{"list":"other","total":76,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"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":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249},{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247},{"id":"2309.16237","title":"Object Motion Guided Human Motion Synthesis","created":"2023-09-28","cited_by_count":212},{"id":"2308.16905","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","created":"2023-08-31","cited_by_count":182},{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161},{"id":"2311.16097","title":"CG-HOI: Contact-Guided 3D Human-Object Interaction Generation","created":"2023-11-27","cited_by_count":138},{"id":"2403.08629","title":"Scaling Up Dynamic Human-Scene Interaction Modeling","created":"2024-03-13","cited_by_count":137},{"id":"2409.06662","title":"World-Grounded Human Motion Recovery via Gravity-View Coordinates","created":"2024-09-10","cited_by_count":137},{"id":"2410.13571","title":"DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation","created":"2024-10-17","cited_by_count":123},{"id":"2412.09621","title":"Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos","created":"2024-12-12","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":"2212.10621","title":"Full-Body Articulated Human-Object Interaction","created":"2022-12-20","cited_by_count":78},{"id":"2403.17920","title":"TC4D: Trajectory-Conditioned Text-to-4D Generation","created":"2024-03-26","cited_by_count":77},{"id":"2502.19459","title":"ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting","created":"2025-02-26","cited_by_count":67},{"id":"2504.07961","title":"Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction","created":"2025-04-10","cited_by_count":67},{"id":"2303.04805","title":"X-Avatar: Expressive Human Avatars","created":"2023-03-08","cited_by_count":66},{"id":"2404.03736","title":"SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer","created":"2024-04-04","cited_by_count":61},{"id":"2410.03187","title":"Autonomous Character-Scene Interaction Synthesis from Text Instruction","created":"2024-10-04","cited_by_count":56},{"id":"2409.11211","title":"SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstruction","created":"2024-09-17","cited_by_count":52},{"id":"2412.12093","title":"CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models","created":"2024-12-16","cited_by_count":52},{"id":"2412.12861","title":"Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera","created":"2024-12-17","cited_by_count":51},{"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},{"id":"2404.11151","title":"REACTO: Reconstructing Articulated Objects from a Single Video","created":"2024-04-17","cited_by_count":45},{"id":"2411.11921","title":"DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes","created":"2024-11-18","cited_by_count":45},{"id":"2406.19353","title":"CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement","created":"2024-06-27","cited_by_count":44},{"id":"2303.13129","title":"Task-Oriented Human-Object Interactions Generation with Implicit Neural Representations","created":"2023-03-23","cited_by_count":42},{"id":"2412.11596","title":"MeshArt: Generating Articulated Meshes with Structure-Guided Transformers","created":"2024-12-16","cited_by_count":41},{"id":"2311.17737","title":"GenZI: Zero-Shot 3D Human-Scene Interaction Generation","created":"2023-11-29","cited_by_count":40},{"id":"2108.08420","title":"D3D-HOI: Dynamic 3D Human-Object Interactions from Videos","created":"2021-08-19","cited_by_count":39},{"id":"2203.16531","title":"Understanding 3D Object Articulation in Internet Videos","created":"2022-03-30","cited_by_count":36},{"id":"2503.08135","title":"ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting","created":"2025-03-11","cited_by_count":35},{"id":"2503.10437","title":"4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models","created":"2025-03-13","cited_by_count":35},{"id":"2503.20785","title":"Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency","created":"2025-03-26","cited_by_count":35},{"id":"2503.09631","title":"V2M4: 4D Mesh Animation Reconstruction from a Single Monocular Video","created":"2025-03-11","cited_by_count":33},{"id":"2507.23785","title":"Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis","created":"2025-07-31","cited_by_count":33},{"id":"2504.10414","title":"HUMOTO: A 4D Dataset of Mocap Human Object Interactions","created":"2025-04-14","cited_by_count":31},{"id":"2503.21761","title":"Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video","created":"2025-03-27","cited_by_count":29},{"id":"2412.04462","title":"4Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion","created":"2024-12-05","cited_by_count":27},{"id":"2504.01956","title":"VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step","created":"2025-04-02","cited_by_count":27},{"id":"2412.18600","title":"ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation","created":"2024-12-24","cited_by_count":25},{"id":"2406.16623","title":"Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesis","created":"2024-06-24","cited_by_count":24},{"id":"2412.07237","title":"ArtFormer: Controllable Generation of Diverse 3D Articulated Objects","created":"2024-12-10","cited_by_count":22},{"id":"2507.23782","title":"MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion","created":"2025-07-31","cited_by_count":19},{"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},{"id":"2601.14253","title":"Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis","created":"2026-01-20","cited_by_count":15},{"id":"2503.16822","title":"RigGS: Rigging of 3D Gaussians for Modeling Articulated Objects in Videos","created":"2025-03-21","cited_by_count":14},{"id":"2506.08797","title":"HunyuanVideo-HOMA: Generic Human-Object Interaction in Multimodal Driven Human Animation","created":"2025-06-10","cited_by_count":14},{"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},{"id":"2504.02747","title":"GEOPARD: Geometric Pretraining for Articulation Prediction in 3D Shapes","created":"2025-04-03","cited_by_count":13},{"id":"2505.22859","title":"4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians","created":"2025-05-28","cited_by_count":13},{"id":"2505.24315","title":"InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing","created":"2025-05-30","cited_by_count":13},{"id":"2506.03594","title":"SplArt: Articulation Estimation and Part-Level Reconstruction with 3D Gaussian Splatting","created":"2025-06-04","cited_by_count":13},{"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},{"id":"2412.00932","title":"FIction: 4D Future Interaction Prediction from Video","created":"2024-12-01","cited_by_count":9},{"id":"2412.05161","title":"DNF: Unconditional 4D Generation with Dictionary-based Neural Fields","created":"2024-12-06","cited_by_count":8},{"id":"2506.20936","title":"PhysRig: Differentiable Physics-Based Skinning and Rigging Framework for Realistic Articulated Object Modeling","created":"2025-06-26","cited_by_count":8},{"id":"2502.20208","title":"4Deform: Neural Surface Deformation for Robust Shape Interpolation","created":"2025-02-27","cited_by_count":7},{"id":"2503.13120","title":"3D Human Interaction Generation: A Survey","created":"2025-03-17","cited_by_count":7},{"id":"2411.09145","title":"Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos","created":"2024-11-14","cited_by_count":6},{"id":"2506.22718","title":"Part Segmentation and Motion Estimation for Articulated Objects with Dynamic 3D Gaussians","created":"2025-06-28","cited_by_count":5},{"id":"2507.18276","title":"Adaptive Articulated Object Manipulation On The Fly with Foundation Model Reasoning and Part Grounding","created":"2025-07-24","cited_by_count":3},{"id":"2601.20835","title":"Open-Vocabulary Functional 3D Human-Scene Interaction Generation","created":"2026-01-28","cited_by_count":3},{"id":"2602.02741","title":"PokeNet: Learning Kinematic Models of Articulated Objects from Human Observations","created":"2026-02-02","cited_by_count":3},{"id":"2602.10659","title":"Multimodal Priors-Augmented Text-Driven 3D Human-Object Interaction Generation","created":"2026-02-11","cited_by_count":2},{"id":"2601.02716","title":"MorphGS: Morphology-Adaptive Articulated 3D Motion Transfer from Videos","created":"2026-01-06","cited_by_count":1}],"next_cursor":null}