"area":null},{"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":"2203.07615","title":"Learning What Not to Segment: A New Perspective on Few-Shot Segmentation","created":"2022-03-15","cited_by_count":120,"area":null},{"id":"2103.16877","title":"ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows","created":"2021-03-31","cited_by_count":113,"area":null},{"id":"2101.06046","title":"Counterfactual Generative Networks","created":"2021-01-15","cited_by_count":111,"area":null},{"id":"2404.01292","title":"Measuring Style Similarity in Diffusion Models","created":"2024-04-01","cited_by_count":109,"area":"diffusion"},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"area":null},{"id":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81,"area":null},{"id":"2102.05262","title":"Input Similarity from the Neural Network Perspective","created":"2021-02-10","cited_by_count":79,"area":null},{"id":"2203.03121","title":"Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer","created":"2022-03-07","cited_by_count":78,"area":null},{"id":"2201.04439","title":"Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases","created":"2022-01-12","cited_by_count":72,"area":null},{"id":"2204.01943","title":"Unified Implicit Neural Stylization","created":"2022-04-05","cited_by_count":67,"area":null},{"id":"2301.05339","title":"A Comprehensive Review of Data-Driven Co-Speech Gesture Generation","created":"2023-01-13","cited_by_count":66,"area":null},{"id":"2106.14490","title":"Making Images Real Again: A Comprehensive Survey on Deep Image Composition","created":"2021-06-28","cited_by_count":63,"area":null},{"id":"2210.16056","title":"MagicMix: Semantic Mixing with Diffusion Models","created":"2022-10-28","cited_by_count":63,"area":"diffusion"},{"id":"2601.16208","title":"Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders","created":"2026-01-22","cited_by_count":53,"area":"diffusion"},{"id":"2304.08490","title":"Conditional Generation of Audio from Video via Foley Analogies","created":"2023-04-17","cited_by_count":52,"area":null},{"id":"2402.11846","title":"UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models","created":"2024-02-19","cited_by_count":50,"area":"diffusion"},{"id":"2105.04551","title":"Stochastic Image-to-Video Synthesis using cINNs","created":"2021-05-10","cited_by_count":49,"area":null},{"id":"2208.07059","title":"UPST-NeRF: Universal Photorealistic Style Transfer of Neural Radiance Fields for 3D Scene","created":"2022-08-15","cited_by_count":47,"area":null},{"id":"2305.19164","title":"LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images","created":"2023-05-30","cited_by_count":46,"area":null},{"id":"2112.00169","title":"3D Photo Stylization: Learning to Generate Stylized Novel Views from a Single Image","created":"2021-11-30","cited_by_count":45,"area":null},{"id":"2401.01702","title":"Image Sculpting: Precise Object Editing with 3D Geometry Control","created":"2024-01-02","cited_by_count":45,"area":null},{"id":"2103.15263","title":"Zero-shot Adversarial Quantization","created":"2021-03-29","cited_by_count":44,"area":null},{"id":"2407.07111","title":"Diffusion Model-Based Video Editing: A Survey","created":"2024-06-26","cited_by_count":44,"area":"diffusion"},{"id":"2107.00471","title":"SinGAN-Seg: Synthetic training data generation for medical image segmentation","created":"2021-06-29","cited_by_count":43,"area":null},{"id":"2206.00923","title":"Modeling Image Composition for Complex Scene Generation","created":"2022-06-02","cited_by_count":43,"area":null},{"id":"2307.02694","title":"Loss Functions and Metrics in Deep Learning","created":"2023-07-05","cited_by_count":42,"area":"rag"},{"id":"2103.11897","title":"Context-Aware Layout to Image Generation with Enhanced Object Appearance","created":"2021-03-22","cited_by_count":41,"area":null},{"id":"2312.15172","title":"Pre-trained Trojan Attacks for Visual Recognition","created":"2023-12-23","cited_by_count":39,"area":"safety"},{"id":"2310.08541","title":"Idea2Img: Iterative Self-Refinement with GPT-4V(ision) for Automatic Image Design and Generation","created":"2023-10-12","cited_by_count":38,"area":null},{"id":"2106.00178","title":"Language-Driven Image Style Transfer","created":"2021-06-01","cited_by_count":37,"area":null},{"id":"2303.15403","title":"Training-free Content Injection using h-space in Diffusion Models","created":"2023-03-27","cited_by_count":36,"area":"diffusion"},{"id":"2404.01247","title":"An image speaks a thousand words, but can everyone listen? On image transcreation for cultural relevance","created":"2024-04-01","cited_by_count":36,"area":null},{"id":"2405.01536","title":"Customizing Text-to-Image Models with a Single Image Pair","created":"2024-05-02","cited_by_count":36,"area":null},{"id":"2104.03507","title":"Progressive Temporal Feature Alignment Network for Video Inpainting","created":"2021-04-08","cited_by_count":35,"area":null},{"id":"2104.13743","title":"Image Inpainting by End-to-End Cascaded Refinement with Mask Awareness","created":"2021-04-28","cited_by_count":35,"area":null},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2112.00007","title":"Sound-Guided Semantic Image Manipulation","created":"2021-11-30","cited_by_count":35,"area":null},{"id":"2303.18080","title":"One-shot Unsupervised Domain Adaptation with Personalized Diffusion Models","created":"2023-03-31","cited_by_count":35,"area":"diffusion"},{"id":"2203.04946","title":"Do better ImageNet classifiers assess perceptual similarity better?","created":"2022-03-09","cited_by_count":34,"area":null},{"id":"2308.05184","title":"PromptPaint: Steering Text-to-Image Generation Through Paint Medium-like Interactions","created":"2023-08-09","cited_by_count":34,"area":"diffusion"},{"id":"2403.10075","title":"A survey of synthetic data augmentation methods in computer vision","created":"2024-03-15","cited_by_count":34,"area":null},{"id":"2111.15078","title":"SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches","created":"2021-11-30","cited_by_count":33,"area":null},{"id":"2204.06504","title":"DL4SciVis: A State-of-the-Art Survey on Deep Learning for Scientific Visualization","created":"2022-04-13","cited_by_count":32,"area":null},{"id":"2406.06382","title":"Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimization","created":"2024-06-10","cited_by_count":32,"area":"diffusion"},{"id":"2409.02543","title":"StyleTokenizer: Defining Image Style by a Single Instance for Controlling Diffusion Models","created":"2024-09-04","cited_by_count":32,"area":"diffusion"},{"id":"2204.02961","title":"SMU-Net: Style matching U-Net for brain tumor segmentation with missing modalities","created":"2022-04-06","cited_by_count":31,"area":null},{"id":"2307.14352","title":"General Image-to-Image Translation with One-Shot Image Guidance","created":"2023-07-20","cited_by_count":31,"area":null},{"id":"2406.06508","title":"Monkey See, Monkey Do: Harnessing Self-attention in Motion Diffusion for Zero-shot Motion Transfer","created":"2024-06-10","cited_by_count":31,"area":"diffusion"},{"id":"2206.05649","title":"TileGen: Tileable, Controllable Material Generation and Capture","created":"2022-06-12","cited_by_count":27,"area":null},{"id":"2411.11045","title":"StableV2V: Stablizing Shape Consistency in Video-to-Video Editing","created":"2024-11-17","cited_by_count":26,"area":null},{"id":"2102.12593","title":"AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation","created":"2021-02-24","cited_by_count":25,"area":null},{"id":"2108.06908","title":"Online Multi-Granularity Distillation for GAN Compression","created":"2021-08-16","cited_by_count":24,"area":null},{"id":"2411.17226","title":"MWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformers","created":"2024-11-26","cited_by_count":24,"area":null},{"id":"2106.06620","title":"Robust Representation Learning via Perceptual Similarity Metrics","created":"2021-06-11","cited_by_count":23,"area":null},{"id":"2203.03238","title":"Semantic Segmentation in Art Paintings","created":"2022-03-07","cited_by_count":23,"area":null},{"id":"2210.10782","title":"Topology Optimization via Machine Learning and Deep Learning: A Review","created":"2022-10-19","cited_by_count":23,"area":null},{"id":"2301.02830","title":"Image Data Augmentation Approaches: A Comprehensive Survey and Future directions","created":"2023-01-07","cited_by_count":23,"area":null},{"id":"2404.05220","title":"StylizedGS: Controllable Stylization for 3D Gaussian Splatting","created":"2024-04-08","cited_by_count":23,"area":null},{"id":"2110.04562","title":"Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learning","created":"2021-10-09","cited_by_count":22,"area":null},{"id":"2205.05072","title":"Learning Visual Styles from Audio-Visual Associations","created":"2022-05-10","cited_by_count":22,"area":null},{"id":"2302.04862","title":"Polynomial Neural Fields for Subband Decomposition and Manipulation","created":"2023-02-09","cited_by_count":22,"area":null},{"id":"2401.15636","title":"FreeStyle: Free Lunch for Text-guided Style Transfer using Diffusion Models","created":"2024-01-28","cited_by_count":22,"area":"diffusion"},{"id":"2104.02726","title":"Creativity and Machine Learning: A Survey","created":"2021-04-06","cited_by_count":21,"area":null},{"id":"2104.14559","title":"Exemplar-Based 3D Portrait Stylization","created":"2021-04-29","cited_by_count":21,"area":null},{"id":"2208.13016","title":"AesUST: Towards Aesthetic-Enhanced Universal Style Transfer","created":"2022-08-27","cited_by_count":21,"area":null},{"id":"2301.03220","title":"Enabling AI-Generated Content (AIGC) Services in Wireless Edge Networks","created":"2023-01-09","cited_by_count":21,"area":null},{"id":"2309.15421","title":"Deep Learning in Deterministic Computational Mechanics","created":"2023-09-27","cited_by_count":21,"area":null},{"id":"2203.16000","title":"StyleFool: Fooling Video Classification Systems via Style Transfer","created":"2022-03-30","cited_by_count":20,"area":null},{"id":"2306.10687","title":"Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillation","created":"2023-06-19","cited_by_count":20,"area":"distill"},{"id":"2412.14580","title":"DiffSim: Taming Diffusion Models for Evaluating Visual Similarity","created":"2024-12-19","cited_by_count":20,"area":"diffusion"},{"id":"2108.00968","title":"Robust Semantic Segmentation with Superpixel-Mix","created":"2021-08-02","cited_by_count":19,"area":null},{"id":"2109.14335","title":"A Systematic Survey of Deep Learning-based Single-Image Super-Resolution","created":"2021-09-29","cited_by_count":19,"area":null},{"id":"2204.08932","title":"Learning to Imagine: Diversify Memory for Incremental Learning using Unlabeled Data","created":"2022-04-19","cited_by_count":19,"area":null},{"id":"2109.11682","title":"Paint4Poem: A Dataset for Artistic Visualization of Classical Chinese Poems","created":"2021-09-23","cited_by_count":18,"area":null},{"id":"2304.10278","title":"Not Only Generative Art: Stable Diffusion for Content-Style Disentanglement in Art Analysis","created":"2023-04-20","cited_by_count":18,"area":"diffusion"},{"id":"2305.12296","title":"PhotoMat: A Material Generator Learned from Single Flash Photos","created":"2023-05-20","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":"2407.09473","title":"StyleSplat: 3D Object Style Transfer with Gaussian Splatting","created":"2024-07-12","cited_by_count":18,"area":null},{"id":"2410.10817","title":"When Does Perceptual Alignment Benefit Vision Representations?","created":"2024-10-14","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":"2310.15144","title":"DEsignBench: Exploring and Benchmarking DALL-E 3 for Imagining Visual Design","created":"2023-10-23","cited_by_count":17,"area":null},{"id":"2108.03894","title":"FIFA: Fast Inference Approximation for Action Segmentation","created":"2021-08-09","cited_by_count":16,"area":null},{"id":"2310.16002","title":"Integrating View Conditions for Image Synthesis","created":"2023-10-24","cited_by_count":16,"area":null},{"id":"2403.08255","title":"Make Me Happier: Evoking Emotions Through Image Diffusion Models","created":"2024-03-13","cited_by_count":16,"area":"diffusion"},{"id":"2406.13393","title":"Style-NeRF2NeRF: 3D Style Transfer From Style-Aligned Multi-View Images","created":"2024-06-19","cited_by_count":16,"area":"diffusion"},{"id":"2112.04665","title":"Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Semantic Segmentation","created":"2021-12-09","cited_by_count":15,"area":null},{"id":"2203.15163","title":"CAT-Net: A Cross-Slice Attention Transformer Model for Prostate Zonal Segmentation in MRI","created":"2022-03-29","cited_by_count":15,"area":null}],"next_cursor":"100"}