{"total":131,"rows":[{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539,"area":null},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983,"area":null},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548,"area":null},{"id":"2501.13928","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","created":"2025-01-23","cited_by_count":367,"area":null},{"id":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314,"area":null},{"id":"2407.20219","title":"Global Structure-from-Motion Revisited","created":"2024-07-29","cited_by_count":218,"area":null},{"id":"2502.12138","title":"FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views","created":"2025-02-17","cited_by_count":180,"area":null},{"id":"2409.19152","title":"MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion","created":"2024-09-27","cited_by_count":162,"area":null},{"id":"2503.01661","title":"MUSt3R: Multi-view Network for Stereo 3D Reconstruction","created":"2025-03-03","cited_by_count":141,"area":null},{"id":"2406.04343","title":"Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image","created":"2024-06-06","cited_by_count":116,"area":null},{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105,"area":null},{"id":"2507.12462","title":"SpatialTrackerV2: 3D Point Tracking Made Easy","created":"2025-07-16","cited_by_count":87,"area":null},{"id":"2412.08376","title":"Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization","created":"2024-12-11","cited_by_count":82,"area":null},{"id":"2505.00702","title":"RayZer: A Self-supervised Large View Synthesis Model","created":"2025-05-01","cited_by_count":77,"area":null},{"id":"2404.14351","title":"Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer","created":"2024-04-22","cited_by_count":73,"area":null},{"id":"2503.17316","title":"Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors","created":"2025-03-21","cited_by_count":72,"area":null},{"id":"2504.07961","title":"Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction","created":"2025-04-10","cited_by_count":67,"area":"diffusion"},{"id":"2411.17698","title":"Video-Guided Foley Sound Generation with Multimodal Controls","created":"2024-11-26","cited_by_count":49,"area":null},{"id":"2507.16290","title":"Dens3R: A Foundation Model for 3D Geometry Prediction","created":"2025-07-22","cited_by_count":46,"area":null},{"id":"2411.16318","title":"One Diffusion to Generate Them All","created":"2024-11-25","cited_by_count":41,"area":"diffusion"},{"id":"2412.09573","title":"FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction","created":"2024-12-12","cited_by_count":41,"area":null},{"id":"2502.07685","title":"Matrix3D: Large Photogrammetry Model All-in-One","created":"2025-02-11","cited_by_count":40,"area":null},{"id":"2506.01103","title":"DeepVerse: 4D Autoregressive Video Generation as a World Model","created":"2025-06-01","cited_by_count":40,"area":"wm"},{"id":"2504.13157","title":"AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis","created":"2025-04-17","cited_by_count":39,"area":null},{"id":"2411.16443","title":"SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis","created":"2024-11-25","cited_by_count":34,"area":"diffusion"},{"id":"2412.21117","title":"Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation","created":"2024-12-30","cited_by_count":34,"area":"diffusion"},{"id":"2510.18313","title":"OmniNWM: Omniscient Driving Navigation World Models","created":"2025-10-21","cited_by_count":33,"area":"wm"},{"id":"2409.19811","title":"Robust Incremental Structure-from-Motion with Hybrid Features","created":"2024-09-29","cited_by_count":31,"area":null},{"id":"2504.01647","title":"FlowR: Flowing from Sparse to Dense 3D Reconstructions","created":"2025-04-02","cited_by_count":28,"area":null},{"id":"2512.11798","title":"Particulate: Feed-Forward 3D Object Articulation","created":"2025-12-12","cited_by_count":23,"area":null},{"id":"2506.09995","title":"PlayerOne: Egocentric World Simulator","created":"2025-06-11","cited_by_count":20,"area":null},{"id":"2510.08673","title":"Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation","created":"2025-10-09","cited_by_count":19,"area":null},{"id":"2412.07746","title":"LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models","created":"2024-12-10","cited_by_count":18,"area":null},{"id":"2412.14158","title":"AKiRa: Augmentation Kit on Rays for optical video generation","created":"2024-12-18","cited_by_count":18,"area":"diffusion"},{"id":"2512.11218","title":"Seeing to Act, Prompting to Specify: A Bayesian Factorization of Vision Language Action Policy","created":"2025-12-12","cited_by_count":18,"area":"mllm"},{"id":"2405.12221","title":"Images that Sound: Composing Images and Sounds on a Single Canvas","created":"2024-05-20","cited_by_count":17,"area":"diffusion"},{"id":"2507.13344","title":"Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models","created":"2025-07-17","cited_by_count":17,"area":"diffusion"},{"id":"2405.14869","title":"PuzzleAvatar: Assembling 3D Avatars from Personal Albums","created":"2024-05-23","cited_by_count":16,"area":null},{"id":"2505.11992","title":"SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations","created":"2025-05-17","cited_by_count":16,"area":"diffusion"},{"id":"2503.15855","title":"VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling","created":"2025-03-20","cited_by_count":14,"area":null},{"id":"2506.05282","title":"Rectified Point Flow: Generic Point Cloud Pose Estimation","created":"2025-06-05","cited_by_count":14,"area":null},{"id":"2509.14981","title":"SPATIALGEN: Layout-guided 3D Indoor Scene Generation","created":"2025-09-18","cited_by_count":14,"area":null},{"id":"2510.02268","title":"Do You Know Where Your Camera Is? View-Invariant Policy Learning with Camera Conditioning","created":"2025-10-02","cited_by_count":14,"area":"offlinerl"},{"id":"2601.15275","title":"RayRoPE: Projective Ray Positional Encoding for Multi-view Attention","created":"2026-01-21","cited_by_count":14,"area":null},{"id":"2607.09024","title":"Video Generation Models are General-Purpose Vision Learners","created":"2026-07-10","cited_by_count":14,"area":null},{"id":"2412.03517","title":"NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images","created":"2024-12-04","cited_by_count":13,"area":null},{"id":"2412.15211","title":"Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation","created":"2024-12-19","cited_by_count":13,"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":"2506.02265","title":"Rig3R: Rig-Aware Conditioning for Learned 3D Reconstruction","created":"2025-06-02","cited_by_count":11,"area":null},{"id":"2511.19827","title":"ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding","created":"2025-11-25","cited_by_count":11,"area":null},{"id":"2503.21082","title":"Can Video Diffusion Model Reconstruct 4D Geometry?","created":"2025-03-27","cited_by_count":10,"area":"diffusion"},{"id":"2504.12356","title":"Regist3R: Incremental Registration with Stereo Foundation Model","created":"2025-04-16","cited_by_count":9,"area":null},{"id":"2603.20176","title":"LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis","created":"2026-03-20","cited_by_count":9,"area":null},{"id":"2411.17240","title":"Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration","created":"2024-11-26","cited_by_count":8,"area":"diffusion"},{"id":"2510.20776","title":"CUPID: Generative 3D Reconstruction via Joint Object and Pose Modeling","created":"2025-10-23","cited_by_count":8,"area":null},{"id":"2605.26103","title":"Global Structure-from-Motion Meets Feedforward Reconstruction","created":"2026-05-25","cited_by_count":8,"area":null},{"id":"2412.16155","title":"Can Generative Video Models Help Pose Estimation?","created":"2024-12-20","cited_by_count":7,"area":null},{"id":"2510.01184","title":"Temporal Score Rescaling for Temperature Sampling in Diffusion and Flow Models","created":"2025-10-01","cited_by_count":7,"area":"diffusion"},{"id":"2408.09144","title":"SSNeRF: Sparse View Semi-supervised Neural Radiance Fields with Augmentation","created":"2024-08-17","cited_by_count":6,"area":null},{"id":"2411.07096","title":"Extreme Rotation Estimation in the Wild","created":"2024-11-11","cited_by_count":6,"area":null},{"id":"2411.07326","title":"$SE(3)$ Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation","created":"2024-11-11","cited_by_count":6,"area":null},{"id":"2506.02112","title":"SAB3R: Semantic-Augmented Backbone in 3D Reconstruction","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2508.11185","title":"CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector","created":"2025-08-15","cited_by_count":6,"area":null},{"id":"2511.22686","title":"Emergent Extreme-View Geometry in 3D Foundation Models","created":"2025-11-27","cited_by_count":6,"area":null},{"id":"2405.06181","title":"Residual-NeRF: Learning Residual NeRFs for Transparent Object Manipulation","created":"2024-05-10","cited_by_count":5,"area":null},{"id":"2512.21883","title":"Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer","created":"2025-12-26","cited_by_count":5,"area":null},{"id":"2603.17840","title":"Video Understanding: From Geometry and Semantics to Unified Models","created":"2026-03-18","cited_by_count":5,"area":null},{"id":"2604.09429","title":"Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories","created":"2026-04-10","cited_by_count":5,"area":null},{"id":"2606.27345","title":"SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion Transformers","created":"2026-06-25","cited_by_count":5,"area":"diffusion"},{"id":"2410.18962","title":"Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction","created":"2024-10-24","cited_by_count":4,"area":null},{"id":"2411.00543","title":"3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction","created":"2024-11-01","cited_by_count":4,"area":null},{"id":"2509.15220","title":"Lightweight and Accurate Multi-View Stereo with Confidence-Aware Diffusion Model","created":"2025-09-18","cited_by_count":4,"area":"diffusion"},{"id":"2510.18521","title":"RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimation","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2512.08930","title":"Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment","created":"2025-12-09","cited_by_count":4,"area":null},{"id":"2512.25073","title":"GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstruction","created":"2025-12-31","cited_by_count":4,"area":null},{"id":"2601.13837","title":"FastGHA: Generalized Few-Shot 3D Gaussian Head Avatars with Real-Time Animation","created":"2026-01-20","cited_by_count":4,"area":null},{"id":"2604.08500","title":"FrameCrafter: Novel View Synthesis as Video Completion","created":"2026-04-09","cited_by_count":4,"area":"diffusion"},{"id":"2605.07079","title":"Learning Visual Feature-Based World Models via Residual Latent Action","created":"2026-05-08","cited_by_count":4,"area":"wm"},{"id":"2605.12938","title":"CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation","created":"2026-05-13","cited_by_count":4,"area":"wm"},{"id":"2509.00843","title":"Look Beyond: Two-Stage Scene View Generation via Panorama and Video Diffusion","created":"2025-08-31","cited_by_count":3,"area":"diffusion"},{"id":"2603.17375","title":"Stereo World Model: Camera-Guided Stereo Video Generation","created":"2026-03-18","cited_by_count":3,"area":"wm"},{"id":"2603.20588","title":"RayMap3R: Inference-Time RayMap for Dynamic 3D Reconstruction","created":"2026-03-21","cited_by_count":3,"area":null},{"id":"2404.14280","title":"RESfM: Robust Deep Equivariant Structure from Motion","created":"2024-04-22","cited_by_count":2,"area":null},{"id":"2407.10331","title":"3D Foundation Models Enable Simultaneous Geometry and Pose Estimation of Grasped Objects","created":"2024-07-14","cited_by_count":2,"area":null},{"id":"2412.08412","title":"Pragmatist: Multiview Conditional Diffusion Models for High-Fidelity 3D Reconstruction from Unposed Sparse Views","created":"2024-12-11","cited_by_count":2,"area":"diffusion"},{"id":"2412.09648","title":"DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models","created":"2024-12-11","cited_by_count":2,"area":"diffusion"},{"id":"2502.05175","title":"Fillerbuster: Unified Generative Scene Completion Model for Casual Captures","created":"2025-02-07","cited_by_count":2,"area":"diffusion"},{"id":"2503.21581","title":"AlignDiff: Learning Physically-Grounded Camera Alignment via Diffusion","created":"2025-03-27","cited_by_count":2,"area":null},{"id":"2505.24819","title":"Bi-Manual Joint Camera Calibration and Scene Representation","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2506.13030","title":"WildCAT3D: Appearance-Aware Multi-View Diffusion in the Wild","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2507.01603","title":"DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation","created":"2025-07-02","cited_by_count":2,"area":"diffusion"},{"id":"2507.09993","title":"3DGAA: Realistic and Robust 3D Gaussian-based Adversarial Attack for Autonomous Driving","created":"2025-07-14","cited_by_count":2,"area":null},{"id":"2606.24472","title":"G$^3$VLA: Geometric inductive bias for Vision-Language-Action Models","created":"2026-06-23","cited_by_count":2,"area":"vla"},{"id":"2608.20308","title":"ACE-Ego-Hand: Repurposing Video Diffusion Models for Occlusion-Robust Egocentric 3D Hand Motion Recovery","created":"2026-08-20","cited_by_count":2,"area":"diffusion"},{"id":"2404.18394","title":"Reconstructing Satellites in 3D from Amateur Telescope Images","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2411.15860","title":"Generalizable Single-view Object Pose Estimation by Two-side Generating and Matching","created":"2024-11-24","cited_by_count":1,"area":null},{"id":"2504.00639","title":"Coca-Splat: Collaborative Optimization for Camera Parameters and 3D Gaussians","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2505.04864","title":"Auto-regressive transformation for image alignment","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2505.22978","title":"Pose-free 3D Gaussian splatting via shape-ray estimation","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2507.10265","title":"Kaleidoscopic Background Attack: Disrupting Pose Estimation with Multi-Fold Radial Symmetry Textures","created":"2025-07-14","cited_by_count":1,"area":null}],"next_cursor":"100"}