{"list":"other","total":67,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"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":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"1707.02921","title":"Enhanced Deep Residual Networks for Single Image Super-Resolution","created":"2017-07-10","cited_by_count":1552},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"id":"1608.03981","title":"Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising","created":"2016-08-13","cited_by_count":1358},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"id":"1501.00092","title":"Image Super-Resolution Using Deep Convolutional Networks","created":"2014-12-31","cited_by_count":1224},{"id":"2211.09794","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","created":"2022-11-17","cited_by_count":1179},{"id":"2212.04488","title":"Multi-Concept Customization of Text-to-Image Diffusion","created":"2022-12-08","cited_by_count":1106},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"id":"2107.10833","title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","created":"2021-07-22","cited_by_count":970},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"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":"2106.03106","title":"Uformer: A General U-Shaped Transformer for Image Restoration","created":"2021-06-06","cited_by_count":866},{"id":"2102.02808","title":"Multi-Stage Progressive Image Restoration","created":"2021-02-04","cited_by_count":816},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2210.11427","title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","created":"2022-10-20","cited_by_count":647},{"id":"2306.10012","title":"MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing","created":"2023-06-16","cited_by_count":624},{"id":"1711.06077","title":"The Perception-Distortion Tradeoff","created":"2017-11-16","cited_by_count":587},{"id":"2103.14006","title":"Designing a Practical Degradation Model for Deep Blind Image Super-Resolution","created":"2021-03-25","cited_by_count":529},{"id":"2204.08958","title":"MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment","created":"2022-04-19","cited_by_count":522},{"id":"2111.08005","title":"Solving Inverse Problems in Medical Imaging with Score-Based Generative Models","created":"2021-11-15","cited_by_count":521},{"id":"1710.04026","title":"FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising","created":"2017-10-11","cited_by_count":510},{"id":"2302.03027","title":"Zero-shot Image-to-Image Translation","created":"2023-02-06","cited_by_count":505},{"id":"2206.02779","title":"Blended Latent Diffusion","created":"2022-06-06","cited_by_count":432},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"2101.04061","title":"Towards Real-World Blind Face Restoration with Generative Facial Prior","created":"2021-01-11","cited_by_count":349},{"id":"2303.11305","title":"SVDiff: Compact Parameter Space for Diffusion Fine-Tuning","created":"2023-03-20","cited_by_count":338},{"id":"2201.02973","title":"MAXIM: Multi-Axis MLP for Image Processing","created":"2022-01-09","cited_by_count":302},{"id":"2302.12066","title":"Teaching CLIP to Count to Ten","created":"2023-02-23","cited_by_count":198},{"id":"2105.06070","title":"GAN Prior Embedded Network for Blind Face Restoration in the Wild","created":"2021-05-13","cited_by_count":197},{"id":"2309.03895","title":"InstructDiffusion: A Generalist Modeling Interface for Vision Tasks","created":"2023-09-07","cited_by_count":164},{"id":"2310.01018","title":"Controlling Vision-Language Models for Multi-Task Image Restoration","created":"2023-10-02","cited_by_count":110},{"id":"2303.17569","title":"Iterative Prompt Learning for Unsupervised Backlit Image Enhancement","created":"2023-03-30","cited_by_count":107},{"id":"2004.03791","title":"Learning A Single Network for Scale-Arbitrary Super-Resolution","created":"2020-04-08","cited_by_count":66},{"id":"2311.16512","title":"CoSeR: Bridging Image and Language for Cognitive Super-Resolution","created":"2023-11-27","cited_by_count":66},{"id":"2303.14302","title":"VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining","created":"2023-03-24","cited_by_count":65},{"id":"2012.03255","title":"Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data","created":"2020-12-06","cited_by_count":42},{"id":"2206.11695","title":"NTIRE 2022 Challenge on Perceptual Image Quality Assessment","created":"2022-06-23","cited_by_count":41},{"id":"1704.02518","title":"Deep Generative Adversarial Compression Artifact Removal","created":"2017-04-08","cited_by_count":38},{"id":"2012.09289","title":"Projected Distribution Loss for Image Enhancement","created":"2020-12-16","cited_by_count":29},{"id":"2104.01374","title":"Interpretable Unsupervised Diversity Denoising and Artefact Removal","created":"2021-04-03","cited_by_count":26},{"id":"2204.04908","title":"No Token Left Behind: Explainability-Aided Image Classification and Generation","created":"2022-04-11","cited_by_count":25},{"id":"2311.14282","title":"Image Super-Resolution with Text Prompt Diffusion","created":"2023-11-24","cited_by_count":23},{"id":"2302.14736","title":"TextIR: A Simple Framework for Text-based Editable Image Restoration","created":"2023-02-28","cited_by_count":17}],"next_cursor":null}