{"list":"other","total":57,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"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":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2303.01469","title":"Consistency Models","created":"2023-03-02","cited_by_count":1822},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"2311.18828","title":"One-step Diffusion with Distribution Matching Distillation","created":"2023-11-30","cited_by_count":1019},{"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":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"1711.09078","title":"Video Enhancement with Task-Oriented Flow","created":"2017-11-24","cited_by_count":619},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2302.08113","title":"MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation","created":"2023-02-16","cited_by_count":536},{"id":"1905.02716","title":"EDVR: Video Restoration with Enhanced Deformable Convolutional Networks","created":"2019-05-07","cited_by_count":494},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"2310.14189","title":"Improved Techniques for Training Consistency Models","created":"2023-10-22","cited_by_count":439},{"id":"2410.12557","title":"One Step Diffusion via Shortcut Models","created":"2024-10-16","cited_by_count":391},{"id":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"id":"2309.15103","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","created":"2023-09-26","cited_by_count":349},{"id":"2104.13371","title":"BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment","created":"2021-04-27","cited_by_count":342},{"id":"2410.10629","title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","created":"2024-10-14","cited_by_count":340},{"id":"2211.04894","title":"Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives","created":"2022-11-09","cited_by_count":320},{"id":"2312.06662","title":"Photorealistic Video Generation with Diffusion Models","created":"2023-12-11","cited_by_count":306},{"id":"2012.02181","title":"BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond","created":"2020-12-03","cited_by_count":304},{"id":"1903.07593","title":"Learning Correspondence from the Cycle-Consistency of Time","created":"2019-03-18","cited_by_count":269},{"id":"1808.00449","title":"Learning Blind Video Temporal Consistency","created":"2018-08-01","cited_by_count":253},{"id":"2008.01928","title":"Component Divide-and-Conquer for Real-World Image Super-Resolution","created":"2020-08-05","cited_by_count":246},{"id":"2006.14613","title":"Space-Time Correspondence as a Contrastive Random Walk","created":"2020-06-25","cited_by_count":239},{"id":"2306.00980","title":"SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds","created":"2023-06-01","cited_by_count":227},{"id":"1812.02898","title":"TDAN: Temporally Deformable Alignment Network for Video Super-Resolution","created":"2018-12-07","cited_by_count":226},{"id":"2410.10733","title":"Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models","created":"2024-10-14","cited_by_count":217},{"id":"2502.01776","title":"Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity","created":"2025-02-03","cited_by_count":217},{"id":"2502.10248","title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","created":"2025-02-14","cited_by_count":168},{"id":"1801.04590","title":"Frame-Recurrent Video Super-Resolution","created":"2018-01-14","cited_by_count":160},{"id":"2408.06070","title":"ControlNeXt: Powerful and Efficient Control for Image and Video Generation","created":"2024-08-12","cited_by_count":159},{"id":"1704.02738","title":"Detail-revealing Deep Video Super-resolution","created":"2017-04-10","cited_by_count":148},{"id":"2111.12704","title":"Investigating Tradeoffs in Real-World Video Super-Resolution","created":"2021-11-24","cited_by_count":134},{"id":"1904.12257","title":"Spatio-Temporal Filter Adaptive Network for Video Deblurring","created":"2019-04-28","cited_by_count":106},{"id":"2007.11803","title":"MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution","created":"2020-07-23","cited_by_count":89},{"id":"2105.10422","title":"LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond","created":"2021-05-21","cited_by_count":88},{"id":"2407.07667","title":"VEnhancer: Generative Space-Time Enhancement for Video Generation","created":"2024-07-10","cited_by_count":64},{"id":"2412.05796","title":"Language-Guided Image Tokenization for Generation","created":"2024-12-08","cited_by_count":36},{"id":"2407.13987","title":"RealViformer: Investigating Attention for Real-World Video Super-Resolution","created":"2024-07-19","cited_by_count":33},{"id":"2502.05179","title":"FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation","created":"2025-02-07","cited_by_count":32},{"id":"2103.15295","title":"Best-Buddy GANs for Highly Detailed Image Super-Resolution","created":"2021-03-29","cited_by_count":30},{"id":"2212.07339","title":"Mitigating Artifacts in Real-World Video Super-Resolution Models","created":"2022-12-14","cited_by_count":29},{"id":"2412.09619","title":"SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training","created":"2024-12-12","cited_by_count":27},{"id":"2111.15288","title":"Revisiting Temporal Alignment for Video Restoration","created":"2021-11-30","cited_by_count":24},{"id":"2408.05710","title":"Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators","created":"2024-08-11","cited_by_count":24},{"id":"2412.07583","title":"Mobile Video Diffusion","created":"2024-12-10","cited_by_count":18},{"id":"2412.00878","title":"Beyond Pixels: Text Enhances Generalization in Real-World Image Restoration","created":"2024-12-01","cited_by_count":17},{"id":"2502.07701","title":"Magic 1-For-1: Generating One Minute Video Clips within One Minute","created":"2025-02-11","cited_by_count":10}],"next_cursor":null}