{"total":167,"rows":[{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539,"area":null},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692,"area":null},{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247,"area":null},{"id":"2406.09905","title":"Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild","created":"2024-06-14","cited_by_count":114,"area":null},{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104,"area":null},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"area":null},{"id":"2503.24391","title":"Easi3R: Estimating Disentangled Motion from DUSt3R Without Training","created":"2025-03-31","cited_by_count":91,"area":null},{"id":"2412.09621","title":"Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos","created":"2024-12-12","cited_by_count":89,"area":null},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84,"area":null},{"id":"2508.10893","title":"STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer","created":"2025-08-14","cited_by_count":82,"area":null},{"id":"2407.05921","title":"TAPVid-3D: A Benchmark for Tracking Any Point in 3D","created":"2024-07-08","cited_by_count":72,"area":null},{"id":"2504.14717","title":"TAPIP3D: Tracking Any Point in Persistent 3D Geometry","created":"2025-04-20","cited_by_count":69,"area":null},{"id":"2510.10726","title":"WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting","created":"2025-10-12","cited_by_count":67,"area":null},{"id":"2410.24211","title":"DELTA: Dense Efficient Long-range 3D Tracking for any video","created":"2024-10-31","cited_by_count":65,"area":null},{"id":"2412.18608","title":"PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models","created":"2024-12-24","cited_by_count":62,"area":"diffusion"},{"id":"2503.16591","title":"UniK3D: Universal Camera Monocular 3D Estimation","created":"2025-03-20","cited_by_count":62,"area":null},{"id":"2410.03665","title":"Estimating Body and Hand Motion in an Ego-sensed World","created":"2024-10-04","cited_by_count":58,"area":null},{"id":"2505.17015","title":"Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models","created":"2025-05-22","cited_by_count":52,"area":"mllm"},{"id":"2506.08015","title":"4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos","created":"2025-06-09","cited_by_count":49,"area":null},{"id":"2403.18118","title":"EgoLifter: Open-world 3D Segmentation for Egocentric Perception","created":"2024-03-26","cited_by_count":47,"area":null},{"id":"2601.00393","title":"NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos","created":"2026-01-01","cited_by_count":46,"area":"wm"},{"id":"2402.13349","title":"Aria Everyday Activities Dataset","created":"2024-02-20","cited_by_count":39,"area":null},{"id":"2604.14141","title":"LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction","created":"2026-04-15","cited_by_count":37,"area":null},{"id":"2604.08542","title":"Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction","created":"2026-04-09","cited_by_count":31,"area":null},{"id":"2404.08640","title":"EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams","created":"2024-04-12","cited_by_count":29,"area":null},{"id":"2504.08541","title":"Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset","created":"2025-04-11","cited_by_count":29,"area":null},{"id":"2404.05072","title":"Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind","created":"2024-04-07","cited_by_count":28,"area":null},{"id":"2410.08208","title":"SPA: 3D Spatial-Awareness Enables Effective Embodied Representation","created":"2024-10-10","cited_by_count":28,"area":null},{"id":"2510.22706","title":"IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction","created":"2025-10-26","cited_by_count":28,"area":null},{"id":"2601.17895","title":"Masked Depth Modeling for Spatial Perception","created":"2026-01-25","cited_by_count":28,"area":null},{"id":"2401.08739","title":"EgoGen: An Egocentric Synthetic Data Generator","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2406.10224","title":"EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models","created":"2024-06-14","cited_by_count":26,"area":null},{"id":"2603.04385","title":"ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training","created":"2026-03-04","cited_by_count":26,"area":null},{"id":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26,"area":null},{"id":"2504.05692","title":"POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction","created":"2025-04-08","cited_by_count":25,"area":null},{"id":"2401.00889","title":"3D Human Pose Perception from Egocentric Stereo Videos","created":"2023-12-30","cited_by_count":23,"area":null},{"id":"2406.19811","title":"EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splatting","created":"2024-06-28","cited_by_count":23,"area":null},{"id":"2504.06815","title":"SVG-IR: Spatially-Varying Gaussian Splatting for Inverse Rendering","created":"2025-04-09","cited_by_count":23,"area":null},{"id":"2602.13172","title":"LongStream: Long-Sequence Streaming Autoregressive Visual Geometry","created":"2026-02-13","cited_by_count":23,"area":null},{"id":"2405.10305","title":"4D Panoptic Scene Graph Generation","created":"2024-05-16","cited_by_count":22,"area":null},{"id":"2602.10094","title":"4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere","created":"2026-02-10","cited_by_count":22,"area":null},{"id":"2503.12542","title":"ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos","created":"2025-03-16","cited_by_count":21,"area":"lr"},{"id":"2506.05287","title":"EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?","created":"2025-06-05","cited_by_count":21,"area":"mllm"},{"id":"2503.00986","title":"Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning","created":"2025-03-02","cited_by_count":20,"area":null},{"id":"2508.17972","title":"SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization","created":"2025-08-25","cited_by_count":20,"area":null},{"id":"2511.20343","title":"AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend","created":"2025-11-25","cited_by_count":20,"area":null},{"id":"2312.04117","title":"Instance Tracking in 3D Scenes from Egocentric Videos","created":"2023-12-07","cited_by_count":17,"area":null},{"id":"2403.06862","title":"Real-Time Simulated Avatar from Head-Mounted Sensors","created":"2024-03-11","cited_by_count":17,"area":null},{"id":"2407.02633","title":"HOIMotion: Forecasting Human Motion During Human-Object Interactions Using Egocentric 3D Object Bounding Boxes","created":"2024-07-02","cited_by_count":17,"area":null},{"id":"2501.07574","title":"UnCommon Objects in 3D","created":"2025-01-13","cited_by_count":17,"area":null},{"id":"2508.01126","title":"UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation","created":"2025-08-02","cited_by_count":17,"area":null},{"id":"2508.21060","title":"Multi-View 3D Point Tracking","created":"2025-08-28","cited_by_count":17,"area":null},{"id":"2512.04939","title":"LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging","created":"2025-12-04","cited_by_count":17,"area":"inference"},{"id":"2503.13176","title":"DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstruction","created":"2025-03-17","cited_by_count":16,"area":null},{"id":"2408.08524","title":"GS-ID: Illumination Decomposition on Gaussian Splatting via Adaptive Light Aggregation and Diffusion-Guided Material Priors","created":"2024-08-16","cited_by_count":14,"area":null},{"id":"2504.14687","title":"Seurat: From Moving Points to Depth","created":"2025-04-20","cited_by_count":13,"area":null},{"id":"2603.02573","title":"Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels","created":"2026-03-03","cited_by_count":13,"area":null},{"id":"2411.16785","title":"MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAM","created":"2024-11-25","cited_by_count":12,"area":null},{"id":"2502.13078","title":"L4P: Towards Unified Low-Level 4D Vision Perception","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2412.02903","title":"EgoCast: Forecasting Egocentric Human Pose in the Wild","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2505.24287","title":"EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding","created":"2025-05-30","cited_by_count":11,"area":null},{"id":"2412.04592","title":"EgoPoints: Advancing Point Tracking for Egocentric Videos","created":"2024-12-05","cited_by_count":10,"area":null},{"id":"2507.08448","title":"Review of Feed-forward 3D Reconstruction: From DUSt3R to VGGT","created":"2025-07-11","cited_by_count":10,"area":null},{"id":"2508.01170","title":"DELTAv2: Accelerating Dense 3D Tracking","created":"2025-08-02","cited_by_count":10,"area":null},{"id":"2511.18416","title":"4D-VGGT: A General Foundation Model with SpatioTemporal Awareness for Dynamic Scene Geometry Estimation","created":"2025-11-23","cited_by_count":10,"area":null},{"id":"2506.07886","title":"EgoM2P: Egocentric Multimodal Multitask Pretraining","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2508.00088","title":"The Monado SLAM Dataset for Egocentric Visual-Inertial Tracking","created":"2025-07-31","cited_by_count":9,"area":null},{"id":"2506.04224","title":"Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset","created":"2025-06-04","cited_by_count":8,"area":null},{"id":"2602.14021","title":"Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow","created":"2026-02-15","cited_by_count":8,"area":null},{"id":"2607.05247","title":"Vision Pretraining for Dense Spatial Perception","created":"2026-07-06","cited_by_count":8,"area":null},{"id":"2312.12042","title":"Pose2Gaze: Eye-body Coordination during Daily Activities for Gaze Prediction from Full-body Poses","created":"2023-12-19","cited_by_count":7,"area":null},{"id":"2503.11652","title":"Bring Your Rear Cameras for Egocentric 3D Human Pose Estimation","created":"2025-03-14","cited_by_count":7,"area":null},{"id":"2503.13120","title":"3D Human Interaction Generation: A Survey","created":"2025-03-17","cited_by_count":7,"area":null},{"id":"2503.21694","title":"Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data","created":"2025-03-27","cited_by_count":7,"area":"diffusion"},{"id":"2512.08358","title":"TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels","created":"2025-12-09","cited_by_count":7,"area":null},{"id":"2603.05591","title":"Thinking with Spatial Code for Physical-World Video Reasoning","created":"2026-03-05","cited_by_count":7,"area":"lr"},{"id":"2604.05212","title":"Boxer: Robust Lifting of Open-World 2D Bounding Boxes to 3D","created":"2026-04-06","cited_by_count":7,"area":null},{"id":"2604.22482","title":"Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyond","created":"2026-04-24","cited_by_count":7,"area":null},{"id":"2404.14409","title":"CrossScore: Towards Multi-View Image Evaluation and Scoring","created":"2024-04-22","cited_by_count":6,"area":null},{"id":"2407.20592","title":"EgoSonics: Generating Synchronized Audio for Silent Egocentric Videos","created":"2024-07-30","cited_by_count":6,"area":null},{"id":"2502.07869","title":"EventEgo3D++: 3D Human Motion Capture from a Head-Mounted Event Camera","created":"2025-02-11","cited_by_count":6,"area":null},{"id":"2505.17966","title":"Is Single-View Mesh Reconstruction Ready for Robotics?","created":"2025-05-23","cited_by_count":6,"area":null},{"id":"2508.07251","title":"Understanding Dynamic Scenes in Ego Centric 4D Point Clouds","created":"2025-08-10","cited_by_count":6,"area":"lr"},{"id":"2510.16134","title":"Aria Gen 2 Pilot Dataset","created":"2025-10-17","cited_by_count":6,"area":null},{"id":"2603.28732","title":"Pandora: Articulated 3D Scene Graphs from Egocentric Vision","created":"2026-03-30","cited_by_count":6,"area":null},{"id":"2603.28896","title":"Fisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lenses","created":"2026-03-30","cited_by_count":6,"area":null},{"id":"2312.12418","title":"LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Dataset","created":"2023-12-19","cited_by_count":5,"area":null},{"id":"2403.09885","title":"GazeMotion: Gaze-guided Human Motion Forecasting","created":"2024-03-14","cited_by_count":5,"area":null},{"id":"2403.16169","title":"Gaze-guided Hand-Object Interaction Synthesis: Dataset and Method","created":"2024-03-24","cited_by_count":5,"area":null},{"id":"2508.21556","title":"ECHO: Ego-Centric modeling of Human-Object interactions","created":"2025-08-29","cited_by_count":5,"area":null},{"id":"2511.18600","title":"NeAR: Coupled Neural Asset-Renderer Stack","created":"2025-11-23","cited_by_count":5,"area":null},{"id":"2601.09430","title":"Video-MSR: Benchmarking Multi-hop Spatial Reasoning Capabilities of MLLMs","created":"2026-01-14","cited_by_count":5,"area":"lr"},{"id":"2605.12587","title":"TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking","created":"2026-05-12","cited_by_count":5,"area":"diffusion"},{"id":"2606.03994","title":"SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image","created":"2026-06-02","cited_by_count":5,"area":null},{"id":"2608.13416","title":"StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs","created":"2026-08-13","cited_by_count":5,"area":null},{"id":"2311.06455","title":"Aria-NeRF: Multimodal Egocentric View Synthesis","created":"2023-11-11","cited_by_count":4,"area":null},{"id":"2503.11345","title":"EgoSplat: Open-Vocabulary Egocentric Scene Understanding with Language Embedded 3D Gaussian Splatting","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2505.04813","title":"WIR3D: Visually-Informed and Geometry-Aware 3D Shape Abstraction","created":"2025-05-07","cited_by_count":4,"area":null},{"id":"2603.12265","title":"OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams","created":"2026-03-12","cited_by_count":4,"area":null},{"id":"2603.25993","title":"FAST3DIS: Feed-forward Anchored Scene Transformer for 3D Instance Segmentation","created":"2026-03-27","cited_by_count":4,"area":null}],"next_cursor":"100"}