{"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":"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":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"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":"2305.16213","title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","created":"2023-05-25","cited_by_count":1219},{"id":"2211.09794","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","created":"2022-11-17","cited_by_count":1179},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"2403.17888","title":"2D Gaussian Splatting for Geometrically Accurate Radiance Fields","created":"2024-03-26","cited_by_count":1076},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2309.13101","title":"Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction","created":"2023-09-22","cited_by_count":759},{"id":"2308.09713","title":"Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis","created":"2023-08-18","cited_by_count":737},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"2209.11163","title":"GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images","created":"2022-09-22","cited_by_count":446},{"id":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442},{"id":"2409.02048","title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","created":"2024-09-03","cited_by_count":403},{"id":"1609.02612","title":"Generating Videos with Scene Dynamics","created":"2016-09-08","cited_by_count":376},{"id":"2303.08320","title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","created":"2023-03-15","cited_by_count":331},{"id":"2305.08891","title":"Common Diffusion Noise Schedules and Sample Steps are Flawed","created":"2023-05-15","cited_by_count":310},{"id":"1511.05440","title":"Deep multi-scale video prediction beyond mean square error","created":"2015-11-17","cited_by_count":300},{"id":"2205.11495","title":"Flexible Diffusion Modeling of Long Videos","created":"2022-05-23","cited_by_count":294},{"id":"2305.10474","title":"Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models","created":"2023-05-17","cited_by_count":285},{"id":"1802.07687","title":"Stochastic Video Generation with a Learned Prior","created":"2018-02-21","cited_by_count":245},{"id":"1710.11252","title":"Stochastic Variational Video Prediction","created":"2017-10-30","cited_by_count":234},{"id":"2301.11280","title":"Text-To-4D Dynamic Scene Generation","created":"2023-01-26","cited_by_count":205},{"id":"2312.17142","title":"DreamGaussian4D: Generative 4D Gaussian Splatting","created":"2023-12-28","cited_by_count":194},{"id":"2311.17984","title":"4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling","created":"2023-11-29","cited_by_count":185},{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161},{"id":"2406.10324","title":"L4GM: Large 4D Gaussian Reconstruction Model","created":"2024-06-14","cited_by_count":144},{"id":"2407.17470","title":"SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency","created":"2024-07-24","cited_by_count":144},{"id":"2411.04928","title":"DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion","created":"2024-11-07","cited_by_count":140},{"id":"2211.13757","title":"Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions","created":"2022-11-24","cited_by_count":133},{"id":"2312.17225","title":"4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency","created":"2023-12-28","cited_by_count":117},{"id":"2405.17414","title":"Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control","created":"2024-05-27","cited_by_count":117},{"id":"2311.14603","title":"Animate124: Animating One Image to 4D Dynamic Scene","created":"2023-11-24","cited_by_count":115},{"id":"1610.00527","title":"Video Pixel Networks","created":"2016-10-03","cited_by_count":108},{"id":"2402.14797","title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","created":"2024-02-22","cited_by_count":105},{"id":"2409.12957","title":"3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion","created":"2024-09-19","cited_by_count":101},{"id":"2406.18717","title":"Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videos","created":"2024-06-26","cited_by_count":97},{"id":"2412.07760","title":"SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints","created":"2024-12-10","cited_by_count":93},{"id":"1412.6604","title":"Video (language) modeling: a baseline for generative models of natural videos","created":"2014-12-20","cited_by_count":92},{"id":"2112.02815","title":"Make It Move: Controllable Image-to-Video Generation with Text Descriptions","created":"2021-12-06","cited_by_count":88},{"id":"2106.13195","title":"FitVid: Overfitting in Pixel-Level Video Prediction","created":"2021-06-24","cited_by_count":87},{"id":"2311.16854","title":"A Unified Approach for Text- and Image-guided 4D Scene Generation","created":"2023-11-28","cited_by_count":82},{"id":"1903.01434","title":"VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation","created":"2019-03-04","cited_by_count":74},{"id":"2302.01330","title":"SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections","created":"2023-02-02","cited_by_count":72},{"id":"2301.09637","title":"InfiniCity: Infinite-Scale City Synthesis","created":"2023-01-23","cited_by_count":68},{"id":"2406.07472","title":"4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models","created":"2024-06-11","cited_by_count":64},{"id":"1807.09755","title":"Flow-Grounded Spatial-Temporal Video Prediction from Still Images","created":"2018-07-25","cited_by_count":55},{"id":"1903.04480","title":"Video Generation from Single Semantic Label Map","created":"2019-03-11","cited_by_count":54},{"id":"2411.02319","title":"GenXD: Generating Any 3D and 4D Scenes","created":"2024-11-04","cited_by_count":50},{"id":"2405.18132","title":"EG4D: Explicit Generation of 4D Object without Score Distillation","created":"2024-05-28","cited_by_count":45},{"id":"2401.08742","title":"Efficient4D: Fast Dynamic 3D Object Generation from a Single-view Video","created":"2024-01-16","cited_by_count":44},{"id":"2106.11303","title":"Understanding Object Dynamics for Interactive Image-to-Video Synthesis","created":"2021-06-21","cited_by_count":38},{"id":"2410.16892","title":"VistaDream: Sampling multiview consistent images for single-view scene reconstruction","created":"2024-10-22","cited_by_count":38},{"id":"2312.00739","title":"Adversarial Score Distillation: When score distillation meets GAN","created":"2023-12-01","cited_by_count":15}],"next_cursor":null}