{"total":1443,"rows":[{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567,"area":null},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556,"area":null},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539,"area":null},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410,"area":null},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984,"area":null},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983,"area":null},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687,"area":null},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647,"area":"mllm"},{"id":"2306.13643","title":"LightGlue: Local Feature Matching at Light Speed","created":"2023-06-23","cited_by_count":590,"area":null},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548,"area":null},{"id":"2203.11496","title":"TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers","created":"2022-03-22","cited_by_count":466,"area":"wm"},{"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":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327,"area":null},{"id":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314,"area":null},{"id":"2305.15404","title":"RoMa: Robust Dense Feature Matching","created":"2023-05-24","cited_by_count":302,"area":null},{"id":"2305.15347","title":"A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence","created":"2023-05-24","cited_by_count":301,"area":"diffusion"},{"id":"2408.16061","title":"3D Reconstruction with Spatial Memory","created":"2024-08-28","cited_by_count":277,"area":null},{"id":"2203.16194","title":"FlowFormer: A Transformer Architecture for Optical Flow","created":"2022-03-30","cited_by_count":275,"area":null},{"id":"2211.05783","title":"Unifying Flow, Stereo and Depth Estimation","created":"2022-11-10","cited_by_count":275,"area":null},{"id":"2410.24207","title":"No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images","created":"2024-10-31","cited_by_count":248,"area":null},{"id":"2103.01486","title":"Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition","created":"2021-03-02","cited_by_count":238,"area":null},{"id":"2312.04563","title":"Visual Geometry Grounded Deep Structure From Motion","created":"2023-12-07","cited_by_count":227,"area":null},{"id":"2308.07134","title":"Language is All a Graph Needs","created":"2023-08-14","cited_by_count":220,"area":null},{"id":"2407.20219","title":"Global Structure-from-Motion Revisited","created":"2024-07-29","cited_by_count":218,"area":null},{"id":"2202.06688","title":"Geometric Transformer for Fast and Robust Point Cloud Registration","created":"2022-02-14","cited_by_count":202,"area":null},{"id":"2108.08291","title":"Pixel-Perfect Structure-from-Motion with Featuremetric Refinement","created":"2021-08-18","cited_by_count":200,"area":null},{"id":"2103.09213","title":"Back to the Feature: Learning Robust Camera Localization from Pixels to Pose","created":"2021-03-16","cited_by_count":199,"area":null},{"id":"2211.11738","title":"SPARF: Neural Radiance Fields from Sparse and Noisy Poses","created":"2022-11-21","cited_by_count":195,"area":null},{"id":"2208.04726","title":"Deep Patch Visual Odometry","created":"2022-08-08","cited_by_count":190,"area":null},{"id":"2103.14167","title":"COTR: Correspondence Transformer for Matching Across Images","created":"2021-03-25","cited_by_count":183,"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":"2202.00667","title":"DKM: Dense Kernelized Feature Matching for Geometry Estimation","created":"2022-02-01","cited_by_count":177,"area":null},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177,"area":null},{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177,"area":null},{"id":"2208.14201","title":"ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer","created":"2022-08-30","cited_by_count":171,"area":null},{"id":"2311.12024","title":"PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction","created":"2023-11-20","cited_by_count":165,"area":null},{"id":"2103.14898","title":"SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences","created":"2021-03-27","cited_by_count":163,"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":"2303.02190","title":"MixVPR: Feature Mixing for Visual Place Recognition","created":"2023-03-03","cited_by_count":161,"area":null},{"id":"2205.12257","title":"OnePose: One-Shot Object Pose Estimation without CAD Models","created":"2022-05-24","cited_by_count":157,"area":null},{"id":"2601.20540","title":"Advancing Open-source World Models","created":"2026-01-28","cited_by_count":154,"area":"wm"},{"id":"2110.14076","title":"CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration","created":"2021-10-26","cited_by_count":152,"area":null},{"id":"2311.15937","title":"Optimal Transport Aggregation for Visual Place Recognition","created":"2023-11-27","cited_by_count":152,"area":null},{"id":"2302.02676","title":"Chain of Hindsight Aligns Language Models with Feedback","created":"2023-02-06","cited_by_count":148,"area":"alignment"},{"id":"2305.02296","title":"DynamicStereo: Consistent Dynamic Depth from Stereo Videos","created":"2023-05-03","cited_by_count":148,"area":null},{"id":"2306.15667","title":"PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment","created":"2023-06-27","cited_by_count":147,"area":null},{"id":"2103.05465","title":"PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency","created":"2021-03-09","cited_by_count":142,"area":null},{"id":"2103.17265","title":"Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors","created":"2021-03-31","cited_by_count":137,"area":null},{"id":"2103.16556","title":"Learning Target Candidate Association to Keep Track of What Not to Track","created":"2021-03-30","cited_by_count":131,"area":null},{"id":"2402.14817","title":"Cameras as Rays: Pose Estimation via Ray Diffusion","created":"2024-02-22","cited_by_count":131,"area":null},{"id":"2201.02767","title":"QuadTree Attention for Vision Transformers","created":"2022-01-08","cited_by_count":129,"area":null},{"id":"2509.26645","title":"TTT3R: 3D Reconstruction as Test-Time Training","created":"2025-09-30","cited_by_count":129,"area":null},{"id":"2203.09645","title":"MatchFormer: Interleaving Attention in Transformers for Feature Matching","created":"2022-03-17","cited_by_count":126,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2305.10626","title":"Language Models Meet World Models: Embodied Experiences Enhance Language Models","created":"2023-05-18","cited_by_count":124,"area":"wm"},{"id":"2204.10776","title":"Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images","created":"2022-04-22","cited_by_count":121,"area":null},{"id":"2304.03608","title":"ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation","created":"2023-04-07","cited_by_count":121,"area":null},{"id":"2305.15581","title":"Unsupervised Semantic Correspondence Using Stable Diffusion","created":"2023-05-24","cited_by_count":120,"area":"diffusion"},{"id":"2403.04765","title":"Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed","created":"2024-03-07","cited_by_count":120,"area":null},{"id":"2110.06558","title":"LENS: Localization enhanced by NeRF synthesis","created":"2021-10-13","cited_by_count":117,"area":null},{"id":"2111.14600","title":"TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers","created":"2021-11-29","cited_by_count":117,"area":null},{"id":"2405.17414","title":"Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control","created":"2024-05-27","cited_by_count":117,"area":"diffusion"},{"id":"2301.07673","title":"OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models","created":"2023-01-18","cited_by_count":115,"area":null},{"id":"2210.05494","title":"Map-free Visual Relocalization: Metric Pose Relative to a Single Image","created":"2022-10-11","cited_by_count":114,"area":null},{"id":"2302.11154","title":"Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities","created":"2023-02-22","cited_by_count":113,"area":null},{"id":"2404.19174","title":"XFeat: Accelerated Features for Lightweight Image Matching","created":"2024-04-30","cited_by_count":113,"area":null},{"id":"2308.10832","title":"EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition","created":"2023-08-21","cited_by_count":111,"area":null},{"id":"2305.14059","title":"Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses","created":"2023-05-23","cited_by_count":107,"area":null},{"id":"2304.08463","title":"Learning to Render Novel Views from Wide-Baseline Stereo Pairs","created":"2023-04-17","cited_by_count":104,"area":null},{"id":"2201.02001","title":"TransVPR: Transformer-based place recognition with multi-level attention aggregation","created":"2022-01-06","cited_by_count":102,"area":null},{"id":"2208.05963","title":"RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild","created":"2022-08-11","cited_by_count":102,"area":null},{"id":"2304.03410","title":"$R^{2}$Former: Unified $R$etrieval and $R$eranking Transformer for Place Recognition","created":"2023-04-06","cited_by_count":102,"area":null},{"id":"2210.10770","title":"LaMAR: Benchmarking Localization and Mapping for Augmented Reality","created":"2022-10-19","cited_by_count":100,"area":null},{"id":"2503.18945","title":"Aether: Geometric-Aware Unified World Modeling","created":"2025-03-24","cited_by_count":97,"area":"wm"},{"id":"2203.14517","title":"REGTR: End-to-end Point Cloud Correspondences with Transformers","created":"2022-03-28","cited_by_count":96,"area":null},{"id":"2103.06422","title":"Holistic 3D Scene Understanding from a Single Image with Implicit Representation","created":"2021-03-11","cited_by_count":94,"area":null},{"id":"2404.06609","title":"GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation","created":"2024-04-09","cited_by_count":94,"area":null},{"id":"2210.10239","title":"GSV-Cities: Toward Appropriate Supervised Visual Place Recognition","created":"2022-10-19","cited_by_count":93,"area":null},{"id":"2108.08771","title":"Learning to Match Features with Seeded Graph Matching Network","created":"2021-08-19","cited_by_count":92,"area":null},{"id":"2207.09137","title":"ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild","created":"2022-07-19","cited_by_count":92,"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":"2305.04926","title":"RelPose++: Recovering 6D Poses from Sparse-view Observations","created":"2023-05-08","cited_by_count":87,"area":null},{"id":"2503.17973","title":"PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos","created":"2025-03-23","cited_by_count":87,"area":null},{"id":"2111.12591","title":"Lepard: Learning partial point cloud matching in rigid and deformable scenes","created":"2021-11-24","cited_by_count":85,"area":null},{"id":"2204.03444","title":"Deep Visual Geo-localization Benchmark","created":"2022-04-07","cited_by_count":84,"area":null},{"id":"2304.02009","title":"OrienterNet: Visual Localization in 2D Public Maps with Neural Matching","created":"2023-04-04","cited_by_count":84,"area":null},{"id":"2308.03768","title":"GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer","created":"2023-07-25","cited_by_count":84,"area":null},{"id":"2103.06443","title":"Where is your place, Visual Place Recognition?","created":"2021-03-11","cited_by_count":82,"area":null},{"id":"2204.00559","title":"DFNet: Enhance Absolute Pose Regression with Direct Feature Matching","created":"2022-04-01","cited_by_count":82,"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":"2203.14628","title":"FS6D: Few-Shot 6D Pose Estimation of Novel Objects","created":"2022-03-28","cited_by_count":81,"area":null},{"id":"2307.01197","title":"Segment Anything Meets Point Tracking","created":"2023-07-03","cited_by_count":81,"area":null},{"id":"2109.13912","title":"PDC-Net+: Enhanced Probabilistic Dense Correspondence Network","created":"2021-09-28","cited_by_count":80,"area":null},{"id":"2407.15420","title":"Local All-Pair Correspondence for Point Tracking","created":"2024-07-22","cited_by_count":80,"area":null},{"id":"2311.18448","title":"HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video","created":"2023-11-30","cited_by_count":78,"area":null},{"id":"2106.02520","title":"CATs: Cost Aggregation Transformers for Visual Correspondence","created":"2021-06-04","cited_by_count":77,"area":null},{"id":"2402.11095","title":"GIM: Learning Generalizable Image Matcher From Internet Videos","created":"2024-02-16","cited_by_count":75,"area":null},{"id":"2108.09666","title":"Relational Embedding for Few-Shot Classification","created":"2021-08-22","cited_by_count":74,"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}],"next_cursor":"100"}