{"list":"other","total":55,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"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":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"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":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2211.09794","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","created":"2022-11-17","cited_by_count":1179},{"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":"2211.12572","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","created":"2022-11-22","cited_by_count":906},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"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":"2212.00490","title":"Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model","created":"2022-12-01","cited_by_count":583},{"id":"2307.10373","title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","created":"2023-07-19","cited_by_count":442},{"id":"2211.12446","title":"EDICT: Exact Diffusion Inversion via Coupled Transformations","created":"2022-11-22","cited_by_count":258},{"id":"2308.15070","title":"DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior","created":"2023-08-29","cited_by_count":257},{"id":"2304.06140","title":"An Edit Friendly DDPM Noise Space: Inversion and Manipulations","created":"2023-04-12","cited_by_count":244},{"id":"2408.16500","title":"CogVLM2: Visual Language Models for Image and Video Understanding","created":"2024-08-29","cited_by_count":217},{"id":"2305.16807","title":"Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models","created":"2023-05-26","cited_by_count":174},{"id":"2403.14602","title":"ReNoise: Real Image Inversion Through Iterative Noising","created":"2024-03-21","cited_by_count":128},{"id":"2310.01018","title":"Controlling Vision-Language Models for Multi-Task Image Restoration","created":"2023-10-02","cited_by_count":110},{"id":"2402.14797","title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","created":"2024-02-22","cited_by_count":105},{"id":"2305.15086","title":"Unpaired Image-to-Image Translation via Neural Schr\\\"odinger Bridge","created":"2023-05-24","cited_by_count":96},{"id":"2407.10172","title":"Restoring Images in Adverse Weather Conditions via Histogram Transformer","created":"2024-07-14","cited_by_count":73},{"id":"2407.21773","title":"RainMamba: Enhanced Locality Learning with State Space Models for Video Deraining","created":"2024-07-31","cited_by_count":56},{"id":"2404.01547","title":"Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining","created":"2024-04-02","cited_by_count":54},{"id":"1803.10433","title":"Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework","created":"2018-03-28","cited_by_count":53},{"id":"2403.00644","title":"Diff-Plugin: Revitalizing Details for Diffusion-based Low-level Tasks","created":"2024-03-01","cited_by_count":48},{"id":"2311.18387","title":"On Exact Inversion of DPM-Solvers","created":"2023-11-30","cited_by_count":47},{"id":"2411.07232","title":"Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models","created":"2024-11-11","cited_by_count":43},{"id":"2103.07939","title":"Semi-Supervised Video Deraining with Dynamical Rain Generator","created":"2021-03-14","cited_by_count":31},{"id":"2206.10779","title":"Not Just Streaks: Towards Ground Truth for Single Image Deraining","created":"2022-06-22","cited_by_count":31},{"id":"2203.11509","title":"Unsupervised Deraining: Where Contrastive Learning Meets Self-similarity","created":"2022-03-22","cited_by_count":30},{"id":"2409.15739","title":"Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint","created":"2024-09-24","cited_by_count":24},{"id":"2410.03936","title":"Learning Truncated Causal History Model for Video Restoration","created":"2024-10-04","cited_by_count":13},{"id":"2501.06751","title":"Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models","created":"2025-01-12","cited_by_count":13},{"id":"2407.17193","title":"Unpaired Photo-realistic Image Deraining with Energy-informed Diffusion Model","created":"2024-07-24","cited_by_count":11},{"id":"2410.07901","title":"Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization","created":"2024-10-10","cited_by_count":11},{"id":"2505.00704","title":"Controllable Weather Synthesis and Removal with Video Diffusion Models","created":"2025-05-01","cited_by_count":11},{"id":"2312.09534","title":"WeatherProof: A Paired-Dataset Approach to Semantic Segmentation in Adverse Weather","created":"2023-12-15","cited_by_count":9},{"id":"2407.01960","title":"Zero-Shot Video Restoration and Enhancement Using Pre-Trained Image Diffusion Model","created":"2024-07-02","cited_by_count":8},{"id":"2410.24151","title":"Scaling Concept With Text-Guided Diffusion Models","created":"2024-10-31","cited_by_count":8},{"id":"2505.16811","title":"Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining","created":"2025-05-22","cited_by_count":8},{"id":"2309.17239","title":"EGVD: Event-Guided Video Deraining","created":"2023-09-29","cited_by_count":6},{"id":"2409.00410","title":"A Hybrid Transformer-Mamba Network for Single Image Deraining","created":"2024-08-31","cited_by_count":6},{"id":"2505.05307","title":"PRE-Mamba: A 4D State Space Model for Ultra-High-Frequent Event Camera Deraining","created":"2025-05-08","cited_by_count":5}],"next_cursor":null}