{"total":161,"rows":[{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548,"area":null},{"id":"2503.11647","title":"ReCamMaster: Camera-Controlled Generative Rendering from A Single Video","created":"2025-03-14","cited_by_count":287,"area":null},{"id":"2412.04463","title":"MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos","created":"2024-12-05","cited_by_count":228,"area":null},{"id":"2508.10934","title":"ViPE: Video Pose Engine for 3D Geometric Perception","created":"2025-08-12","cited_by_count":170,"area":null},{"id":"2503.05638","title":"TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models","created":"2025-03-07","cited_by_count":125,"area":"diffusion"},{"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,"area":"diffusion"},{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105,"area":null},{"id":"2503.18945","title":"Aether: Geometric-Aware Unified World Modeling","created":"2025-03-24","cited_by_count":97,"area":"wm"},{"id":"2412.09621","title":"Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos","created":"2024-12-12","cited_by_count":89,"area":null},{"id":"2511.01266","title":"MotionStream: Real-Time Video Generation with Interactive Motion Controls","created":"2025-11-03","cited_by_count":76,"area":null},{"id":"2501.01895","title":"EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation","created":"2025-01-03","cited_by_count":61,"area":"wm"},{"id":"2503.14445","title":"Bolt3D: Generating 3D Scenes in Seconds","created":"2025-03-18","cited_by_count":59,"area":"diffusion"},{"id":"2506.08015","title":"4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos","created":"2025-06-09","cited_by_count":49,"area":null},{"id":"2503.16396","title":"SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation","created":"2025-03-20","cited_by_count":48,"area":"diffusion"},{"id":"2508.02095","title":"VLM4D: Towards Spatiotemporal Awareness in Vision Language Models","created":"2025-08-04","cited_by_count":46,"area":"lr"},{"id":"2505.18151","title":"WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions","created":"2025-05-23","cited_by_count":45,"area":null},{"id":"2509.19296","title":"Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation","created":"2025-09-23","cited_by_count":41,"area":"diffusion"},{"id":"2509.20358","title":"PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation","created":"2025-09-24","cited_by_count":41,"area":"diffusion"},{"id":"2503.09151","title":"Reangle-A-Video: 4D Video Generation as Video-to-Video Translation","created":"2025-03-12","cited_by_count":35,"area":"diffusion"},{"id":"2503.20785","title":"Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency","created":"2025-03-26","cited_by_count":35,"area":null},{"id":"2512.10935","title":"Any4D: Unified Feed-Forward Metric 4D Reconstruction","created":"2025-12-11","cited_by_count":35,"area":null},{"id":"2508.13154","title":"4DNeX: Feed-Forward 4D Generative Modeling Made Easy","created":"2025-08-18","cited_by_count":34,"area":"diffusion"},{"id":"2506.17220","title":"Emergent Temporal Correspondences from Video Diffusion Transformers","created":"2025-06-20","cited_by_count":31,"area":"diffusion"},{"id":"2507.14501","title":"Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey","created":"2025-07-19","cited_by_count":27,"area":null},{"id":"2501.10928","title":"Generative Physical AI in Vision: A Survey","created":"2025-01-19","cited_by_count":24,"area":null},{"id":"2505.05474","title":"3D Scene Generation: A Survey","created":"2025-05-08","cited_by_count":24,"area":"diffusion"},{"id":"2512.02015","title":"Generative Video Motion Editing with 3D Point Tracks","created":"2025-12-01","cited_by_count":23,"area":null},{"id":"2505.21876","title":"EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance","created":"2025-05-28","cited_by_count":21,"area":"diffusion"},{"id":"2508.03334","title":"Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video Generation","created":"2025-08-05","cited_by_count":21,"area":"diffusion"},{"id":"2510.06208","title":"ShapeGen4D: Towards High Quality 4D Shape Generation from Videos","created":"2025-10-07","cited_by_count":21,"area":null},{"id":"2509.25079","title":"UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation","created":"2025-09-29","cited_by_count":20,"area":"diffusion"},{"id":"2510.20385","title":"Positional Encoding Field","created":"2025-10-23","cited_by_count":20,"area":"diffusion"},{"id":"2507.13344","title":"Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models","created":"2025-07-17","cited_by_count":17,"area":"diffusion"},{"id":"2510.15869","title":"Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery","created":"2025-10-17","cited_by_count":17,"area":null},{"id":"2503.22622","title":"Zero4D: Training-Free 4D Video Generation From Single Video Using Off-the-Shelf Video Diffusion","created":"2025-03-28","cited_by_count":16,"area":"diffusion"},{"id":"2601.16148","title":"ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion","created":"2026-01-22","cited_by_count":16,"area":null},{"id":"2412.20720","title":"4D Gaussian Splatting: Modeling Dynamic Scenes with Native 4D Primitives","created":"2024-12-30","cited_by_count":15,"area":null},{"id":"2503.04641","title":"Simulating the Real World: A Unified Survey of Multimodal Generative Models","created":"2025-03-06","cited_by_count":15,"area":null},{"id":"2503.12024","title":"SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steering","created":"2025-03-15","cited_by_count":15,"area":null},{"id":"2601.14253","title":"Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis","created":"2026-01-20","cited_by_count":15,"area":null},{"id":"2602.14941","title":"AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories","created":"2026-02-16","cited_by_count":15,"area":null},{"id":"2504.16081","title":"Survey of Video Diffusion Models: Foundations, Implementations, and Applications","created":"2025-04-22","cited_by_count":14,"area":"diffusion"},{"id":"2506.18839","title":"4Real-Video-V2: Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation","created":"2025-06-18","cited_by_count":14,"area":null},{"id":"2506.18890","title":"4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time","created":"2025-06-23","cited_by_count":14,"area":null},{"id":"2507.12646","title":"Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos","created":"2025-07-16","cited_by_count":14,"area":"diffusion"},{"id":"2512.05076","title":"BulletTime: Decoupled Control of Time and Camera Pose for Video Generation","created":"2025-12-04","cited_by_count":14,"area":"diffusion"},{"id":"2510.26796","title":"See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting","created":"2025-10-30","cited_by_count":12,"area":null},{"id":"2512.05115","title":"Light-X: Generative 4D Video Rendering with Camera and Illumination Control","created":"2025-12-04","cited_by_count":12,"area":null},{"id":"2601.16982","title":"AnyView: Synthesizing Any Novel View in Dynamic Scenes","created":"2026-01-23","cited_by_count":12,"area":null},{"id":"2604.06168","title":"Action Images: End-to-End Policy Learning via Multiview Video Generation","created":"2026-04-07","cited_by_count":12,"area":"wm"},{"id":"2606.20545","title":"Current World Models Lack a Persistent State Core","created":"2026-06-18","cited_by_count":12,"area":"wm"},{"id":"2504.11092","title":"Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting","created":"2025-04-15","cited_by_count":11,"area":null},{"id":"2511.19827","title":"ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding","created":"2025-11-25","cited_by_count":11,"area":null},{"id":"2512.25075","title":"SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and Time","created":"2025-12-31","cited_by_count":11,"area":"diffusion"},{"id":"2503.21082","title":"Can Video Diffusion Model Reconstruct 4D Geometry?","created":"2025-03-27","cited_by_count":10,"area":"diffusion"},{"id":"2505.16565","title":"M2SVid: End-to-End Inpainting and Refinement for Monocular-to-Stereo Video Conversion","created":"2025-05-22","cited_by_count":10,"area":null},{"id":"2506.09665","title":"VideoMat: Extracting PBR Materials from Video Diffusion Models","created":"2025-06-11","cited_by_count":10,"area":"diffusion"},{"id":"2509.23828","title":"Uni4D-LLM: A Unified SpatioTemporal-Aware VLM for 4D Understanding and Generation","created":"2025-09-28","cited_by_count":10,"area":"mllm"},{"id":"2504.02312","title":"OmniCam: Unified Multimodal Video Generation via Camera Control","created":"2025-04-03","cited_by_count":9,"area":null},{"id":"2602.04876","title":"PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generation","created":"2026-02-04","cited_by_count":9,"area":null},{"id":"2603.20176","title":"LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis","created":"2026-03-20","cited_by_count":9,"area":null},{"id":"2511.18922","title":"One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control","created":"2025-11-24","cited_by_count":8,"area":null},{"id":"2506.06023","title":"Restereo: Diffusion stereo video generation and restoration","created":"2025-06-06","cited_by_count":7,"area":"diffusion"},{"id":"2506.13697","title":"Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry","created":"2025-06-16","cited_by_count":7,"area":null},{"id":"2510.09036","title":"RoDyn: Taming Interactive Robot-Dynamic 2.5D World Model for Robotic Manipulation","created":"2025-10-10","cited_by_count":7,"area":"wm"},{"id":"2511.00503","title":"Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models","created":"2025-11-01","cited_by_count":7,"area":"diffusion"},{"id":"2511.22147","title":"RemedyGS: Defend 3D Gaussian Splatting against Computation Cost Attacks","created":"2025-11-27","cited_by_count":7,"area":null},{"id":"2607.06559","title":"RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation","created":"2026-07-07","cited_by_count":7,"area":"wm"},{"id":"2504.10001","title":"GaussVideoDreamer: 3D Scene Generation with Video Diffusion and Inconsistency-Aware Gaussian Splatting","created":"2025-04-14","cited_by_count":6,"area":"diffusion"},{"id":"2505.00135","title":"Eye2Eye: A Simple Approach for Monocular-to-Stereo Video Synthesis","created":"2025-04-30","cited_by_count":6,"area":null},{"id":"2506.10978","title":"Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models","created":"2025-06-12","cited_by_count":6,"area":"diffusion"},{"id":"2509.06579","title":"CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis","created":"2025-09-08","cited_by_count":6,"area":"diffusion"},{"id":"2511.07409","title":"DIMO: Diverse 3D Motion Generation for Arbitrary Objects","created":"2025-11-10","cited_by_count":6,"area":null},{"id":"2512.02793","title":"IC-World: In-Context Generation for Shared World Modeling","created":"2025-12-01","cited_by_count":6,"area":"wm"},{"id":"2512.05672","title":"InverseCrafter: Efficient Video ReCapture as a Latent Domain Inverse Problem","created":"2025-12-05","cited_by_count":6,"area":"diffusion"},{"id":"2412.07696","title":"SimVS: Simulating World Inconsistencies for Robust View Synthesis","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2412.10718","title":"Grid: Omni Visual Generation","created":"2024-12-14","cited_by_count":5,"area":null},{"id":"2504.12684","title":"SOPHY: Learning to Generate Simulation-Ready Objects with Physical Materials","created":"2025-04-17","cited_by_count":5,"area":null},{"id":"2508.19204","title":"LSD-3D: Large-Scale 3D Driving Scene Generation with Geometry Grounding","created":"2025-08-26","cited_by_count":5,"area":null},{"id":"2510.00978","title":"A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features","created":"2025-10-01","cited_by_count":5,"area":null},{"id":"2512.07821","title":"WorldReel: 4D Video Generation with Consistent Geometry and Motion Modeling","created":"2025-12-08","cited_by_count":5,"area":null},{"id":"2601.04194","title":"Choreographing a World of Dynamic Objects","created":"2026-01-07","cited_by_count":5,"area":null},{"id":"2603.17840","title":"Video Understanding: From Geometry and Semantics to Unified Models","created":"2026-03-18","cited_by_count":5,"area":null},{"id":"2603.28489","title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","created":"2026-03-30","cited_by_count":5,"area":"wm"},{"id":"2506.18792","title":"ViDAR: Video Diffusion-Aware 4D Reconstruction From Monocular Inputs","created":"2025-06-23","cited_by_count":4,"area":"diffusion"},{"id":"2507.16406","title":"Sparse-View 3D Reconstruction: Recent Advances and Open Challenges","created":"2025-07-22","cited_by_count":4,"area":null},{"id":"2509.06950","title":"Scaling Transformer-Based Novel View Synthesis Models with Token Disentanglement and Synthetic Data","created":"2025-09-08","cited_by_count":4,"area":null},{"id":"2510.19255","title":"Advances in 4D Representation: Geometry, Motion, and Interaction","created":"2025-10-22","cited_by_count":4,"area":null},{"id":"2511.18991","title":"View-Consistent Diffusion Representations for 3D-Consistent Video Generation","created":"2025-11-24","cited_by_count":4,"area":"diffusion"},{"id":"2512.10940","title":"OmniView: An All-Seeing Diffusion Model for 3D and 4D View Synthesis","created":"2025-12-11","cited_by_count":4,"area":"diffusion"},{"id":"2601.16214","title":"CamPilot: Improving Camera Control in Video Diffusion Model with Efficient Camera Reward Feedback","created":"2026-01-22","cited_by_count":4,"area":"diffusion"},{"id":"2602.18873","title":"BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generation","created":"2026-02-21","cited_by_count":4,"area":null},{"id":"2603.17989","title":"Versatile Editing of Video Content, Actions, and Dynamics without Training","created":"2026-03-18","cited_by_count":4,"area":null},{"id":"2605.25449","title":"Pantheon360: Taming Digital Twin Generation via 3D-Aware 360{\\deg} Video Diffusion","created":"2026-05-25","cited_by_count":4,"area":"diffusion"},{"id":"2503.15996","title":"Animating the Uncaptured: Humanoid Mesh Animation with Video Diffusion Models","created":"2025-03-20","cited_by_count":3,"area":"diffusion"},{"id":"2511.12921","title":"Generative Photographic Control for Scene-Consistent Video Cinematic Editing","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2512.16915","title":"StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors","created":"2025-12-18","cited_by_count":3,"area":null},{"id":"2602.08961","title":"MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2603.17375","title":"Stereo World Model: Camera-Guided Stereo Video Generation","created":"2026-03-18","cited_by_count":3,"area":"wm"},{"id":"2603.28757","title":"SonoWorld: From One Image to a 3D Audio-Visual Scene","created":"2026-03-30","cited_by_count":3,"area":null}],"next_cursor":"100"}