{"list":"other","total":79,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"id":"1611.07700","title":"3D Menagerie: Modeling the 3D shape and pose of animals","created":"2016-11-23","cited_by_count":312},{"id":"2311.15475","title":"MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers","created":"2023-11-27","cited_by_count":259},{"id":"2306.17115","title":"Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation","created":"2023-06-29","cited_by_count":228},{"id":"2501.12375","title":"Video Depth Anything: Consistent Depth Estimation for Super-Long Videos","created":"2025-01-21","cited_by_count":207},{"id":"2112.12761","title":"BANMo: Building Animatable 3D Neural Models from Many Casual Videos","created":"2021-12-23","cited_by_count":197},{"id":"2312.17142","title":"DreamGaussian4D: Generative 4D Gaussian Splatting","created":"2023-12-28","cited_by_count":194},{"id":"2311.17984","title":"4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling","created":"2023-11-29","cited_by_count":185},{"id":"2312.13763","title":"Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models","created":"2023-12-21","cited_by_count":169},{"id":"2406.10163","title":"MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers","created":"2024-06-14","cited_by_count":144},{"id":"2406.10324","title":"L4GM: Large 4D Gaussian Reconstruction Model","created":"2024-06-14","cited_by_count":144},{"id":"2407.17470","title":"SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency","created":"2024-07-24","cited_by_count":144},{"id":"2410.11831","title":"CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos","created":"2024-10-15","cited_by_count":128},{"id":"2411.00776","title":"Randomized Autoregressive Visual Generation","created":"2024-11-01","cited_by_count":127},{"id":"2311.02848","title":"Consistent4D: Consistent 360{\\deg} Dynamic Object Generation from Monocular Video","created":"2023-11-06","cited_by_count":125},{"id":"2312.17225","title":"4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency","created":"2023-12-28","cited_by_count":117},{"id":"2311.14603","title":"Animate124: Animating One Image to 4D Dynamic Scene","created":"2023-11-24","cited_by_count":115},{"id":"2211.12497","title":"MagicPony: Learning Articulated 3D Animals in the Wild","created":"2022-11-22","cited_by_count":112},{"id":"2405.20674","title":"4Diffusion: Multi-view Video Diffusion Model for 4D Generation","created":"2024-05-31","cited_by_count":104},{"id":"2408.02555","title":"MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization","created":"2024-08-05","cited_by_count":104},{"id":"2403.14939","title":"STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians","created":"2024-03-22","cited_by_count":102},{"id":"2403.12365","title":"GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation","created":"2024-03-19","cited_by_count":100},{"id":"2405.16645","title":"Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models","created":"2024-05-26","cited_by_count":100},{"id":"2504.11451","title":"PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyond","created":"2025-04-15","cited_by_count":95},{"id":"2409.18114","title":"EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation","created":"2024-09-26","cited_by_count":87},{"id":"2403.17920","title":"TC4D: Trajectory-Conditioned Text-to-4D Generation","created":"2024-03-26","cited_by_count":77},{"id":"2205.02825","title":"Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations","created":"2022-05-05","cited_by_count":71},{"id":"2404.01284","title":"Large Motion Model for Unified Multi-Modal Motion Generation","created":"2024-04-01","cited_by_count":65},{"id":"2404.03736","title":"SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer","created":"2024-04-04","cited_by_count":61},{"id":"2401.02400","title":"Learning the 3D Fauna of the Web","created":"2024-01-04","cited_by_count":59},{"id":"2410.06756","title":"DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation","created":"2024-10-09","cited_by_count":58},{"id":"2407.11398","title":"Animate3D: Animating Any 3D Model with Multi-view Video Diffusion","created":"2024-07-16","cited_by_count":56},{"id":"2105.02451","title":"Learning Skeletal Articulations with Neural Blend Shapes","created":"2021-05-06","cited_by_count":53},{"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":"2502.09615","title":"RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets","created":"2025-02-13","cited_by_count":47},{"id":"2404.11151","title":"REACTO: Reconstructing Articulated Objects from a Single Video","created":"2024-04-17","cited_by_count":45},{"id":"2405.18132","title":"EG4D: Explicit Generation of 4D Object without Score Distillation","created":"2024-05-28","cited_by_count":45},{"id":"2504.12451","title":"One Model to Rig Them All: Diverse Skeleton Rigging with UniRig","created":"2025-04-16","cited_by_count":45},{"id":"2502.12135","title":"MagicArticulate: Make Your 3D Models Articulation-Ready","created":"2025-02-17","cited_by_count":43},{"id":"2502.17327","title":"AnyTop: Character Animation Diffusion with Any Topology","created":"2025-02-24","cited_by_count":41},{"id":"1908.08506","title":"Predicting Animation Skeletons for 3D Articulated Models via Volumetric Nets","created":"2019-08-22","cited_by_count":39},{"id":"2012.00230","title":"Point2Skeleton: Learning Skeletal Representations from Point Clouds","created":"2020-12-01","cited_by_count":37},{"id":"2503.09631","title":"V2M4: 4D Mesh Animation Reconstruction from a Single Monocular Video","created":"2025-03-11","cited_by_count":33},{"id":"2109.15025","title":"3D Pose Transfer with Correspondence Learning and Mesh Refinement","created":"2021-09-30","cited_by_count":30},{"id":"2503.14880","title":"DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework","created":"2025-03-19","cited_by_count":30},{"id":"2312.03795","title":"AnimatableDreamer: Text-Guided Non-rigid 3D Model Generation and Reconstruction with Canonical Score Distillation","created":"2023-12-06","cited_by_count":28},{"id":"2505.06227","title":"Anymate: A Dataset and Baselines for Learning 3D Object Rigging","created":"2025-05-09","cited_by_count":27},{"id":"2411.17423","title":"DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters","created":"2024-11-26","cited_by_count":24},{"id":"2409.07179","title":"Phy124: Fast Physics-Driven 4D Content Generation from a Single Image","created":"2024-09-11","cited_by_count":23},{"id":"2411.16800","title":"Phys4DGen: Physics-Compliant 4D Generation with Multi-Material Composition Perception","created":"2024-11-25","cited_by_count":23},{"id":"2411.18197","title":"Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characters","created":"2024-11-27","cited_by_count":23},{"id":"2211.10278","title":"Unsupervised 3D Pose Transfer with Cross Consistency and Dual Reconstruction","created":"2022-11-18","cited_by_count":21},{"id":"2312.13604","title":"Ponymation: Learning Articulated 3D Animal Motions from Unlabeled Online Videos","created":"2023-12-21","cited_by_count":21},{"id":"2210.09463","title":"Morig: Motion-aware rigging of character meshes from point clouds","created":"2022-10-17","cited_by_count":20},{"id":"2410.07155","title":"Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis","created":"2024-10-09","cited_by_count":19},{"id":"2405.14017","title":"MagicPose4D: Crafting Articulated Models with Appearance and Motion Control","created":"2024-05-22","cited_by_count":18},{"id":"2203.04746","title":"SkinningNet: Two-Stream Graph Convolutional Neural Network for Skinning Prediction of Synthetic Characters","created":"2022-03-09","cited_by_count":16},{"id":"2501.01722","title":"AR4D: Autoregressive 4D Generation from Monocular Videos","created":"2025-01-03","cited_by_count":16},{"id":"2405.19957","title":"PLA4D: Pixel-Level Alignments for Text-to-4D Gaussian Splatting","created":"2024-05-30","cited_by_count":15},{"id":"2407.12684","title":"4Dynamic: Text-to-4D Generation with Hybrid Priors","created":"2024-07-17","cited_by_count":15},{"id":"2408.08342","title":"CT4D: Consistent Text-to-4D Generation with Animatable Meshes","created":"2024-08-15","cited_by_count":14},{"id":"2503.16822","title":"RigGS: Rigging of 3D Gaussians for Modeling Articulated Objects in Videos","created":"2025-03-21","cited_by_count":14},{"id":"2304.08279","title":"MoDA: Modeling Deformable 3D Objects from Casual Videos","created":"2023-04-17","cited_by_count":13},{"id":"2311.15435","title":"Functional Diffusion","created":"2023-11-26","cited_by_count":13},{"id":"2504.01204","title":"Articulated Kinematics Distillation from Video Diffusion Models","created":"2025-04-01","cited_by_count":13},{"id":"2405.16849","title":"Sync4D: Video Guided Controllable Dynamics for Physics-Based 4D Generation","created":"2024-05-27","cited_by_count":12},{"id":"2412.02317","title":"HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset","created":"2024-12-03","cited_by_count":12},{"id":"2505.10250","title":"ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization","created":"2025-05-15","cited_by_count":7},{"id":"2406.00238","title":"Robust Biharmonic Skinning Using Geometric Fields","created":"2024-06-01","cited_by_count":6},{"id":"2503.08417","title":"AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models","created":"2025-03-11","cited_by_count":4},{"id":"2503.15996","title":"Animating the Uncaptured: Humanoid Mesh Animation with Video Diffusion Models","created":"2025-03-20","cited_by_count":3}],"next_cursor":null}