{"list":"other","total":79,"rows":[{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2112.07945","title":"Efficient Geometry-aware 3D Generative Adversarial Networks","created":"2021-12-15","cited_by_count":1205},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2402.05054","title":"LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation","created":"2024-02-07","cited_by_count":739},{"id":"1801.09847","title":"Open3D: A Modern Library for 3D Data Processing","created":"2018-01-30","cited_by_count":721},{"id":"2204.11918","title":"Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items","created":"2022-04-25","cited_by_count":612},{"id":"1610.07584","title":"Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling","created":"2016-10-24","cited_by_count":558},{"id":"2210.06978","title":"LION: Latent Point Diffusion Models for 3D Shape Generation","created":"2022-10-12","cited_by_count":553},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548},{"id":"2310.10642","title":"Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting","created":"2023-10-16","cited_by_count":476},{"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":"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":"2209.11163","title":"GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images","created":"2022-09-22","cited_by_count":446},{"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":"2405.10314","title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","created":"2024-05-16","cited_by_count":432},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365},{"id":"2403.12008","title":"SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion","created":"2024-03-18","cited_by_count":364},{"id":"2312.07920","title":"DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes","created":"2023-12-13","cited_by_count":360},{"id":"2108.08839","title":"PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers","created":"2021-08-19","cited_by_count":286},{"id":"2407.13764","title":"Shape of Motion: 4D Reconstruction from a Single Video","created":"2024-07-18","cited_by_count":250},{"id":"2412.04463","title":"MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos","created":"2024-12-05","cited_by_count":228},{"id":"2502.06608","title":"TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models","created":"2025-02-10","cited_by_count":213},{"id":"2405.14832","title":"Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer","created":"2024-05-23","cited_by_count":210},{"id":"2312.17142","title":"DreamGaussian4D: Generative 4D Gaussian Splatting","created":"2023-12-28","cited_by_count":194},{"id":"2312.03806","title":"XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies","created":"2023-12-06","cited_by_count":189},{"id":"2012.05901","title":"Robust Consistent Video Depth Estimation","created":"2020-12-10","cited_by_count":188},{"id":"2303.05371","title":"3DGen: Triplane Latent Diffusion for Textured Mesh Generation","created":"2023-03-09","cited_by_count":183},{"id":"1905.02082","title":"ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals","created":"2019-05-06","cited_by_count":181},{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161},{"id":"2003.00410","title":"PF-Net: Point Fractal Network for 3D Point Cloud Completion","created":"2020-03-01","cited_by_count":146},{"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":"2305.04461","title":"Locally Attentional SDF Diffusion for Controllable 3D Shape Generation","created":"2023-05-08","cited_by_count":130},{"id":"2311.02848","title":"Consistent4D: Consistent 360{\\deg} Dynamic Object Generation from Monocular Video","created":"2023-11-06","cited_by_count":125},{"id":"1812.02725","title":"Visual Object Networks: Image Generation with Disentangled 3D Representation","created":"2018-12-06","cited_by_count":124},{"id":"2105.01905","title":"4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface","created":"2021-05-05","cited_by_count":124},{"id":"2411.04924","title":"MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views","created":"2024-11-07","cited_by_count":116},{"id":"2104.00587","title":"NeRF-VAE: A Geometry Aware 3D Scene Generative Model","created":"2021-04-01","cited_by_count":112},{"id":"2305.19590","title":"Neural Kernel Surface Reconstruction","created":"2023-05-31","cited_by_count":104},{"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":"2504.13152","title":"St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World","created":"2025-04-17","cited_by_count":89},{"id":"2601.03782","title":"PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation","created":"2026-01-07","cited_by_count":82},{"id":"2405.20337","title":"OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving","created":"2024-05-30","cited_by_count":78},{"id":"2305.01643","title":"Neural LiDAR Fields for Novel View Synthesis","created":"2023-05-02","cited_by_count":67},{"id":"2503.14445","title":"Bolt3D: Generating 3D Scenes in Seconds","created":"2025-03-18","cited_by_count":59},{"id":"2203.16529","title":"CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphism","created":"2022-03-30","cited_by_count":57},{"id":"2512.08924","title":"Efficiently Reconstructing Dynamic Scenes One D4RT at a Time","created":"2025-12-09","cited_by_count":54},{"id":"2006.07660","title":"Convolutional Generation of Textured 3D Meshes","created":"2020-06-13","cited_by_count":52},{"id":"2401.08742","title":"Efficient4D: Fast Dynamic 3D Object Generation from a Single-view Video","created":"2024-01-16","cited_by_count":44},{"id":"2503.16318","title":"Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction","created":"2025-03-20","cited_by_count":44},{"id":"2512.10935","title":"Any4D: Unified Feed-Forward Metric 4D Reconstruction","created":"2025-12-11","cited_by_count":35},{"id":"2507.23785","title":"Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis","created":"2025-07-31","cited_by_count":33},{"id":"2103.16341","title":"Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction","created":"2021-03-30","cited_by_count":31},{"id":"2401.06614","title":"Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking","created":"2024-01-12","cited_by_count":29},{"id":"2110.02330","title":"Shape-aware Multi-Person Pose Estimation from Multi-View Images","created":"2021-10-05","cited_by_count":24},{"id":"2504.14516","title":"Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction","created":"2025-04-20","cited_by_count":24},{"id":"2406.19811","title":"EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splatting","created":"2024-06-28","cited_by_count":23},{"id":"2411.08402","title":"V2X-R: Cooperative LiDAR-4D Radar Fusion with Denoising Diffusion for 3D Object Detection","created":"2024-11-13","cited_by_count":18},{"id":"2503.23282","title":"AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos","created":"2025-03-30","cited_by_count":18},{"id":"2508.21060","title":"Multi-View 3D Point Tracking","created":"2025-08-28","cited_by_count":17},{"id":"2505.22859","title":"4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians","created":"2025-05-28","cited_by_count":13},{"id":"1712.03084","title":"An Integrated Platform for Live 3D Human Reconstruction and Motion Capturing","created":"2017-12-08","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":"2412.15618","title":"3D Shape Tokenization via Latent Flow Matching","created":"2024-12-20","cited_by_count":10},{"id":"2405.03388","title":"3D LiDAR Mapping in Dynamic Environments Using a 4D Implicit Neural Representation","created":"2024-05-06","cited_by_count":8},{"id":"2510.14960","title":"C4D: 4D Made from 3D through Dual Correspondences","created":"2025-10-16","cited_by_count":8},{"id":"2602.14021","title":"Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow","created":"2026-02-15","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":"2603.04179","title":"NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction","created":"2026-03-04","cited_by_count":7},{"id":"2504.12825","title":"TwoSquared: 4D Generation from 2D Image Pairs","created":"2025-04-17","cited_by_count":3}],"next_cursor":null}