{"total":75,"rows":[{"id":"2406.01584","title":"SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models","created":"2024-06-03","cited_by_count":311,"area":"lr"},{"id":"2410.19115","title":"MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision","created":"2024-10-24","cited_by_count":299,"area":null},{"id":"2412.12392","title":"MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors","created":"2024-12-16","cited_by_count":205,"area":null},{"id":"2406.09394","title":"WonderWorld: Interactive 3D Scene Generation from a Single Image","created":"2024-06-13","cited_by_count":202,"area":null},{"id":"2504.00983","title":"WorldScore: A Unified Evaluation Benchmark for World Generation","created":"2025-04-01","cited_by_count":156,"area":null},{"id":"2411.08128","title":"CameraHMR: Aligning People with Perspective","created":"2024-11-12","cited_by_count":65,"area":null},{"id":"2311.17138","title":"Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now","created":"2023-11-28","cited_by_count":61,"area":null},{"id":"2404.03421","title":"Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View","created":"2024-04-04","cited_by_count":61,"area":null},{"id":"2403.13438","title":"SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors","created":"2024-03-18","cited_by_count":54,"area":"lr"},{"id":"2409.06704","title":"GeoCalib: Learning Single-image Calibration with Geometric Optimization","created":"2024-09-10","cited_by_count":52,"area":null},{"id":"2501.02464","title":"Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera","created":"2025-01-05","cited_by_count":40,"area":null},{"id":"2306.00180","title":"FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow","created":"2023-05-31","cited_by_count":39,"area":null},{"id":"2412.04458","title":"Cubify Anything: Scaling Indoor 3D Object Detection","created":"2024-12-05","cited_by_count":39,"area":null},{"id":"2505.00788","title":"SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models","created":"2025-05-01","cited_by_count":38,"area":"lr"},{"id":"2505.08548","title":"From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation","created":"2025-05-13","cited_by_count":35,"area":"lr"},{"id":"2306.10988","title":"Tame a Wild Camera: In-the-Wild Monocular Camera Calibration","created":"2023-06-19","cited_by_count":34,"area":null},{"id":"2312.13252","title":"Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Model","created":"2023-12-20","cited_by_count":29,"area":"diffusion"},{"id":"2307.03244","title":"PSDR-Room: Single Photo to Scene using Differentiable Rendering","created":"2023-07-06","cited_by_count":23,"area":null},{"id":"2303.10559","title":"Deep Learning for Camera Calibration and Beyond: A Survey","created":"2023-03-19","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":"2303.11329","title":"Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation","created":"2023-03-20","cited_by_count":18,"area":null},{"id":"2503.12701","title":"AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration","created":"2025-03-16","cited_by_count":18,"area":null},{"id":"2403.18493","title":"VersaT2I: Improving Text-to-Image Models with Versatile Reward","created":"2024-03-27","cited_by_count":17,"area":null},{"id":"2410.08168","title":"ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusion","created":"2024-10-10","cited_by_count":16,"area":null},{"id":"2604.08626","title":"WildDet3D: Scaling Promptable 3D Detection in the Wild","created":"2026-04-09","cited_by_count":14,"area":null},{"id":"2501.12910","title":"PreciseCam: Precise Camera Control for Text-to-Image Generation","created":"2025-01-22","cited_by_count":13,"area":null},{"id":"2506.01955","title":"Dual-Process Image Generation","created":"2025-06-02","cited_by_count":12,"area":null},{"id":"2503.16289","title":"SceneMI: Motion In-betweening for Modeling Human-Scene Interactions","created":"2025-03-20","cited_by_count":11,"area":null},{"id":"2601.22054","title":"MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2405.15619","title":"DiffCalib: Reformulating Monocular Camera Calibration as Diffusion-Based Dense Incident Map Generation","created":"2024-05-24","cited_by_count":9,"area":"diffusion"},{"id":"2409.16178","title":"SDFit: 3D Object Pose and Shape by Fitting a Morphable SDF to a Single Image","created":"2024-09-24","cited_by_count":9,"area":null},{"id":"2505.24870","title":"GenSpace: Benchmarking Spatially-Aware Image Generation","created":"2025-05-30","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":"2507.18678","title":"Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting","created":"2025-07-24","cited_by_count":8,"area":null},{"id":"2403.19653","title":"Detecting Origin Attribution for Text-to-Image Diffusion Models","created":"2024-03-28","cited_by_count":7,"area":"diffusion"},{"id":"2601.16192","title":"360Anything: Geometry-Free Lifting of Images and Videos to 360{\\deg}","created":"2026-01-22","cited_by_count":7,"area":null},{"id":"2411.07096","title":"Extreme Rotation Estimation in the Wild","created":"2024-11-11","cited_by_count":6,"area":null},{"id":"2508.08384","title":"Spatiotemporally Consistent Indoor Lighting Estimation with Diffusion Priors","created":"2025-08-11","cited_by_count":6,"area":"diffusion"},{"id":"2312.06594","title":"Mitigating Perspective Distortion-induced Shape Ambiguity in Image Crops","created":"2023-12-11","cited_by_count":4,"area":null},{"id":"2509.11862","title":"Bridging Vision Language Models and Symbolic Grounding for Video Question Answering","created":"2025-09-15","cited_by_count":4,"area":"mllm"},{"id":"2407.18914","title":"Floating No More: Object-Ground Reconstruction from a Single Image","created":"2024-07-26","cited_by_count":3,"area":null},{"id":"2603.05888","title":"PixARMesh: Autoregressive Mesh-Native Single-View Scene Reconstruction","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2603.25411","title":"HiSpatial: Taming Hierarchical 3D Spatial Understanding in Vision-Language Models","created":"2026-03-26","cited_by_count":3,"area":"lr"},{"id":"2405.02296","title":"M\\\"obius Transform for Mitigating Perspective Distortions in Representation Learning","created":"2024-03-07","cited_by_count":2,"area":null},{"id":"2412.04471","title":"PaintScene4D: Consistent 4D Scene Generation from Text Prompts","created":"2024-12-05","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":"2510.23589","title":"InFlux: A Benchmark for Self-Calibration of Dynamic Intrinsics of Video Cameras","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2512.09112","title":"GimbalDiffusion: Gravity-Aware Camera Control for Video Generation","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2605.14615","title":"CalibAnyView: Beyond Single-View Camera Calibration in the Wild","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2605.27372","title":"G3T Up! Gravity Aligned Coordinate Frames Simplify Pointmap Processing","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2606.14841","title":"Multi-HMR 2: Multi-Person Camera-Centric Human Detection, Mesh Recovery and Tracking","created":"2026-06-12","cited_by_count":2,"area":null},{"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":"2409.19641","title":"fCOP: Focal Length Estimation from Category-level Object Priors","created":"2024-09-29","cited_by_count":1,"area":null},{"id":"2504.11031","title":"Acquisition of high-quality images for camera calibration in robotics applications via speech prompts","created":"2025-04-15","cited_by_count":1,"area":null},{"id":"2504.16499","title":"PRaDA: Projective Radial Distortion Averaging","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2505.00866","title":"Are Minimal Radial Distortion Solvers Really Necessary for Relative Pose Estimation?","created":"2025-05-01","cited_by_count":1,"area":null},{"id":"2607.04880","title":"PRISM: Personalized Robotic Dataset Generation via Image-based Scene and Motion Synthesis","created":"2026-07-06","cited_by_count":1,"area":"vla"},{"id":"2609.01479","title":"CameraEditor: Camera-Controlled Image Editing via Video-Prior Sequential Modeling","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.37732","title":"The Camera Inside the Editor: Reading the Implicit Camera of Image Editors with Painted Calibration Patterns","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2403.15583","title":"U-ARE-ME: Uncertainty-Aware Rotation Estimation in Manhattan Environments","created":"2024-03-22","cited_by_count":0,"area":null},{"id":"2410.03686","title":"LCM: Log Conformal Maps for Robust Representation Learning to Mitigate Perspective Distortion","created":"2024-09-20","cited_by_count":0,"area":null},{"id":"2502.08902","title":"CoL3D: Collaborative Learning of Single-view Depth and Camera Intrinsics for Metric 3D Shape Recovery","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2503.21562","title":"uLayout: Unified Room Layout Estimation for Perspective and Panoramic Images","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2509.17620","title":"Tensor-Based Self-Calibration of Cameras via the TrifocalCalib Method","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2601.22796","title":"HeatMat: Simulation of City Material Impact on Urban Heat Island Effect","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.19035","title":"OpenVO: Open-World Visual Odometry with Temporal Dynamics Awareness","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2603.23179","title":"Gimbal360: Canonicalizing Planar Diffusion for Spherical Panorama Completion","created":"2026-03-24","cited_by_count":0,"area":"diffusion"},{"id":"2606.14619","title":"StereoGeo: an end-to-end stereo camera calibration method","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.22094","title":"Cross-View Yaw Estimation in Location Uncertainty with Line-Aligning Yaw Scoring","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2607.21438","title":"DAPM: UAV Monocular Depth Estimation from Any Height, Pitch, Roll and FOV","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.22039","title":"ORBIT++: Benchmarking SfM in the Wild with 360{\\deg} Video","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2609.04196","title":"Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.35658","title":"Many Eyes, One World: Feed-Forward 3D Reconstruction from Mixed Cameras","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01388","title":"Supervising Sound Localization by In-the-wild Egomotion","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.01589","title":"PAGER: Partial-to-global Alignment via Geometric and Relational Distillation","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}