{"list":"other","total":71,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"2211.12572","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","created":"2022-11-22","cited_by_count":906},{"id":"2304.08465","title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","created":"2023-04-17","cited_by_count":727},{"id":"2311.17117","title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","created":"2023-11-28","cited_by_count":688},{"id":"2306.13643","title":"LightGlue: Local Feature Matching at Light Speed","created":"2023-06-23","cited_by_count":590},{"id":"2211.13227","title":"Paint by Example: Exemplar-based Image Editing with Diffusion Models","created":"2022-11-23","cited_by_count":489},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"2307.09481","title":"AnyDoor: Zero-shot Object-level Image Customization","created":"2023-07-18","cited_by_count":412},{"id":"2311.16498","title":"MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model","created":"2023-11-27","cited_by_count":330},{"id":"2304.01186","title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","created":"2023-04-03","cited_by_count":314},{"id":"2306.03514","title":"Recognize Anything: A Strong Image Tagging Model","created":"2023-06-06","cited_by_count":309},{"id":"1903.07593","title":"Learning Correspondence from the Cycle-Consistency of Time","created":"2019-03-18","cited_by_count":269},{"id":"2411.04746","title":"Taming Rectified Flow for Inversion and Editing","created":"2024-11-07","cited_by_count":204},{"id":"2406.01900","title":"Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation","created":"2024-06-04","cited_by_count":174},{"id":"2411.17440","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition","created":"2024-11-26","cited_by_count":158},{"id":"2303.05125","title":"Cones: Concept Neurons in Diffusion Models for Customized Generation","created":"2023-03-09","cited_by_count":150},{"id":"2012.04781","title":"You Only Need Adversarial Supervision for Semantic Image Synthesis","created":"2020-12-08","cited_by_count":129},{"id":"2305.19327","title":"Cones 2: Customizable Image Synthesis with Multiple Subjects","created":"2023-05-30","cited_by_count":101},{"id":"2411.03286","title":"DiT4Edit: Diffusion Transformer for Image Editing","created":"2024-11-05","cited_by_count":101},{"id":"1908.07500","title":"Image Synthesis From Reconfigurable Layout and Style","created":"2019-08-20","cited_by_count":85},{"id":"1612.00835","title":"Scribbler: Controlling Deep Image Synthesis with Sketch and Color","created":"2016-12-02","cited_by_count":78},{"id":"2106.02520","title":"CATs: Cost Aggregation Transformers for Visual Correspondence","created":"2021-06-04","cited_by_count":77},{"id":"2005.10825","title":"Instance-aware Image Colorization","created":"2020-05-21","cited_by_count":76},{"id":"1906.09909","title":"Deep Exemplar-based Video Colorization","created":"2019-06-24","cited_by_count":75},{"id":"2104.02495","title":"Deep Animation Video Interpolation in the Wild","created":"2021-04-06","cited_by_count":65},{"id":"2210.16056","title":"MagicMix: Semantic Mixing with Diffusion Models","created":"2022-10-28","cited_by_count":63},{"id":"2112.05143","title":"GAN-Supervised Dense Visual Alignment","created":"2021-12-09","cited_by_count":62},{"id":"2312.03047","title":"MagicStick: Controllable Video Editing via Control Handle Transformations","created":"2023-12-05","cited_by_count":62},{"id":"2309.16668","title":"RealFill: Reference-Driven Generation for Authentic Image Completion","created":"2023-09-28","cited_by_count":59},{"id":"2406.08850","title":"COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing","created":"2024-06-13","cited_by_count":59},{"id":"2005.05207","title":"Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence","created":"2020-05-11","cited_by_count":53},{"id":"2403.08268","title":"Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts","created":"2024-03-13","cited_by_count":52},{"id":"2003.11571","title":"Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis","created":"2020-03-25","cited_by_count":49},{"id":"2404.14239","title":"MultiBooth: Towards Generating All Your Concepts in an Image from Text","created":"2024-04-22","cited_by_count":45},{"id":"2409.01055","title":"Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation","created":"2024-09-02","cited_by_count":42},{"id":"1908.01311","title":"Fully Automatic Video Colorization with Self-Regularization and Diversity","created":"2019-08-04","cited_by_count":40},{"id":"1908.05840","title":"Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing Loss","created":"2019-08-16","cited_by_count":35},{"id":"2412.01197","title":"InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences","created":"2024-12-02","cited_by_count":34},{"id":"1705.07208","title":"PixColor: Pixel Recursive Colorization","created":"2017-05-19","cited_by_count":32},{"id":"2312.03771","title":"DreamInpainter: Text-Guided Subject-Driven Image Inpainting with Diffusion Models","created":"2023-12-05","cited_by_count":31},{"id":"2205.11634","title":"TransforMatcher: Match-to-Match Attention for Semantic Correspondence","created":"2022-05-23","cited_by_count":29},{"id":"1901.10889","title":"Pixelated Semantic Colorization","created":"2019-01-27","cited_by_count":28},{"id":"2207.06095","title":"Eliminating Gradient Conflict in Reference-based Line-Art Colorization","created":"2022-07-13","cited_by_count":25},{"id":"2312.04145","title":"Diffusing Colors: Image Colorization with Text Guided Diffusion","created":"2023-12-07","cited_by_count":25},{"id":"2412.14173","title":"AniDoc: Animation Creation Made Easier","created":"2024-12-18","cited_by_count":22},{"id":"2109.02614","title":"The Animation Transformer: Visual Correspondence via Segment Matching","created":"2021-09-06","cited_by_count":20},{"id":"2311.17083","title":"CLiC: Concept Learning in Context","created":"2023-11-28","cited_by_count":20},{"id":"2405.07425","title":"Sakuga-42M Dataset: Scaling Up Cartoon Research","created":"2024-05-13","cited_by_count":17},{"id":"2408.12128","title":"Diffusion-Based Visual Art Creation: A Survey and New Perspectives","created":"2024-08-22","cited_by_count":17},{"id":"2501.08332","title":"MangaNinja: Line Art Colorization with Precise Reference Following","created":"2025-01-14","cited_by_count":17},{"id":"2410.00337","title":"SyntheOcc: Synthesize Geometric-Controlled Street View Images through 3D Semantic MPIs","created":"2024-10-01","cited_by_count":14},{"id":"2112.01335","title":"Semantic-Sparse Colorization Network for Deep Exemplar-based Colorization","created":"2021-12-02","cited_by_count":12},{"id":"2106.08017","title":"Color2Embed: Fast Exemplar-Based Image Colorization using Color Embeddings","created":"2021-06-15","cited_by_count":9},{"id":"2303.11137","title":"AnimeDiffusion: Anime Face Line Drawing Colorization via Diffusion Models","created":"2023-03-20","cited_by_count":9},{"id":"2401.01456","title":"ColorizeDiffusion: Adjustable Sketch Colorization with Reference Image and Text","created":"2024-01-02","cited_by_count":8},{"id":"2412.04146","title":"AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models","created":"2024-12-05","cited_by_count":7},{"id":"2410.04932","title":"OmniBooth: Learning Latent Control for Image Synthesis with Multi-modal Instruction","created":"2024-10-07","cited_by_count":2}],"next_cursor":null}