{"list":"other","total":133,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"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":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"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":"2011.12948","title":"Nerfies: Deformable Neural Radiance Fields","created":"2020-11-25","cited_by_count":1198},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"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":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548},{"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":"2310.19512","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","created":"2023-10-30","cited_by_count":535},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2503.07598","title":"VACE: All-in-One Video Creation and Editing","created":"2025-03-10","cited_by_count":479},{"id":"2310.12190","title":"DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors","created":"2023-10-18","cited_by_count":471},{"id":"2303.09535","title":"FateZero: Fusing Attentions for Zero-shot Text-based Video Editing","created":"2023-03-16","cited_by_count":466},{"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":"2307.10373","title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","created":"2023-07-19","cited_by_count":442},{"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":"2011.12950","title":"Space-time Neural Irradiance Fields for Free-Viewpoint Video","created":"2020-11-25","cited_by_count":414},{"id":"2409.02048","title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","created":"2024-09-03","cited_by_count":403},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"2503.03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","created":"2025-03-05","cited_by_count":341},{"id":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319},{"id":"2303.04761","title":"Video-P2P: Video Editing with Cross-attention Control","created":"2023-03-08","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":"2312.06662","title":"Photorealistic Video Generation with Diffusion Models","created":"2023-12-11","cited_by_count":306},{"id":"2306.08637","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","created":"2023-06-14","cited_by_count":287},{"id":"2503.11647","title":"ReCamMaster: Camera-Controlled Generative Rendering from A Single Video","created":"2025-03-14","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":"2308.08089","title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","created":"2023-08-16","cited_by_count":264},{"id":"2407.13764","title":"Shape of Motion: 4D Reconstruction from a Single Video","created":"2024-07-18","cited_by_count":250},{"id":"2412.04463","title":"MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos","created":"2024-12-05","cited_by_count":228},{"id":"2211.11082","title":"DynIBaR: Neural Dynamic Image-Based Rendering","created":"2022-11-20","cited_by_count":224},{"id":"2204.04153","title":"Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories","created":"2022-04-08","cited_by_count":217},{"id":"2401.15977","title":"Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling","created":"2024-01-29","cited_by_count":211},{"id":"2210.13445","title":"Monocular Dynamic View Synthesis: A Reality Check","created":"2022-10-24","cited_by_count":200},{"id":"2301.02239","title":"Robust Dynamic Radiance Fields","created":"2023-01-05","cited_by_count":194},{"id":"2306.05422","title":"Tracking Everything Everywhere All at Once","created":"2023-06-08","cited_by_count":193},{"id":"2501.03847","title":"Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control","created":"2025-01-07","cited_by_count":185},{"id":"2308.09592","title":"StableVideo: Text-driven Consistency-aware Diffusion Video Editing","created":"2023-08-18","cited_by_count":183},{"id":"2503.14489","title":"Stable Virtual Camera: Generative View Synthesis with Diffusion Models","created":"2025-03-18","cited_by_count":182},{"id":"2404.04319","title":"SpatialTracker: Tracking Any 2D Pixels in 3D Space","created":"2024-04-05","cited_by_count":181},{"id":"2405.17421","title":"MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds","created":"2024-05-27","cited_by_count":179},{"id":"2412.02700","title":"Motion Prompting: Controlling Video Generation with Motion Trajectories","created":"2024-12-03","cited_by_count":178},{"id":"2301.02238","title":"HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling","created":"2023-01-05","cited_by_count":174},{"id":"2508.10934","title":"ViPE: Video Pose Engine for 3D Geometric Perception","created":"2025-08-12","cited_by_count":170},{"id":"2310.05922","title":"FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing","created":"2023-10-09","cited_by_count":167},{"id":"2407.21705","title":"Tora: Trajectory-oriented Diffusion Transformer for Video Generation","created":"2024-07-31","cited_by_count":164},{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161},{"id":"2403.07420","title":"DragAnything: Motion Control for Anything using Entity Representation","created":"2024-03-12","cited_by_count":159},{"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":"2407.06358","title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions","created":"2024-07-08","cited_by_count":146},{"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":"2109.11418","title":"Layered Neural Atlases for Consistent Video Editing","created":"2021-09-23","cited_by_count":137},{"id":"2410.11831","title":"CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos","created":"2024-10-15","cited_by_count":128},{"id":"2311.17009","title":"Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer","created":"2023-11-28","cited_by_count":124},{"id":"2405.14868","title":"Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis","created":"2024-05-23","cited_by_count":117},{"id":"2501.08331","title":"Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise","created":"2025-01-14","cited_by_count":117},{"id":"2312.04524","title":"RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models","created":"2023-12-07","cited_by_count":114},{"id":"2402.14797","title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","created":"2024-02-22","cited_by_count":105},{"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":"2401.00896","title":"TrailBlazer: Trajectory Control for Diffusion-Based Video Generation","created":"2023-12-31","cited_by_count":91},{"id":"2405.20222","title":"MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model","created":"2024-05-30","cited_by_count":89},{"id":"2504.13152","title":"St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World","created":"2025-04-17","cited_by_count":89},{"id":"2507.12462","title":"SpatialTrackerV2: 3D Point Tracking Made Easy","created":"2025-07-16","cited_by_count":87},{"id":"2312.00845","title":"VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models","created":"2023-12-01","cited_by_count":86},{"id":"2309.16496","title":"CCEdit: Creative and Controllable Video Editing via Diffusion Models","created":"2023-09-28","cited_by_count":82},{"id":"2407.15420","title":"Local All-Pair Correspondence for Point Tracking","created":"2024-07-22","cited_by_count":80},{"id":"2312.17681","title":"FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis","created":"2023-12-29","cited_by_count":79},{"id":"2405.15364","title":"NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer","created":"2024-05-24","cited_by_count":79},{"id":"2308.14749","title":"MagicEdit: High-Fidelity and Temporally Coherent Video Editing","created":"2023-08-28","cited_by_count":76},{"id":"2504.06397","title":"PromptHMR: Promptable Human Mesh Recovery","created":"2025-04-08","cited_by_count":76},{"id":"2405.13865","title":"ReVideo: Remake a Video with Motion and Content Control","created":"2024-05-22","cited_by_count":74},{"id":"2502.08639","title":"CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation","created":"2025-02-12","cited_by_count":74},{"id":"2504.14717","title":"TAPIP3D: Tracking Any Point in Persistent 3D Geometry","created":"2025-04-20","cited_by_count":69},{"id":"2410.24211","title":"DELTA: Dense Efficient Long-range 3D Tracking for any video","created":"2024-10-31","cited_by_count":65},{"id":"2411.19324","title":"Trajectory Attention for Fine-grained Video Motion Control","created":"2024-11-28","cited_by_count":63},{"id":"2312.03047","title":"MagicStick: Controllable Video Editing via Control Handle Transformations","created":"2023-12-05","cited_by_count":62},{"id":"2506.04590","title":"Follow-Your-Creation: Empowering 4D Creation through Video Inpainting","created":"2025-06-05","cited_by_count":62},{"id":"2503.16421","title":"MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance","created":"2025-03-20","cited_by_count":61},{"id":"2311.18830","title":"MotionEditor: Editing Video Motion via Content-Aware Diffusion","created":"2023-11-30","cited_by_count":57},{"id":"2405.16537","title":"I2VEdit: First-Frame-Guided Video Editing via Image-to-Video Diffusion Models","created":"2024-05-26","cited_by_count":55}],"next_cursor":"100"}