{"list":"other","total":102,"rows":[{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2011.12948","title":"Nerfies: Deformable Neural Radiance Fields","created":"2020-11-25","cited_by_count":1198},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2011.13084","title":"Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes","created":"2020-11-26","cited_by_count":751},{"id":"2301.10241","title":"K-Planes: Explicit Radiance Fields in Space, Time, and Appearance","created":"2023-01-24","cited_by_count":746},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2310.15008","title":"Wonder3D: Single Image to 3D using Cross-Domain Diffusion","created":"2023-10-23","cited_by_count":689},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"2301.09632","title":"HexPlane: A Fast Representation for Dynamic Scenes","created":"2023-01-23","cited_by_count":587},{"id":"2406.13897","title":"CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets","created":"2024-05-30","cited_by_count":455},{"id":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442},{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429},{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247},{"id":"2301.11280","title":"Text-To-4D Dynamic Scene Generation","created":"2023-01-26","cited_by_count":205},{"id":"2512.14692","title":"Native and Compact Structured Latents for 3D Generation","created":"2025-12-16","cited_by_count":175},{"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":"2412.03558","title":"MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation","created":"2024-12-04","cited_by_count":117},{"id":"2502.12894","title":"CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image","created":"2025-02-18","cited_by_count":106},{"id":"2305.19590","title":"Neural Kernel Surface Reconstruction","created":"2023-05-31","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":"2503.22236","title":"Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging","created":"2025-03-28","cited_by_count":99},{"id":"2504.20995","title":"TesserAct: Learning 4D Embodied World Models","created":"2025-04-29","cited_by_count":94},{"id":"2411.09595","title":"LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models","created":"2024-11-14","cited_by_count":91},{"id":"2505.14521","title":"Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling","created":"2025-05-20","cited_by_count":89},{"id":"2505.02836","title":"Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation","created":"2025-05-05","cited_by_count":67},{"id":"2509.07996","title":"3D and 4D World Modeling: A Survey","created":"2025-09-04","cited_by_count":67},{"id":"2405.02280","title":"DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos","created":"2024-05-03","cited_by_count":63},{"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":"2508.15769","title":"SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass","created":"2025-08-21","cited_by_count":54},{"id":"2511.15706","title":"RoMa v2: Harder Better Faster Denser Feature Matching","created":"2025-11-19","cited_by_count":51},{"id":"2602.10116","title":"SAGE: Scalable Agentic 3D Scene Generation for Embodied AI","created":"2026-02-10","cited_by_count":50},{"id":"2601.11109","title":"Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning","created":"2026-01-16","cited_by_count":49},{"id":"2502.09615","title":"RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets","created":"2025-02-13","cited_by_count":47},{"id":"2405.18525","title":"REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignment","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":"2502.02590","title":"Articulate AnyMesh: Open-Vocabulary 3D Articulated Objects Modeling","created":"2025-02-04","cited_by_count":43},{"id":"2502.12135","title":"MagicArticulate: Make Your 3D Models Articulation-Ready","created":"2025-02-17","cited_by_count":43},{"id":"2508.10898","title":"Puppeteer: Rig and Animate Your 3D Models","created":"2025-08-14","cited_by_count":43},{"id":"2511.13648","title":"PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image","created":"2025-11-17","cited_by_count":37},{"id":"2506.10600","title":"EmbodiedGen: Towards a Generative 3D World Engine for Embodied Intelligence","created":"2025-06-12","cited_by_count":36},{"id":"2211.03568","title":"CASA: Category-agnostic Skeletal Animal Reconstruction","created":"2022-11-04","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":"2512.10935","title":"Any4D: Unified Feed-Forward Metric 4D Reconstruction","created":"2025-12-11","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":"2405.21066","title":"Mixed Diffusion for 3D Indoor Scene Synthesis","created":"2024-05-31","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":"2403.15064","title":"Recent Trends in 3D Reconstruction of General Non-Rigid Scenes","created":"2024-03-22","cited_by_count":28},{"id":"2506.00742","title":"ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary","created":"2025-05-31","cited_by_count":28},{"id":"2411.17423","title":"DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters","created":"2024-11-26","cited_by_count":24},{"id":"2505.05474","title":"3D Scene Generation: A Survey","created":"2025-05-08","cited_by_count":24},{"id":"2411.16800","title":"Phys4DGen: Physics-Compliant 4D Generation with Multi-Material Composition Perception","created":"2024-11-25","cited_by_count":23},{"id":"2507.22825","title":"DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion","created":"2025-07-30","cited_by_count":23},{"id":"2404.12379","title":"Dynamic Gaussians Mesh: Consistent Mesh Reconstruction from Dynamic Scenes","created":"2024-04-18","cited_by_count":22},{"id":"2601.11514","title":"ShapeR: Robust Conditional 3D Shape Generation from Casual Captures","created":"2026-01-16","cited_by_count":22},{"id":"2602.11757","title":"Code2Worlds: Empowering Coding LLMs for 4D World Generation","created":"2026-02-12","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":"2512.10957","title":"SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model","created":"2025-12-11","cited_by_count":17},{"id":"2409.18980","title":"IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-Web","created":"2024-09-14","cited_by_count":16},{"id":"2511.21978","title":"PAT3D: Physics-Augmented Text-to-3D Scene Generation","created":"2025-11-26","cited_by_count":16},{"id":"2601.16148","title":"ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion","created":"2026-01-22","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":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14},{"id":"2509.07978","title":"One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation","created":"2025-09-09","cited_by_count":14},{"id":"2501.02519","title":"Layout2Scene: 3D Semantic Layout Guided Scene Generation via Geometry and Appearance Diffusion Priors","created":"2025-01-05","cited_by_count":13},{"id":"2506.08640","title":"Orientation Matters: Making 3D Generative Models Orientation-Aligned","created":"2025-06-10","cited_by_count":13},{"id":"2404.04363","title":"Idea23D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs","created":"2024-04-05","cited_by_count":12},{"id":"2601.05251","title":"Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video","created":"2026-01-08","cited_by_count":12},{"id":"2409.13803","title":"Intrinsic Single-Image HDR Reconstruction","created":"2024-09-20","cited_by_count":11},{"id":"2507.08416","title":"InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes","created":"2025-07-11","cited_by_count":11},{"id":"2510.15564","title":"Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation","created":"2025-10-17","cited_by_count":11},{"id":"2605.27351","title":"Feedforward 3D Editing Learns from Semantic-Part Transformation","created":"2026-05-26","cited_by_count":10},{"id":"2512.03210","title":"Flux4D: Flow-based Unsupervised 4D Reconstruction","created":"2025-12-02","cited_by_count":9},{"id":"2602.01661","title":"From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction","created":"2026-02-02","cited_by_count":9},{"id":"2503.17827","title":"4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding","created":"2025-03-22","cited_by_count":8},{"id":"2506.11430","title":"Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization","created":"2025-06-13","cited_by_count":7},{"id":"2604.03305","title":"HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis","created":"2026-03-31","cited_by_count":7},{"id":"2604.20539","title":"Animator-Centric Skeleton Generation on Objects with Fine-Grained Details","created":"2026-04-22","cited_by_count":7},{"id":"2512.13683","title":"I-Scene: 3D Instance Models are Implicit Generalizable Spatial Learners","created":"2025-12-15","cited_by_count":6},{"id":"2602.22785","title":"SceneTransporter: Optimal Transport-Guided Compositional Latent Diffusion for Single-Image Structured 3D Scene Generation","created":"2026-02-26","cited_by_count":6},{"id":"2509.23607","title":"ZeroScene: A Zero-Shot Framework for 3D Scene Generation from a Single Image and Controllable Texture Editing","created":"2025-09-28","cited_by_count":5},{"id":"2604.11792","title":"LottieGPT: Tokenizing Vector Animation for Autoregressive Generation","created":"2026-04-13","cited_by_count":5},{"id":"2308.14353","title":"ZhuJiu: A Multi-dimensional, Multi-faceted Chinese Benchmark for Large Language Models","created":"2023-08-28","cited_by_count":4},{"id":"2509.16610","title":"LLMsPark: A Benchmark for Evaluating Large Language Models in Strategic Gaming Contexts","created":"2025-09-20","cited_by_count":4},{"id":"2510.19255","title":"Advances in 4D Representation: Geometry, Motion, and Interaction","created":"2025-10-22","cited_by_count":4},{"id":"2512.22745","title":"Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation","created":"2025-12-28","cited_by_count":4},{"id":"2512.13639","title":"Charge: A Comprehensive Novel View Synthesis Benchmark and Dataset to Bind Them All","created":"2025-12-15","cited_by_count":2},{"id":"2605.20150","title":"TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization","created":"2026-05-19","cited_by_count":2}],"next_cursor":"100"}