{"list":"other","total":69,"rows":[{"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":"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":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"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":"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":"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":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2310.19512","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","created":"2023-10-30","cited_by_count":535},{"id":"1612.00222","title":"Interaction Networks for Learning about Objects, Relations and Physics","created":"2016-12-01","cited_by_count":509},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484},{"id":"2310.12190","title":"DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors","created":"2023-10-18","cited_by_count":471},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455},{"id":"2311.12198","title":"PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics","created":"2023-11-20","cited_by_count":377},{"id":"2311.04145","title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","created":"2023-11-07","cited_by_count":350},{"id":"2309.15103","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","created":"2023-09-26","cited_by_count":349},{"id":"2110.04994","title":"Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans","created":"2021-10-11","cited_by_count":336},{"id":"2312.06662","title":"Photorealistic Video Generation with Diffusion Models","created":"2023-12-11","cited_by_count":306},{"id":"2310.11441","title":"Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V","created":"2023-10-17","cited_by_count":299},{"id":"2403.12013","title":"GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image","created":"2024-03-18","cited_by_count":286},{"id":"2305.10474","title":"Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models","created":"2023-05-17","cited_by_count":285},{"id":"1910.00935","title":"DiffTaichi: Differentiable Programming for Physical Simulation","created":"2019-10-01","cited_by_count":258},{"id":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255},{"id":"1806.01242","title":"Graph networks as learnable physics engines for inference and control","created":"2018-06-04","cited_by_count":244},{"id":"2304.06790","title":"Inpaint Anything: Segment Anything Meets Image Inpainting","created":"2023-04-13","cited_by_count":233},{"id":"2310.20700","title":"SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction","created":"2023-10-31","cited_by_count":233},{"id":"1810.01566","title":"Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids","created":"2018-10-03","cited_by_count":220},{"id":"2203.14367","title":"Thin-Plate Spline Motion Model for Image Animation","created":"2022-03-27","cited_by_count":210},{"id":"2312.04433","title":"DreamVideo: Composing Your Dream Videos with Customized Subject and Motion","created":"2023-12-07","cited_by_count":188},{"id":"2303.05512","title":"PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification","created":"2023-03-09","cited_by_count":154},{"id":"2005.05751","title":"Unpaired Motion Style Transfer from Video to Animation","created":"2020-05-12","cited_by_count":94},{"id":"2309.07906","title":"Generative Image Dynamics","created":"2023-09-14","cited_by_count":94},{"id":"1806.08047","title":"Flexible Neural Representation for Physics Prediction","created":"2018-06-21","cited_by_count":91},{"id":"1906.03853","title":"DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions","created":"2019-06-10","cited_by_count":63},{"id":"2311.12631","title":"GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning","created":"2023-11-21","cited_by_count":61},{"id":"1812.02246","title":"Photo Wake-Up: 3D Character Animation from a Single Photo","created":"2018-12-05","cited_by_count":60},{"id":"2310.10769","title":"LAMP: Learn A Motion Pattern for Few-Shot-Based Video Generation","created":"2023-10-16","cited_by_count":59},{"id":"2004.13664","title":"Visual Grounding of Learned Physical Models","created":"2020-04-28","cited_by_count":55},{"id":"2311.12792","title":"Intrinsic Image Decomposition via Ordinal Shading","created":"2023-11-21","cited_by_count":53},{"id":"2404.04242","title":"Physical Property Understanding from Language-Embedded Feature Fields","created":"2024-04-05","cited_by_count":48},{"id":"2112.03051","title":"Controllable Animation of Fluid Elements in Still Images","created":"2021-12-06","cited_by_count":45},{"id":"2210.01794","title":"Implicit Warping for Animation with Image Sets","created":"2022-10-04","cited_by_count":45},{"id":"2312.02928","title":"LivePhoto: Real Image Animation with Text-guided Motion Control","created":"2023-12-05","cited_by_count":44},{"id":"2107.02790","title":"iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis","created":"2021-07-06","cited_by_count":42},{"id":"2401.18085","title":"Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators","created":"2024-01-31","cited_by_count":39},{"id":"2106.11303","title":"Understanding Object Dynamics for Interactive Image-to-Video Synthesis","created":"2021-06-21","cited_by_count":38},{"id":"1808.03246","title":"Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing","created":"2018-08-09","cited_by_count":36},{"id":"2404.09833","title":"Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video","created":"2024-04-15","cited_by_count":26},{"id":"2312.03793","title":"AnimateZero: Video Diffusion Models are Zero-Shot Image Animators","created":"2023-12-06","cited_by_count":19},{"id":"1904.06580","title":"Combining Physical Simulators and Object-Based Networks for Control","created":"2019-04-13","cited_by_count":18},{"id":"2309.02434","title":"ReliTalk: Relightable Talking Portrait Generation from a Single Video","created":"2023-09-05","cited_by_count":12},{"id":"1807.09245","title":"Visual Dynamics: Stochastic Future Generation via Layered Cross Convolutional Networks","created":"2018-07-24","cited_by_count":11},{"id":"2312.03698","title":"Intrinsic Harmonization for Illumination-Aware Compositing","created":"2023-12-06","cited_by_count":11},{"id":"2112.01502","title":"Dimensions of Motion: Monocular Prediction through Flow Subspaces","created":"2021-12-02","cited_by_count":10},{"id":"2210.02553","title":"Water Simulation and Rendering from a Still Photograph","created":"2022-10-05","cited_by_count":5}],"next_cursor":null}