{"list":"other","total":95,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"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":"2206.00927","title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps","created":"2022-06-02","cited_by_count":1979},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2112.07945","title":"Efficient Geometry-aware 3D Generative Adversarial Networks","created":"2021-12-15","cited_by_count":1205},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2310.00426","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","created":"2023-09-30","cited_by_count":864},{"id":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"id":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"1907.11922","title":"MaskGAN: Towards Diverse and Interactive Facial Image Manipulation","created":"2019-07-27","cited_by_count":628},{"id":"1811.00982","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","created":"2018-11-02","cited_by_count":544},{"id":"2102.02766","title":"Designing an Encoder for StyleGAN Image Manipulation","created":"2021-02-04","cited_by_count":544},{"id":"2112.07804","title":"Tackling the Generative Learning Trilemma with Denoising Diffusion GANs","created":"2021-12-15","cited_by_count":516},{"id":"2302.07121","title":"Universal Guidance for Diffusion Models","created":"2023-02-14","cited_by_count":437},{"id":"2302.13848","title":"ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation","created":"2023-02-27","cited_by_count":416},{"id":"2005.09007","title":"U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection","created":"2020-05-18","cited_by_count":412},{"id":"2307.09481","title":"AnyDoor: Zero-shot Object-level Image Customization","created":"2023-07-18","cited_by_count":412},{"id":"2211.12194","title":"SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation","created":"2022-11-22","cited_by_count":382},{"id":"2101.05278","title":"GAN Inversion: A Survey","created":"2021-01-14","cited_by_count":367},{"id":"1610.07629","title":"A Learned Representation For Artistic Style","created":"2016-10-24","cited_by_count":341},{"id":"2312.04461","title":"PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding","created":"2023-12-07","cited_by_count":328},{"id":"2302.09778","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","created":"2023-02-20","cited_by_count":304},{"id":"2311.11284","title":"LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching","created":"2023-11-19","cited_by_count":290},{"id":"1711.08447","title":"VITON: An Image-based Virtual Try-on Network","created":"2017-11-22","cited_by_count":286},{"id":"1804.06655","title":"Deep Face Recognition: A Survey","created":"2018-04-18","cited_by_count":276},{"id":"1711.10337","title":"Are GANs Created Equal? A Large-Scale Study","created":"2017-11-28","cited_by_count":267},{"id":"1905.01270","title":"DRIT++: Diverse Image-to-Image Translation via Disentangled Representations","created":"2019-05-02","cited_by_count":244},{"id":"2106.06340","title":"SimSwap: An Efficient Framework For High Fidelity Face Swapping","created":"2021-06-11","cited_by_count":243},{"id":"2206.09012","title":"Diffusion models as plug-and-play priors","created":"2022-06-17","cited_by_count":231},{"id":"2305.16311","title":"Break-A-Scene: Extracting Multiple Concepts from a Single Image","created":"2023-05-25","cited_by_count":231},{"id":"2307.06949","title":"HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models","created":"2023-07-13","cited_by_count":225},{"id":"1912.13457","title":"FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping","created":"2019-12-31","cited_by_count":221},{"id":"2203.15270","title":"MAT: Mask-Aware Transformer for Large Hole Image Inpainting","created":"2022-03-29","cited_by_count":218},{"id":"2206.02262","title":"Diffusion-GAN: Training GANs with Diffusion","created":"2022-06-05","cited_by_count":205},{"id":"1910.09777","title":"Self-Correction for Human Parsing","created":"2019-10-22","cited_by_count":180},{"id":"2203.09043","title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","created":"2022-03-17","cited_by_count":175},{"id":"2003.05863","title":"Towards Photo-Realistic Virtual Try-On by Adaptively Generating$\\leftrightarrow$Preserving Image Content","created":"2020-03-12","cited_by_count":149},{"id":"2204.11823","title":"StyleGAN-Human: A Data-Centric Odyssey of Human Generation","created":"2022-04-25","cited_by_count":144},{"id":"2207.00050","title":"Semantic Image Synthesis via Diffusion Models","created":"2022-06-30","cited_by_count":132},{"id":"2005.05535","title":"DeepFaceLab: Integrated, flexible and extensible face-swapping framework","created":"2020-05-12","cited_by_count":131},{"id":"2402.03286","title":"Training-Free Consistent Text-to-Image Generation","created":"2024-02-05","cited_by_count":125},{"id":"2201.07786","title":"Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation","created":"2022-01-19","cited_by_count":119},{"id":"2402.17113","title":"Transparent Image Layer Diffusion using Latent Transparency","created":"2024-02-27","cited_by_count":114},{"id":"2105.04932","title":"One Shot Face Swapping on Megapixels","created":"2021-05-11","cited_by_count":105},{"id":"2305.19327","title":"Cones 2: Customizable Image Synthesis with Multiple Subjects","created":"2023-05-30","cited_by_count":101},{"id":"2006.05132","title":"A Survey on Generative Adversarial Networks: Variants, Applications, and Training","created":"2020-06-09","cited_by_count":97},{"id":"2105.02201","title":"PD-GAN: Probabilistic Diverse GAN for Image Inpainting","created":"2021-05-05","cited_by_count":80},{"id":"2310.08579","title":"HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion","created":"2023-10-12","cited_by_count":68},{"id":"2307.09036","title":"PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation","created":"2023-07-18","cited_by_count":58},{"id":"2312.02663","title":"FaceStudio: Put Your Face Everywhere in Seconds","created":"2023-12-05","cited_by_count":53},{"id":"2203.04564","title":"Region-Aware Face Swapping","created":"2022-03-09","cited_by_count":45},{"id":"2203.07293","title":"InsetGAN for Full-Body Image Generation","created":"2022-03-14","cited_by_count":45},{"id":"1911.10538","title":"Breaking the cycle -- Colleagues are all you need","created":"2019-11-24","cited_by_count":40},{"id":"2101.06175","title":"PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation","created":"2021-01-15","cited_by_count":35},{"id":"2401.15975","title":"StableIdentity: Inserting Anybody into Anywhere at First Sight","created":"2024-01-29","cited_by_count":35},{"id":"2112.05907","title":"Smooth-Swap: A Simple Enhancement for Face-Swapping with Smoothness","created":"2021-12-11","cited_by_count":30},{"id":"1905.00307","title":"3DFaceGAN: Adversarial Nets for 3D Face Representation, Generation, and Translation","created":"2019-05-01","cited_by_count":27},{"id":"2307.00300","title":"DreamIdentity: Improved Editability for Efficient Face-identity Preserved Image Generation","created":"2023-07-01","cited_by_count":26},{"id":"2102.11464","title":"FaceController: Controllable Attribute Editing for Face in the Wild","created":"2021-02-23","cited_by_count":22},{"id":"2103.11135","title":"High Resolution Face Editing with Masked GAN Latent Code Optimization","created":"2021-03-20","cited_by_count":21},{"id":"2204.13100","title":"Few-Shot Head Swapping in the Wild","created":"2022-04-27","cited_by_count":21},{"id":"2203.02762","title":"DrawingInStyles: Portrait Image Generation and Editing with Spatially Conditioned StyleGAN","created":"2022-03-05","cited_by_count":18},{"id":"1904.02296","title":"Gated-GAN: Adversarial Gated Networks for Multi-Collection Style Transfer","created":"2019-04-04","cited_by_count":17},{"id":"2211.06757","title":"DriftRec: Adapting diffusion models to blind JPEG restoration","created":"2022-11-12","cited_by_count":15},{"id":"2312.02149","title":"Generative Powers of Ten","created":"2023-12-04","cited_by_count":15},{"id":"1808.07757","title":"Deep Portrait Image Completion and Extrapolation","created":"2018-08-23","cited_by_count":12},{"id":"2210.15194","title":"Few-shot Image Generation via Masked Discrimination","created":"2022-10-27","cited_by_count":12},{"id":"2212.09399","title":"AI Art in Architecture","created":"2022-12-19","cited_by_count":12},{"id":"1807.06650","title":"Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions","created":"2018-07-17","cited_by_count":11},{"id":"2310.08094","title":"SingleInsert: Inserting New Concepts from a Single Image into Text-to-Image Models for Flexible Editing","created":"2023-10-12","cited_by_count":10},{"id":"2207.05430","title":"Learning Diverse Tone Styles for Image Retouching","created":"2022-07-12","cited_by_count":8},{"id":"2312.04236","title":"Detecting and Restoring Non-Standard Hands in Stable Diffusion Generated Images","created":"2023-12-07","cited_by_count":3},{"id":"2404.04833","title":"ShoeModel: Learning to Wear on the User-specified Shoes via Diffusion Model","created":"2024-04-07","cited_by_count":2}],"next_cursor":null}