{"list":"other","total":70,"rows":[{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2311.16493","title":"Mip-Splatting: Alias-free 3D Gaussian Splatting","created":"2023-11-27","cited_by_count":667},{"id":"2306.13643","title":"LightGlue: Local Feature Matching at Light Speed","created":"2023-06-23","cited_by_count":590},{"id":"1905.03561","title":"D2-Net: A Trainable CNN for Joint Detection and Description of Local Features","created":"2019-05-09","cited_by_count":326},{"id":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314},{"id":"2006.13566","title":"DISK: Learning local features with policy gradient","created":"2020-06-24","cited_by_count":312},{"id":"2305.15404","title":"RoMa: Robust Dense Feature Matching","created":"2023-05-24","cited_by_count":302},{"id":"2203.04838","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","created":"2022-03-09","cited_by_count":231},{"id":"2202.00667","title":"DKM: Dense Kernelized Feature Matching for Geometry Estimation","created":"2022-02-01","cited_by_count":177},{"id":"2208.14201","title":"ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer","created":"2022-08-30","cited_by_count":171},{"id":"1805.09662","title":"LF-Net: Learning Local Features from Images","created":"2018-05-24","cited_by_count":151},{"id":"2308.02097","title":"Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation","created":"2023-08-04","cited_by_count":129},{"id":"2203.09645","title":"MatchFormer: Interleaving Attention in Transformers for Feature Matching","created":"2022-03-17","cited_by_count":126},{"id":"2404.19174","title":"XFeat: Accelerated Features for Lightweight Image Matching","created":"2024-04-30","cited_by_count":113},{"id":"2501.06336","title":"MEt3R: Measuring Multi-View Consistency in Generated Images","created":"2025-01-10","cited_by_count":95},{"id":"2204.04120","title":"Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline","created":"2022-04-08","cited_by_count":91},{"id":"2202.09769","title":"Dynamic Spatial Propagation Network for Depth Completion","created":"2022-02-20","cited_by_count":71},{"id":"2404.04256","title":"Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation","created":"2024-04-05","cited_by_count":71},{"id":"2403.09634","title":"OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning","created":"2024-03-14","cited_by_count":65},{"id":"2204.11700","title":"ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matching","created":"2022-04-25","cited_by_count":62},{"id":"2405.12979","title":"OmniGlue: Generalizable Feature Matching with Foundation Model Guidance","created":"2024-05-21","cited_by_count":56},{"id":"2007.13143","title":"Challenge-Aware RGBT Tracking","created":"2020-07-26","cited_by_count":53},{"id":"2404.09692","title":"XoFTR: Cross-modal Feature Matching Transformer","created":"2024-04-15","cited_by_count":48},{"id":"2412.19412","title":"MINIMA: Modality Invariant Image Matching","created":"2024-12-27","cited_by_count":47},{"id":"2501.10761","title":"Infrared and Visible Image Fusion: From Data Compatibility to Task Adaption","created":"2025-01-18","cited_by_count":46},{"id":"2110.08988","title":"FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segmentation","created":"2021-10-18","cited_by_count":45},{"id":"2403.16002","title":"SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking","created":"2024-03-24","cited_by_count":44},{"id":"2103.01055","title":"P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching","created":"2021-03-01","cited_by_count":42},{"id":"2112.02306","title":"Toward Practical Monocular Indoor Depth Estimation","created":"2021-12-04","cited_by_count":42},{"id":"2303.15710","title":"Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Tasks","created":"2023-03-28","cited_by_count":41},{"id":"2501.02464","title":"Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera","created":"2025-01-05","cited_by_count":40},{"id":"2407.11351","title":"Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities","created":"2024-07-16","cited_by_count":31},{"id":"2410.07577","title":"3D Vision-Language Gaussian Splatting","created":"2024-10-10","cited_by_count":31},{"id":"2411.19278","title":"OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration","created":"2024-11-28","cited_by_count":30},{"id":"2404.12154","title":"StyleBooth: Image Style Editing with Multimodal Instruction","created":"2024-04-18","cited_by_count":28},{"id":"2205.07439","title":"ReDFeat: Recoupling Detection and Description for Multimodal Feature Learning","created":"2022-05-16","cited_by_count":26},{"id":"2406.11711","title":"OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations","created":"2024-06-17","cited_by_count":24},{"id":"2103.03150","title":"SSTN: Self-Supervised Domain Adaptation Thermal Object Detection for Autonomous Driving","created":"2021-03-04","cited_by_count":23},{"id":"2205.09383","title":"Emergent Visual Sensors for Autonomous Vehicles","created":"2022-05-19","cited_by_count":19},{"id":"2303.06834","title":"DarkVisionNet: Low-Light Imaging via RGB-NIR Fusion with Deep Inconsistency Prior","created":"2023-03-13","cited_by_count":19},{"id":"2204.08759","title":"Edge-enhanced Feature Distillation Network for Efficient Super-Resolution","created":"2022-04-19","cited_by_count":18},{"id":"2310.19372","title":"RGB-X Object Detection via Scene-Specific Fusion Modules","created":"2023-10-30","cited_by_count":15},{"id":"2509.24878","title":"ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation","created":"2025-09-29","cited_by_count":14},{"id":"2204.10266","title":"DooDLeNet: Double DeepLab Enhanced Feature Fusion for Thermal-color Semantic Segmentation","created":"2022-04-21","cited_by_count":13},{"id":"2409.07200","title":"ThermalGaussian: Thermal 3D Gaussian Splatting","created":"2024-09-11","cited_by_count":13},{"id":"2309.15751","title":"InfraParis: A multi-modal and multi-task autonomous driving dataset","created":"2023-09-27","cited_by_count":12},{"id":"2311.14459","title":"IDD-AW: A Benchmark for Safe and Robust Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather","created":"2023-11-24","cited_by_count":12},{"id":"2508.16408","title":"SAMFusion: Sensor-Adaptive Multimodal Fusion for 3D Object Detection in Adverse Weather","created":"2025-08-22","cited_by_count":12},{"id":"2503.09447","title":"Online Language Splatting","created":"2025-03-12","cited_by_count":10},{"id":"2503.02581","title":"Unveiling the Potential of Segment Anything Model 2 for RGB-Thermal Semantic Segmentation with Language Guidance","created":"2025-03-04","cited_by_count":9},{"id":"2503.17122","title":"R-LiViT: A LiDAR-Visual-Thermal Dataset Enabling Vulnerable Road User Focused Roadside Perception","created":"2025-03-21","cited_by_count":9},{"id":"2505.24053","title":"3DGEER: 3D Gaussian Rendering Made Exact and Efficient for Generic Cameras","created":"2025-05-29","cited_by_count":8},{"id":"2003.06945","title":"Scene Completeness-Aware Lidar Depth Completion for Driving Scenario","created":"2020-03-15","cited_by_count":7},{"id":"2203.09091","title":"deepNIR: Datasets for generating synthetic NIR images and improved fruit detection system using deep learning techniques","created":"2022-03-17","cited_by_count":7},{"id":"2411.18025","title":"Pixel-aligned RGB-NIR Stereo Imaging and Dataset for Robot Vision","created":"2024-11-27","cited_by_count":7},{"id":"2504.02801","title":"F-ViTA: Foundation Model Guided Visible to Thermal Translation","created":"2025-04-03","cited_by_count":7},{"id":"2410.22733","title":"ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses","created":"2024-10-30","cited_by_count":6},{"id":"2401.15159","title":"RABBIT: A Robot-Assisted Bed Bathing System with Multimodal Perception and Integrated Compliance","created":"2024-01-26","cited_by_count":5},{"id":"2006.00821","title":"Exploring Thermal Images for Object Detection in Underexposure Regions for Autonomous Driving","created":"2020-06-01","cited_by_count":4},{"id":"2509.16017","title":"DistillMatch: Leveraging Knowledge Distillation from Vision Foundation Model for Multimodal Image Matching","created":"2025-09-19","cited_by_count":4},{"id":"2409.16706","title":"Pix2Next: Leveraging Vision Foundation Models for RGB to NIR Image Translation","created":"2024-09-25","cited_by_count":2},{"id":"2409.02486","title":"Boosting Generalizability towards Zero-Shot Cross-Dataset Single-Image Indoor Depth by Meta-Initialization","created":"2024-09-04","cited_by_count":1}],"next_cursor":null}