{"list":"other","total":63,"rows":[{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"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":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"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":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"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":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"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":"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":"2004.07728","title":"Image Quality Assessment: Unifying Structure and Texture Similarity","created":"2020-04-16","cited_by_count":811},{"id":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"id":"2108.02938","title":"ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models","created":"2021-08-06","cited_by_count":635},{"id":"1607.08221","title":"MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition","created":"2016-07-27","cited_by_count":624},{"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":"1710.04026","title":"FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising","created":"2017-10-11","cited_by_count":510},{"id":"1904.00523","title":"Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model","created":"2019-04-01","cited_by_count":403},{"id":"2304.08466","title":"Synthetic Data from Diffusion Models Improves ImageNet Classification","created":"2023-04-17","cited_by_count":327},{"id":"2210.07574","title":"Is synthetic data from generative models ready for image recognition?","created":"2022-10-14","cited_by_count":320},{"id":"2401.13627","title":"Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild","created":"2024-01-24","cited_by_count":286},{"id":"2008.01928","title":"Component Divide-and-Conquer for Real-World Image Super-Resolution","created":"2020-08-05","cited_by_count":246},{"id":"2003.13659","title":"Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation","created":"2020-03-30","cited_by_count":225},{"id":"2303.11950","title":"Learning A Sparse Transformer Network for Effective Image Deraining","created":"2023-03-21","cited_by_count":205},{"id":"2105.06070","title":"GAN Prior Embedded Network for Blind Face Restoration in the Wild","created":"2021-05-13","cited_by_count":197},{"id":"2304.06025","title":"DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion","created":"2023-04-12","cited_by_count":167},{"id":"1809.00437","title":"Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networks","created":"2018-09-03","cited_by_count":133},{"id":"1905.05169","title":"Zoom To Learn, Learn To Zoom","created":"2019-05-13","cited_by_count":115},{"id":"2203.09195","title":"Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution","created":"2022-03-17","cited_by_count":114},{"id":"2312.08962","title":"Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models","created":"2023-12-14","cited_by_count":105},{"id":"2203.14216","title":"Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution","created":"2022-03-27","cited_by_count":96},{"id":"2003.07018","title":"Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution","created":"2020-03-16","cited_by_count":90},{"id":"2309.11523","title":"RMT: Retentive Networks Meet Vision Transformers","created":"2023-09-20","cited_by_count":68},{"id":"2402.01832","title":"SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?","created":"2024-02-02","cited_by_count":64},{"id":"2303.13132","title":"Masked Image Training for Generalizable Deep Image Denoising","created":"2023-03-23","cited_by_count":57},{"id":"1904.03378","title":"Camera Lens Super-Resolution","created":"2019-04-06","cited_by_count":56},{"id":"2312.02918","title":"Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration","created":"2023-12-05","cited_by_count":50},{"id":"2303.06440","title":"Xformer: Hybrid X-Shaped Transformer for Image Denoising","created":"2023-03-11","cited_by_count":37},{"id":"2304.00534","title":"LG-BPN: Local and Global Blind-Patch Network for Self-Supervised Real-World Denoising","created":"2023-04-02","cited_by_count":37},{"id":"2409.12568","title":"InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning","created":"2024-09-19","cited_by_count":36},{"id":"2009.09399","title":"DVG-Face: Dual Variational Generation for Heterogeneous Face Recognition","created":"2020-09-20","cited_by_count":32},{"id":"2211.16928","title":"Knowledge Distillation based Degradation Estimation for Blind Super-Resolution","created":"2022-11-30","cited_by_count":28},{"id":"2203.04962","title":"Learning the Degradation Distribution for Blind Image Super-Resolution","created":"2022-03-09","cited_by_count":27},{"id":"2206.07038","title":"AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos","created":"2022-06-14","cited_by_count":23},{"id":"2410.15385","title":"LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration","created":"2024-10-20","cited_by_count":18},{"id":"2205.03524","title":"Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution","created":"2022-05-07","cited_by_count":10},{"id":"2303.17783","title":"Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer","created":"2023-03-31","cited_by_count":6},{"id":"2401.00370","title":"UGPNet: Universal Generative Prior for Image Restoration","created":"2023-12-31","cited_by_count":2}],"next_cursor":null}