{"list":"other","total":89,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2305.16213","title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","created":"2023-05-25","cited_by_count":1219},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2308.16512","title":"MVDream: Multi-view Diffusion for 3D Generation","created":"2023-08-31","cited_by_count":938},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2306.16928","title":"One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization","created":"2023-06-29","cited_by_count":560},{"id":"2301.11445","title":"3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models","created":"2023-01-26","cited_by_count":458},{"id":"2405.10314","title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","created":"2024-05-16","cited_by_count":432},{"id":"2501.12202","title":"Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation","created":"2025-01-21","cited_by_count":356},{"id":"2311.07885","title":"One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion","created":"2023-11-14","cited_by_count":283},{"id":"1701.03077","title":"A General and Adaptive Robust Loss Function","created":"2017-01-11","cited_by_count":236},{"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":"2312.04433","title":"DreamVideo: Composing Your Dream Videos with Customized Subject and Motion","created":"2023-12-07","cited_by_count":188},{"id":"2311.17984","title":"4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling","created":"2023-11-29","cited_by_count":185},{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161},{"id":"2406.10324","title":"L4GM: Large 4D Gaussian Reconstruction Model","created":"2024-06-14","cited_by_count":144},{"id":"2105.01905","title":"4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface","created":"2021-05-05","cited_by_count":124},{"id":"2312.17225","title":"4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency","created":"2023-12-28","cited_by_count":117},{"id":"2412.03632","title":"MV-Adapter: Multi-view Consistent Image Generation Made Easy","created":"2024-12-04","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":"2405.16645","title":"Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models","created":"2024-05-26","cited_by_count":100},{"id":"2503.15451","title":"MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space","created":"2025-03-19","cited_by_count":86},{"id":"2205.05740","title":"Surface Representation for Point Clouds","created":"2022-05-11","cited_by_count":84},{"id":"2405.20337","title":"OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving","created":"2024-05-30","cited_by_count":78},{"id":"2403.17920","title":"TC4D: Trajectory-Conditioned Text-to-4D Generation","created":"2024-03-26","cited_by_count":77},{"id":"2406.07472","title":"4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models","created":"2024-06-11","cited_by_count":64},{"id":"2412.18608","title":"PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models","created":"2024-12-24","cited_by_count":62},{"id":"2206.08010","title":"MoDi: Unconditional Motion Synthesis from Diverse Data","created":"2022-06-16","cited_by_count":59},{"id":"2407.11398","title":"Animate3D: Animating Any 3D Model with Multi-view Video Diffusion","created":"2024-07-16","cited_by_count":56},{"id":"2003.12283","title":"LIMP: Learning Latent Shape Representations with Metric Preservation Priors","created":"2020-03-27","cited_by_count":55},{"id":"2403.19435","title":"BAMM: Bidirectional Autoregressive Motion Model","created":"2024-03-28","cited_by_count":55},{"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":"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":"2412.09982","title":"SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video","created":"2024-12-13","cited_by_count":44},{"id":"2408.14732","title":"OctFusion: Octree-based Diffusion Models for 3D Shape Generation","created":"2024-08-27","cited_by_count":43},{"id":"2508.10898","title":"Puppeteer: Rig and Animate Your 3D Models","created":"2025-08-14","cited_by_count":43},{"id":"2502.17327","title":"AnyTop: Character Animation Diffusion with Any Topology","created":"2025-02-24","cited_by_count":41},{"id":"2405.16822","title":"Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels","created":"2024-05-27","cited_by_count":38},{"id":"2501.00601","title":"DreamDrive: Generative 4D Scene Modeling from Street View Images","created":"2024-12-31","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":"2303.15413","title":"Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation","created":"2023-03-27","cited_by_count":32},{"id":"2305.20082","title":"Control4D: Efficient 4D Portrait Editing with Text","created":"2023-05-31","cited_by_count":32},{"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},{"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},{"id":"2312.09305","title":"Stable Score Distillation for High-Quality 3D Generation","created":"2023-12-14","cited_by_count":27},{"id":"2412.04462","title":"4Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion","created":"2024-12-05","cited_by_count":27},{"id":"2505.06227","title":"Anymate: A Dataset and Baselines for Learning 3D Object Rigging","created":"2025-05-09","cited_by_count":27},{"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":"2402.14253","title":"MVD$^2$: Efficient Multiview 3D Reconstruction for Multiview Diffusion","created":"2024-02-22","cited_by_count":22},{"id":"2311.18303","title":"OmniMotionGPT: Animal Motion Generation with Limited Data","created":"2023-11-30","cited_by_count":20},{"id":"2404.06091","title":"Hash3D: Training-free Acceleration for 3D Generation","created":"2024-04-09","cited_by_count":19},{"id":"2502.11697","title":"MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow","created":"2025-02-17","cited_by_count":17},{"id":"2310.12678","title":"TapMo: Shape-aware Motion Generation of Skeleton-free Characters","created":"2023-10-19","cited_by_count":16},{"id":"2501.01722","title":"AR4D: Autoregressive 4D Generation from Monocular Videos","created":"2025-01-03","cited_by_count":16},{"id":"2506.19851","title":"AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models","created":"2025-06-24","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":"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},{"id":"2305.15753","title":"T2TD: Text-3D Generation Model based on Prior Knowledge Guidance","created":"2023-05-25","cited_by_count":13},{"id":"2504.11389","title":"VideoPanda: Video Panoramic Diffusion with Multi-view Attention","created":"2025-04-15","cited_by_count":13},{"id":"2410.00890","title":"Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation","created":"2024-10-01","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":"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":"2505.20283","title":"Category-Agnostic Neural Object Rigging","created":"2025-05-26","cited_by_count":9},{"id":"2508.07409","title":"CharacterShot: Controllable and Consistent 4D Character Animation","created":"2025-08-10","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":"2406.18582","title":"CanFields: Consolidating Diffeomorphic Flows for Non-Rigid 4D Interpolation from Arbitrary-Length Sequences","created":"2024-06-05","cited_by_count":7},{"id":"2502.20208","title":"4Deform: Neural Surface Deformation for Robust Shape Interpolation","created":"2025-02-27","cited_by_count":7},{"id":"2312.13071","title":"Point Deformable Network with Enhanced Normal Embedding for Point Cloud Analysis","created":"2023-12-20","cited_by_count":6},{"id":"2504.00457","title":"Distilling Multi-view Diffusion Models into 3D Generators","created":"2025-04-01","cited_by_count":4},{"id":"2504.12825","title":"TwoSquared: 4D Generation from 2D Image Pairs","created":"2025-04-17","cited_by_count":3},{"id":"2507.07521","title":"Spline Deformation Field","created":"2025-07-10","cited_by_count":3},{"id":"2510.12537","title":"Unconditional Human Motion and Shape Generation via Balanced Score-Based Diffusion","created":"2025-10-14","cited_by_count":2},{"id":"2108.02507","title":"Shape Modeling with Spline Partitions","created":"2021-08-05","cited_by_count":1}],"next_cursor":null}