{"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"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":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"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":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2305.01569","title":"Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation","created":"2023-05-02","cited_by_count":977},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"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":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"id":"2312.16256","title":"DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision","created":"2023-12-26","cited_by_count":537},{"id":"2303.12789","title":"Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions","created":"2023-03-22","cited_by_count":484},{"id":"2303.09535","title":"FateZero: Fusing Attentions for Zero-shot Text-based Video Editing","created":"2023-03-16","cited_by_count":466},{"id":"2307.10373","title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","created":"2023-07-19","cited_by_count":442},{"id":"1609.07769","title":"Deep Joint Rain Detection and Removal from a Single Image","created":"2016-09-25","cited_by_count":352},{"id":"2305.13077","title":"ControlVideo: Training-free Controllable Text-to-Video Generation","created":"2023-05-22","cited_by_count":327},{"id":"2303.12688","title":"Pix2Video: Video Editing using Image Diffusion","created":"2023-03-22","cited_by_count":320},{"id":"1601.07661","title":"DehazeNet: An End-to-End System for Single Image Haze Removal","created":"2016-01-28","cited_by_count":314},{"id":"2204.02491","title":"Text2LIVE: Text-Driven Layered Image and Video Editing","created":"2022-04-05","cited_by_count":312},{"id":"2111.14813","title":"TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions","created":"2021-11-29","cited_by_count":244},{"id":"1908.03245","title":"GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing","created":"2019-08-08","cited_by_count":227},{"id":"2104.09367","title":"Contrastive Learning for Compact Single Image Dehazing","created":"2021-04-19","cited_by_count":219},{"id":"2207.14626","title":"Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models","created":"2022-07-29","cited_by_count":215},{"id":"2201.00424","title":"Splicing ViT Features for Semantic Appearance Transfer","created":"2022-01-02","cited_by_count":209},{"id":"1711.10098","title":"Attentive Generative Adversarial Network for Raindrop Removal from a Single Image","created":"2017-11-28","cited_by_count":204},{"id":"1708.04512","title":"DesnowNet: Context-Aware Deep Network for Snow Removal","created":"2017-08-15","cited_by_count":200},{"id":"2302.01329","title":"Dreamix: Video Diffusion Models are General Video Editors","created":"2023-02-02","cited_by_count":191},{"id":"2304.09790","title":"AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation","created":"2023-04-19","cited_by_count":180},{"id":"2310.05922","title":"FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing","created":"2023-10-09","cited_by_count":167},{"id":"2403.14468","title":"AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks","created":"2024-03-21","cited_by_count":154},{"id":"2401.04092","title":"GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation","created":"2024-01-08","cited_by_count":153},{"id":"2403.12036","title":"One-Step Image Translation with Text-to-Image Models","created":"2024-03-18","cited_by_count":116},{"id":"2309.16496","title":"CCEdit: Creative and Controllable Video Editing via Diffusion Models","created":"2023-09-28","cited_by_count":82},{"id":"2312.17681","title":"FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis","created":"2023-12-29","cited_by_count":79},{"id":"2407.10172","title":"Restoring Images in Adverse Weather Conditions via Histogram Transformer","created":"2024-07-14","cited_by_count":73},{"id":"2303.07945","title":"Edit-A-Video: Single Video Editing with Object-Aware Consistency","created":"2023-03-14","cited_by_count":67},{"id":"2009.03683","title":"Rain rendering for evaluating and improving robustness to bad weather","created":"2020-09-06","cited_by_count":57},{"id":"2501.18590","title":"DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models","created":"2025-01-30","cited_by_count":57},{"id":"2407.21773","title":"RainMamba: Enhanced Locality Learning with State Space Models for Video Deraining","created":"2024-07-31","cited_by_count":56},{"id":"2403.12962","title":"FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation","created":"2024-03-19","cited_by_count":49},{"id":"2207.05621","title":"MSP-Former: Multi-Scale Projection Transformer for Single Image Desnowing","created":"2022-07-12","cited_by_count":39},{"id":"2308.03867","title":"From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal","created":"2023-08-07","cited_by_count":39},{"id":"2211.13226","title":"ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Field","created":"2022-11-23","cited_by_count":37},{"id":"2411.02394","title":"AutoVFX: Physically Realistic Video Editing from Natural Language Instructions","created":"2024-11-04","cited_by_count":27},{"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":"2411.17226","title":"MWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformers","created":"2024-11-26","cited_by_count":24},{"id":"1910.03997","title":"Semantic Understanding of Foggy Scenes with Purely Synthetic Data","created":"2019-10-09","cited_by_count":22},{"id":"2309.13700","title":"Video Adverse-Weather-Component Suppression Network via Weather Messenger and Adversarial Backpropagation","created":"2023-09-24","cited_by_count":21},{"id":"2305.06716","title":"Distracting Downpour: Adversarial Weather Attacks for Motion Estimation","created":"2023-05-11","cited_by_count":15},{"id":"2110.02871","title":"ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods","created":"2021-10-06","cited_by_count":14},{"id":"2503.21442","title":"RainyGS: Efficient Rain Synthesis with Physically-Based Gaussian Splatting","created":"2025-03-27","cited_by_count":13},{"id":"1905.03709","title":"Visualizing the Consequences of Climate Change Using Cycle-Consistent Adversarial Networks","created":"2019-05-02","cited_by_count":12},{"id":"2504.05296","title":"Let it Snow! Animating 3D Gaussian Scenes with Dynamic Weather Effects via Physics-Guided Score Distillation","created":"2025-04-07","cited_by_count":7},{"id":"2001.09531","title":"Using Simulated Data to Generate Images of Climate Change","created":"2020-01-26","cited_by_count":4}],"next_cursor":null}