{"total":104,"rows":[{"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,"area":null},{"id":"2409.08270","title":"FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally","created":"2024-09-12","cited_by_count":58,"area":null},{"id":"2502.20220","title":"Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars","created":"2025-02-27","cited_by_count":53,"area":null},{"id":"2411.02319","title":"GenXD: Generating Any 3D and 4D Scenes","created":"2024-11-04","cited_by_count":50,"area":null},{"id":"2412.03526","title":"Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos","created":"2024-12-04","cited_by_count":49,"area":null},{"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":"2508.10898","title":"Puppeteer: Rig and Animate Your 3D Models","created":"2025-08-14","cited_by_count":43,"area":null},{"id":"2503.06955","title":"Motion Anything: Any to Motion Generation","created":"2025-03-10","cited_by_count":42,"area":null},{"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":"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":"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":"2507.05763","title":"DreamArt: Generating Interactable Articulated Objects from a Single Image","created":"2025-07-08","cited_by_count":25,"area":null},{"id":"2411.16800","title":"Phys4DGen: Physics-Compliant 4D Generation with Multi-Material Composition Perception","created":"2024-11-25","cited_by_count":23,"area":null},{"id":"2510.06208","title":"ShapeGen4D: Towards High Quality 4D Shape Generation from Videos","created":"2025-10-07","cited_by_count":21,"area":null},{"id":"2506.06440","title":"Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulation","created":"2025-06-06","cited_by_count":20,"area":null},{"id":"2412.06234","title":"Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction","created":"2024-12-09","cited_by_count":18,"area":null},{"id":"2501.08983","title":"Compositional Generative Model of Unbounded 4D Cities","created":"2025-01-15","cited_by_count":17,"area":null},{"id":"2601.16148","title":"ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion","created":"2026-01-22","cited_by_count":16,"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":"2506.09997","title":"DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos","created":"2025-06-11","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":"2604.15239","title":"TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens","created":"2026-04-16","cited_by_count":15,"area":null},{"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":"2503.20776","title":"Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields","created":"2025-03-26","cited_by_count":13,"area":null},{"id":"2601.05251","title":"Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video","created":"2026-01-08","cited_by_count":12,"area":null},{"id":"2412.04464","title":"DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction","created":"2024-12-05","cited_by_count":11,"area":null},{"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":"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":"2508.13911","title":"PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis","created":"2025-08-19","cited_by_count":10,"area":null},{"id":"2506.22432","title":"Shape-for-Motion: Precise and Consistent Video Editing with 3D Proxy","created":"2025-06-27","cited_by_count":9,"area":null},{"id":"2508.07409","title":"CharacterShot: Controllable and Consistent 4D Character Animation","created":"2025-08-10","cited_by_count":9,"area":null},{"id":"2512.03210","title":"Flux4D: Flow-based Unsupervised 4D Reconstruction","created":"2025-12-02","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":"2507.18678","title":"Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting","created":"2025-07-24","cited_by_count":8,"area":null},{"id":"2512.14284","title":"SS4D: Native 4D Generative Model via Structured Spacetime Latents","created":"2025-12-16","cited_by_count":8,"area":null},{"id":"2412.05278","title":"Birth and Death of a Rose","created":"2024-12-06","cited_by_count":7,"area":null},{"id":"2502.03465","title":"Seeing World Dynamics in a Nutshell","created":"2025-02-05","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":"2509.24209","title":"Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-view Videos","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2605.21472","title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","created":"2026-05-20","cited_by_count":7,"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":"2412.20422","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":"2503.04257","title":"How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2503.14698","title":"Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting","created":"2025-03-18","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":"2512.07821","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":"2506.19798","title":"CoCo4D: Comprehensive and Complex 4D Scene Generation","created":"2025-06-24","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":"2601.14103","title":"Interp3D: Correspondence-aware Interpolation for Generative Textured 3D Morphing","created":"2026-01-20","cited_by_count":4,"area":null},{"id":"2602.01723","title":"FastPhysGS: Accelerating Physics-based Dynamic 3DGS Simulation via Interior Completion and Adaptive Optimization","created":"2026-02-02","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":"2602.06548","title":"NECromancer: Breathing Life into Skeletons via BVH Animation","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2604.07350","title":"Fast Spatial Memory with Elastic Test-Time Training","created":"2026-04-08","cited_by_count":3,"area":null},{"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":"2512.05044","title":"Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generation","created":"2025-12-04","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":"2512.17717","title":"FlexAvatar: Flexible Large Reconstruction Model for Animatable Gaussian Head Avatars with Detailed Deformation","created":"2025-12-19","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":"2605.22190","title":"No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos","created":"2026-05-21","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":"2606.23688","title":"Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2503.14501","title":"Advances in 4D Generation: A Survey","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2510.18101","title":"From Volume Rendering to 3D Gaussian Splatting: Theory and Applications","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2511.16662","title":"TriDiff-4D: Fast 4D Generation through Diffusion-based Triplane Re-posing","created":"2025-11-20","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":"2603.18639","title":"OrthoPhys: Physically Plausible Video Generation with Orthogonal-View Geometry Guidance","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2604.09688","title":"Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2605.19786","title":"Fast 4D Mesh Generation by Spatio-Temporal Attention Chains","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2605.26109","title":"Helix4D: Complex 4D Mesh Generation","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2606.25344","title":"Follow Your Track: Precise Skeleton Animation Controlled by 3D Trajectories","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2609.01823","title":"Kirin: Animal Motion Generation from In-the-Wild Video","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.39960","title":"Reconstructing the Dynamic World: A Representation-Centric View of 4D Scene Reconstruction","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2506.24121","title":"TextMesh4D: Zero-shot Text-to-4D Mesh Generation","created":"2025-06-30","cited_by_count":0,"area":null},{"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":"2512.20531","title":"SirenPose: Dynamic Scene Reconstruction via Geometric Supervision","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2603.13783","title":"RetimeGS: Continuous-Time Reconstruction of 4D Gaussian Splatting","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2603.29734","title":"GRVS: a Generalizable and Recurrent Approach to Monocular Dynamic View Synthesis","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.02799","title":"UNICA: A Unified Neural Framework for Controllable 3D Avatars","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.27422","title":"Difix3D-W: Distractor-Free Few-Shot 3D Gaussian Splatting in the Wild","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.04527","title":"Velox: Learning Representations of 4D Geometry and Appearance","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.22342","title":"4D-GSW: Kinematic-Aware Spatio-Temporal Consistent Watermarking for 4D Gaussian Splatting","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.02491","title":"MORPHOS: Autoregressive 4D Generation with Temporal Structured Latents","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.04593","title":"4D Reconstruction from Sparse Dynamic Cameras","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.05162","title":"Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text","created":"2026-06-03","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":"2606.19156","title":"Hand-4DGS: Feed-Forward 3D Gaussian Splatting for 4D Hand Reconstruction from Egocentric Videos","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.28215","title":"HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2606.30347","title":"FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.00157","title":"Progressive Pose-Guided 4D Animal Reconstruction from Monocular Video","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.04661","title":"Targeted Structure Completion for Sparse-View 3D Reconstruction in Autonomous Driving","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.12206","title":"RegHead: Non-Humanoid Head Blendshapes via Feed-Forward Registration","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.27634","title":"4DHumanDiff: Direct Text-to-4DGS Generation for Consistent 360-Degree Dynamic Humans","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.07598","title":"NewtonGS: Physics-Structured Object-Level Neural Newtonian Dynamics for Gaussian Scene Animation","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.11077","title":"Learning Gaussian Structure: Intervention-Guided Density Control for Feed-Forward Driving Reconstruction","created":"2026-08-11","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}],"next_cursor":"100"}