{"total":100,"rows":[{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161,"area":"diffusion"},{"id":"2407.12781","title":"VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control","created":"2024-07-17","cited_by_count":156,"area":"diffusion"},{"id":"2411.18673","title":"AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers","created":"2024-11-27","cited_by_count":154,"area":"diffusion"},{"id":"2407.17470","title":"SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency","created":"2024-07-24","cited_by_count":144,"area":"diffusion"},{"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,"area":"diffusion"},{"id":"2412.12091","title":"Wonderland: Navigating 3D Scenes from a Single Image","created":"2024-12-16","cited_by_count":99,"area":"diffusion"},{"id":"2412.07760","title":"SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints","created":"2024-12-10","cited_by_count":93,"area":"diffusion"},{"id":"2407.11398","title":"Animate3D: Animating Any 3D Model with Multi-view Video Diffusion","created":"2024-07-16","cited_by_count":56,"area":"diffusion"},{"id":"2411.02319","title":"GenXD: Generating Any 3D and 4D Scenes","created":"2024-11-04","cited_by_count":50,"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":"2405.18132","title":"EG4D: Explicit Generation of 4D Object without Score Distillation","created":"2024-05-28","cited_by_count":45,"area":"diffusion"},{"id":"2508.10898","title":"Puppeteer: Rig and Animate Your 3D Models","created":"2025-08-14","cited_by_count":43,"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":"2406.08659","title":"Vivid-ZOO: Multi-View Video Generation with Diffusion Model","created":"2024-06-12","cited_by_count":40,"area":"diffusion"},{"id":"2501.00601","title":"DreamDrive: Generative 4D Scene Modeling from Street View Images","created":"2024-12-31","cited_by_count":35,"area":"wm"},{"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":"2507.23785","title":"Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis","created":"2025-07-31","cited_by_count":33,"area":"diffusion"},{"id":"2506.09982","title":"AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation","created":"2025-06-11","cited_by_count":32,"area":null},{"id":"2408.04631","title":"Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics","created":"2024-08-08","cited_by_count":28,"area":null},{"id":"2410.10774","title":"Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention","created":"2024-10-14","cited_by_count":24,"area":"diffusion"},{"id":"2409.07179","title":"Phy124: Fast Physics-Driven 4D Content Generation from a Single Image","created":"2024-09-11","cited_by_count":23,"area":"diffusion"},{"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":"2405.17532","title":"ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance","created":"2024-05-27","cited_by_count":18,"area":"diffusion"},{"id":"2510.12785","title":"MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars","created":"2025-10-14","cited_by_count":17,"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":"2407.12684","title":"4Dynamic: Text-to-4D Generation with Hybrid Priors","created":"2024-07-17","cited_by_count":15,"area":"diffusion"},{"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":"2506.19851","title":"AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models","created":"2025-06-24","cited_by_count":15,"area":"diffusion"},{"id":"2511.08585","title":"Simulating the Visual World with Artificial Intelligence: A Roadmap","created":"2025-11-11","cited_by_count":15,"area":"wm"},{"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":"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":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14,"area":null},{"id":"2506.07489","title":"Drive Any Mesh: 4D Latent Diffusion for Mesh Deformation from Video","created":"2025-06-09","cited_by_count":12,"area":"diffusion"},{"id":"2601.05251","title":"Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video","created":"2026-01-08","cited_by_count":12,"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":"2502.08377","title":"Not All Frame Features Are Equal: Video-to-4D Generation via Decoupling Dynamic-Static Features","created":"2025-02-12","cited_by_count":10,"area":null},{"id":"2503.21082","title":"Can Video Diffusion Model Reconstruct 4D Geometry?","created":"2025-03-27","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":"2503.17827","title":"4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding","created":"2025-03-22","cited_by_count":8,"area":"mllm"},{"id":"2607.01766","title":"SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation","created":"2026-07-02","cited_by_count":8,"area":"agents"},{"id":"2412.05278","title":"Birth and Death of a Rose","created":"2024-12-06","cited_by_count":7,"area":null},{"id":"2412.19142","title":"CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting","created":"2024-12-26","cited_by_count":7,"area":null},{"id":"2504.08366","title":"In-2-4D: Inbetweening from Two Single-View Images to 4D Generation","created":"2025-04-11","cited_by_count":7,"area":null},{"id":"2509.24997","title":"PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusion","created":"2025-09-29","cited_by_count":7,"area":"diffusion"},{"id":"2603.13435","title":"CtrlAttack: A Unified Attack on World-Model Control in Diffusion Models","created":"2026-03-13","cited_by_count":7,"area":"wm"},{"id":"2503.06053","title":"DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation","created":"2025-03-08","cited_by_count":6,"area":null},{"id":"2507.04547","title":"FB-Diff: Fourier Basis-guided Diffusion for Temporal Interpolation of 4D Medical Imaging","created":"2025-07-06","cited_by_count":6,"area":"diffusion"},{"id":"2510.12768","title":"Uncertainty Matters in Dynamic Gaussian Splatting for Monocular 4D Reconstruction","created":"2025-10-14","cited_by_count":6,"area":null},{"id":"2511.07409","title":"DIMO: Diverse 3D Motion Generation for Arbitrary Objects","created":"2025-11-10","cited_by_count":6,"area":null},{"id":"2606.31388","title":"One Video, One World: Turning Monocular Video into Physical 4D Scenes","created":"2026-06-30","cited_by_count":6,"area":null},{"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":"2412.20422","title":"Bringing Objects to Life: training-free 4D generation from 3D objects through view consistent noise","created":"2024-12-29","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":"2509.10687","title":"Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation","created":"2025-09-12","cited_by_count":5,"area":null},{"id":"2512.12534","title":"Animus3D: Text-driven 3D Animation via Motion Score Distillation","created":"2025-12-14","cited_by_count":5,"area":"diffusion"},{"id":"2601.04194","title":"Choreographing a World of Dynamic Objects","created":"2026-01-07","cited_by_count":5,"area":null},{"id":"2602.03890","title":"4DPC$^2$hat: Towards Dynamic Point Cloud Understanding with Failure-Aware Bootstrapping","created":"2026-02-03","cited_by_count":5,"area":"mllm"},{"id":"2602.24290","title":"UFO-4D: Unposed Feedforward 4D Reconstruction from Two Images","created":"2026-02-27","cited_by_count":5,"area":null},{"id":"2503.08032","title":"HOFAR: High-Order Augmentation of Flow Autoregressive Transformers","created":"2025-03-11","cited_by_count":4,"area":"diffusion"},{"id":"2510.19255","title":"Advances in 4D Representation: Geometry, Motion, and Interaction","created":"2025-10-22","cited_by_count":4,"area":null},{"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":"2604.26917","title":"AnimateAnyMesh++: A Flexible Feed-Forward Framework for High-Fidelity Text-Driven Mesh Animation","created":"2026-04-29","cited_by_count":4,"area":null},{"id":"2504.12825","title":"TwoSquared: 4D Generation from 2D Image Pairs","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2508.04467","title":"4DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generation","created":"2025-08-06","cited_by_count":3,"area":"diffusion"},{"id":"2509.11092","title":"PanoLora: Bridging Perspective and Panoramic Video Generation with LoRA Adaptation","created":"2025-09-14","cited_by_count":3,"area":null},{"id":"2604.21592","title":"Sculpt4D: Generating 4D Shapes via Sparse-Attention Diffusion Transformers","created":"2026-04-23","cited_by_count":3,"area":"diffusion"},{"id":"2605.17248","title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","created":"2026-05-17","cited_by_count":3,"area":"diffusion"},{"id":"2504.18318","title":"STP4D: Spatio-Temporal-Prompt Consistent Modeling for Text-to-4D Gaussian Splatting","created":"2025-04-25","cited_by_count":2,"area":"diffusion"},{"id":"2510.23605","title":"Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2512.10860","title":"SWiT-4D: Sliding-Window Transformer for Lossless and Parameter-Free Temporal 4D Generation","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2602.18830","title":"Spatial-Temporal State Propagation Autoregressive Model for 4D Object Generation","created":"2026-02-21","cited_by_count":2,"area":null},{"id":"2606.09187","title":"CP4D: Compositional Physics-aware 4D Scene Generation","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2407.04697","title":"VCoME: Verbal Video Composition with Multimodal Editing Effects","created":"2024-07-05","cited_by_count":1,"area":null},{"id":"2503.11945","title":"Your Text Encoder Can Be An Object-Level Watermarking Controller","created":"2025-03-15","cited_by_count":1,"area":"safety"},{"id":"2503.14501","title":"Advances in 4D Generation: A Survey","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2508.06715","title":"Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2512.05272","title":"Inferring Compositional 4D Scenes without Ever Seeing One","created":"2025-12-04","cited_by_count":1,"area":null},{"id":"2512.06158","title":"Tracking-Guided 4D Generation: Foundation-Tracker Motion Priors for 3D Model Animation","created":"2025-12-05","cited_by_count":1,"area":null},{"id":"2602.19089","title":"Ani3DHuman: Photorealistic 3D Human Animation with Self-guided Stochastic Sampling","created":"2026-02-22","cited_by_count":1,"area":"diffusion"},{"id":"2604.22700","title":"4DLoG: Generative Modeling of Neurodegenerative Brain Anatomy with 4D Longitudinal Diffusion Model","created":"2026-04-24","cited_by_count":1,"area":"diffusion"},{"id":"2605.19786","title":"Fast 4D Mesh Generation by Spatio-Temporal Attention Chains","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2607.08246","title":"SkelGen4D: Weakly-Supervised Skeleton-Based 4D Generation for Text-Driven Mesh Animation","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2608.12314","title":"StateFlow: Building, Evolving, and Accessing 3D World States for Previsualization","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2412.03407","title":"Skel3D: Skeleton Guided Novel View Synthesis","created":"2024-12-04","cited_by_count":0,"area":"diffusion"},{"id":"2509.00403","title":"DevilSight: Augmenting Monocular Human Avatar Reconstruction through a Virtual Perspective","created":"2025-08-30","cited_by_count":0,"area":null},{"id":"2511.00248","title":"Object-Aware 4D Human Motion Generation","created":"2025-10-31","cited_by_count":0,"area":"diffusion"},{"id":"2512.20531","title":"SirenPose: Dynamic Scene Reconstruction via Geometric Supervision","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2512.22294","title":"A Three-Level Alignment Framework for Large-Scale 3D Retrieval and Controlled 4D Generation","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2602.04271","title":"SkeletonGaussian: Editable 4D Generation through Gaussian Skeletonization","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.29572","title":"Turbo4DGen: Ultra-Fast Acceleration for 4D Generation","created":"2026-01-24","cited_by_count":0,"area":"wm"},{"id":"2605.04527","title":"Velox: Learning Representations of 4D Geometry and Appearance","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.13838","title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","created":"2026-05-13","cited_by_count":0,"area":"diffusion"},{"id":"2606.10988","title":"AnimaSpark: A Feed-Forward Method for Animating Arbitrary 3D Objects","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.12189","title":"DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2607.02516","title":"Alignment Is All You Need For X-to-4D Generation","created":"2026-07-02","cited_by_count":0,"area":"diffusion"},{"id":"2607.12206","title":"RegHead: Non-Humanoid Head Blendshapes via Feed-Forward Registration","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.31113","title":"BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.34271","title":"Scaling Versatile 3D Assets Editing with a Million-Scale Dataset","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.11181","title":"MATE4D: Matrix-Guided Editable 4D Generation from a Single Image","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}