{"list":"other","total":71,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2008.05711","title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","created":"2020-08-13","cited_by_count":1044},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"1610.06475","title":"ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras","created":"2016-10-20","cited_by_count":806},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"id":"2112.12130","title":"NICE-SLAM: Neural Implicit Scalable Encoding for SLAM","created":"2021-12-22","cited_by_count":589},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"2312.06741","title":"Gaussian Splatting SLAM","created":"2023-12-11","cited_by_count":415},{"id":"1606.05830","title":"Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age","created":"2016-06-19","cited_by_count":411},{"id":"2302.07817","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","created":"2023-02-15","cited_by_count":409},{"id":"2312.02126","title":"SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM","created":"2023-12-04","cited_by_count":388},{"id":"2312.03203","title":"Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields","created":"2023-12-06","cited_by_count":364},{"id":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363},{"id":"2303.09551","title":"SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving","created":"2023-03-16","cited_by_count":316},{"id":"2302.12251","title":"VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion","created":"2023-02-23","cited_by_count":313},{"id":"2311.11700","title":"GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting","created":"2023-11-20","cited_by_count":278},{"id":"2311.18482","title":"Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding","created":"2023-11-30","cited_by_count":208},{"id":"2412.12392","title":"MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors","created":"2024-12-16","cited_by_count":205},{"id":"2307.01492","title":"FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation","created":"2023-07-04","cited_by_count":165},{"id":"2405.17429","title":"GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction","created":"2024-05-27","cited_by_count":157},{"id":"2311.16728","title":"Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Cameras","created":"2023-11-28","cited_by_count":141},{"id":"2505.12549","title":"VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold","created":"2025-05-18","cited_by_count":136},{"id":"2311.12754","title":"SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction","created":"2023-11-21","cited_by_count":133},{"id":"2309.09502","title":"RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision","created":"2023-09-18","cited_by_count":128},{"id":"2305.14059","title":"Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses","created":"2023-05-23","cited_by_count":107},{"id":"2402.07181","title":"3D Gaussian as a New Era: A Survey","created":"2024-02-11","cited_by_count":104},{"id":"2404.09502","title":"SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction","created":"2024-04-15","cited_by_count":96},{"id":"2309.14616","title":"NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space","created":"2023-09-26","cited_by_count":90},{"id":"2402.03246","title":"SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAM","created":"2024-02-05","cited_by_count":87},{"id":"2412.04384","title":"GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction","created":"2024-12-05","cited_by_count":86},{"id":"2403.12550","title":"RGBD GS-ICP SLAM","created":"2024-03-19","cited_by_count":65},{"id":"2401.09413","title":"POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images","created":"2024-01-17","cited_by_count":52},{"id":"2408.11447","title":"GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting","created":"2024-08-21","cited_by_count":50},{"id":"2312.03774","title":"OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries","created":"2023-12-06","cited_by_count":48},{"id":"2412.13193","title":"GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding","created":"2024-12-17","cited_by_count":46},{"id":"2412.04380","title":"EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding","created":"2024-12-05","cited_by_count":45},{"id":"2411.09219","title":"Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation","created":"2024-11-14","cited_by_count":39},{"id":"2407.04049","title":"Occupancy as Set of Points","created":"2024-07-04","cited_by_count":38},{"id":"2407.11730","title":"Monocular Occupancy Prediction for Scalable Indoor Scenes","created":"2024-07-16","cited_by_count":31},{"id":"2504.09540","title":"EmbodiedOcc++: Boosting Embodied 3D Occupancy Prediction with Plane Regularization and Uncertainty Sampler","created":"2025-04-13","cited_by_count":27},{"id":"2502.17288","title":"GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flow","created":"2025-02-24","cited_by_count":24},{"id":"2407.12294","title":"VEON: Vocabulary-Enhanced Occupancy Prediction","created":"2024-07-17","cited_by_count":22},{"id":"2404.19149","title":"SAGS: Structure-Aware 3D Gaussian Splatting","created":"2024-04-29","cited_by_count":21},{"id":"2404.06926","title":"Gaussian-LIC: Real-Time Photo-Realistic SLAM with Gaussian Splatting and LiDAR-Inertial-Camera Fusion","created":"2024-04-10","cited_by_count":17},{"id":"2403.11679","title":"NEDS-SLAM: A Neural Explicit Dense Semantic SLAM Framework using 3D Gaussian Splatting","created":"2024-03-18","cited_by_count":16},{"id":"2411.17660","title":"DROID-Splat: Combining end-to-end SLAM with 3D Gaussian Splatting","created":"2024-11-26","cited_by_count":15},{"id":"2504.14604","title":"RoboOcc: Enhancing the Geometric and Semantic Scene Understanding for Robots","created":"2025-04-20","cited_by_count":15},{"id":"2303.09977","title":"Semantic Scene Completion with Cleaner Self","created":"2023-03-17","cited_by_count":12},{"id":"2409.07456","title":"Self-Evolving Depth-Supervised 3D Gaussian Splatting from Rendered Stereo Pairs","created":"2024-09-11","cited_by_count":11},{"id":"2411.15800","title":"PG-SLAM: Photo-realistic and Geometry-aware RGB-D SLAM in Dynamic Environments","created":"2024-11-24","cited_by_count":11},{"id":"2602.21552","title":"Generalizing Visual Geometry Priors to Sparse Gaussian Occupancy Prediction","created":"2026-02-25","cited_by_count":11},{"id":"2410.08262","title":"ROMAN: Open-Set Object Map Alignment for Robust View-Invariant Global Localization","created":"2024-10-10","cited_by_count":10},{"id":"2502.05752","title":"PINGS: Gaussian Splatting Meets Distance Fields within a Point-Based Implicit Neural Map","created":"2025-02-09","cited_by_count":10},{"id":"2504.10117","title":"AGO: Adaptive Grounding for Open World 3D Occupancy Prediction","created":"2025-04-14","cited_by_count":9},{"id":"2503.12369","title":"L2COcc: Lightweight Camera-Centric Semantic Scene Completion via Distillation of LiDAR Model","created":"2025-03-16","cited_by_count":8},{"id":"2407.21126","title":"Self-supervised Multi-future Occupancy Forecasting for Autonomous Driving","created":"2024-07-30","cited_by_count":7},{"id":"2409.13055","title":"MGSO: Monocular Real-time Photometric SLAM with Efficient 3D Gaussian Splatting","created":"2024-09-19","cited_by_count":7},{"id":"2109.04687","title":"CLINS: Continuous-Time Trajectory Estimation for LiDAR-Inertial System","created":"2021-09-10","cited_by_count":6},{"id":"2507.04004","title":"Gaussian-LIC2: LiDAR-Inertial-Camera Gaussian Splatting SLAM","created":"2025-07-05","cited_by_count":5},{"id":"2602.22667","title":"Monocular Open Vocabulary Occupancy Prediction for Indoor Scenes","created":"2026-02-26","cited_by_count":5},{"id":"2510.22141","title":"LOC: A General Language-Guided Framework for Open-Set 3D Occupancy Prediction","created":"2025-10-25","cited_by_count":4},{"id":"2602.02318","title":"Enhancing Indoor Occupancy Prediction via Sparse Query-Based Multi-Level Consistent Knowledge Distillation","created":"2026-02-02","cited_by_count":4},{"id":"2603.27781","title":"GS3LAM: Gaussian Semantic Splatting SLAM","created":"2026-03-29","cited_by_count":4},{"id":"2601.00359","title":"Efficient Prediction of Dense Visual Embeddings via Distillation and RGB-D Transformers","created":"2026-01-01","cited_by_count":1}],"next_cursor":null}