{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"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":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"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":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2011.12948","title":"Nerfies: Deformable Neural Radiance Fields","created":"2020-11-25","cited_by_count":1198},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"2011.13084","title":"Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes","created":"2020-11-26","cited_by_count":751},{"id":"2301.10241","title":"K-Planes: Explicit Radiance Fields in Space, Time, and Appearance","created":"2023-01-24","cited_by_count":746},{"id":"2308.09713","title":"Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis","created":"2023-08-18","cited_by_count":737},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"2301.09632","title":"HexPlane: A Fast Representation for Dynamic Scenes","created":"2023-01-23","cited_by_count":587},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455},{"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":"2105.06468","title":"Dynamic View Synthesis from Dynamic Monocular Video","created":"2021-05-13","cited_by_count":420},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"2306.08637","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","created":"2023-06-14","cited_by_count":287},{"id":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276},{"id":"2407.13764","title":"Shape of Motion: 4D Reconstruction from a Single Video","created":"2024-07-18","cited_by_count":250},{"id":"2304.11968","title":"Track Anything: Segment Anything Meets Videos","created":"2023-04-24","cited_by_count":234},{"id":"2211.11082","title":"DynIBaR: Neural Dynamic Image-Based Rendering","created":"2022-11-20","cited_by_count":224},{"id":"2303.06042","title":"MVImgNet: A Large-scale Dataset of Multi-view Images","created":"2023-03-10","cited_by_count":220},{"id":"2301.11280","title":"Text-To-4D Dynamic Scene Generation","created":"2023-01-26","cited_by_count":205},{"id":"2210.13445","title":"Monocular Dynamic View Synthesis: A Reality Check","created":"2022-10-24","cited_by_count":200},{"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":"2405.17421","title":"MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds","created":"2024-05-27","cited_by_count":179},{"id":"2301.02238","title":"HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling","created":"2023-01-05","cited_by_count":174},{"id":"2402.03162","title":"Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion","created":"2024-02-05","cited_by_count":167},{"id":"2004.01294","title":"Novel View Synthesis of Dynamic Scenes with Globally Coherent Depths from a Monocular Camera","created":"2020-04-02","cited_by_count":166},{"id":"2202.08614","title":"Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-time","created":"2022-02-17","cited_by_count":165},{"id":"2407.12781","title":"VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control","created":"2024-07-17","cited_by_count":156},{"id":"2306.09310","title":"Infinite Photorealistic Worlds using Procedural Generation","created":"2023-06-15","cited_by_count":147},{"id":"2406.10324","title":"L4GM: Large 4D Gaussian Reconstruction Model","created":"2024-06-14","cited_by_count":144},{"id":"2311.02848","title":"Consistent4D: Consistent 360{\\deg} Dynamic Object Generation from Monocular Video","created":"2023-11-06","cited_by_count":125},{"id":"2312.00112","title":"DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting","created":"2023-11-30","cited_by_count":124},{"id":"2406.10126","title":"Training-free Camera Control for Video Generation","created":"2024-06-14","cited_by_count":122},{"id":"1904.11111","title":"Learning the Depths of Moving People by Watching Frozen People","created":"2019-04-25","cited_by_count":120},{"id":"2405.14868","title":"Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis","created":"2024-05-23","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":"2402.14797","title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","created":"2024-02-22","cited_by_count":105},{"id":"2403.16182","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","created":"2024-03-24","cited_by_count":95},{"id":"2403.17920","title":"TC4D: Trajectory-Conditioned Text-to-4D Generation","created":"2024-03-26","cited_by_count":77},{"id":"2411.05003","title":"ReCapture: Generative Video Camera Controls for User-Provided Videos using Masked Video Fine-Tuning","created":"2024-11-07","cited_by_count":70},{"id":"2411.02319","title":"GenXD: Generating Any 3D and 4D Scenes","created":"2024-11-04","cited_by_count":50},{"id":"2401.08742","title":"Efficient4D: Fast Dynamic 3D Object Generation from a Single-view Video","created":"2024-01-16","cited_by_count":44},{"id":"2406.08659","title":"Vivid-ZOO: Multi-View Video Generation with Diffusion Model","created":"2024-06-12","cited_by_count":40},{"id":"2310.18999","title":"DynPoint: Dynamic Neural Point For View Synthesis","created":"2023-10-29","cited_by_count":37},{"id":"2310.08587","title":"Pseudo-Generalized Dynamic View Synthesis from a Video","created":"2023-10-12","cited_by_count":27},{"id":"2312.02135","title":"Fast View Synthesis of Casual Videos with Soup-of-Planes","created":"2023-12-04","cited_by_count":22}],"next_cursor":null}