{"list":"other","total":59,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"2312.06741","title":"Gaussian Splatting SLAM","created":"2023-12-11","cited_by_count":415},{"id":"2312.16084","title":"LangSplat: 3D Language Gaussian Splatting","created":"2023-12-26","cited_by_count":415},{"id":"2312.00732","title":"Gaussian Grouping: Segment and Edit Anything in 3D Scenes","created":"2023-12-01","cited_by_count":393},{"id":"2210.05714","title":"Visual Language Maps for Robot Navigation","created":"2022-10-11","cited_by_count":365},{"id":"2312.03203","title":"Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields","created":"2023-12-06","cited_by_count":364},{"id":"1910.04751","title":"Panoptic-DeepLab","created":"2019-10-10","cited_by_count":363},{"id":"2210.03105","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","created":"2022-10-06","cited_by_count":303},{"id":"2205.04334","title":"Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation","created":"2022-05-09","cited_by_count":243},{"id":"1905.10520","title":"6-DOF GraspNet: Variational Grasp Generation for Object Manipulation","created":"2019-05-25","cited_by_count":242},{"id":"2311.18482","title":"Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding","created":"2023-11-30","cited_by_count":208},{"id":"2203.01509","title":"SoftGroup for 3D Instance Segmentation on Point Clouds","created":"2022-03-03","cited_by_count":200},{"id":"2209.03494","title":"Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations","created":"2022-09-07","cited_by_count":196},{"id":"2304.14377","title":"Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM","created":"2023-04-27","cited_by_count":184},{"id":"2212.09802","title":"Panoptic Lifting for 3D Scene Understanding with Neural Fields","created":"2022-12-19","cited_by_count":174},{"id":"2304.04278","title":"Point-SLAM: Dense Neural Point Cloud-based SLAM","created":"2023-04-09","cited_by_count":160},{"id":"2203.15224","title":"Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation","created":"2022-03-29","cited_by_count":152},{"id":"2210.15858","title":"Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representation","created":"2022-10-28","cited_by_count":149},{"id":"2406.02058","title":"OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding","created":"2024-06-04","cited_by_count":145},{"id":"1609.05130","title":"SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks","created":"2016-09-16","cited_by_count":135},{"id":"1905.01220","title":"Seamless Scene Segmentation","created":"2019-05-03","cited_by_count":112},{"id":"2412.09401","title":"SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos","created":"2024-12-12","cited_by_count":102},{"id":"1903.01177","title":"PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things","created":"2019-03-04","cited_by_count":98},{"id":"2211.05776","title":"High-Quality Entity Segmentation","created":"2022-11-10","cited_by_count":93},{"id":"2401.01970","title":"FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding","created":"2024-01-03","cited_by_count":86},{"id":"2403.15624","title":"Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting","created":"2024-03-22","cited_by_count":82},{"id":"2401.07745","title":"MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation","created":"2024-01-15","cited_by_count":56},{"id":"2310.03923","title":"Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation","created":"2023-10-05","cited_by_count":54},{"id":"2208.10925","title":"Vox-Surf: Voxel-based Implicit Surface Representation","created":"2022-08-21","cited_by_count":49},{"id":"2212.00338","title":"3D-Aware Object Goal Navigation via Simultaneous Exploration and Identification","created":"2022-12-01","cited_by_count":46},{"id":"2409.14067","title":"SplatLoc: 3D Gaussian Splatting-based Visual Localization for Augmented Reality","created":"2024-09-21","cited_by_count":43},{"id":"2408.11811","title":"EmbodiedSAM: Online Segment Any 3D Thing in Real Time","created":"2024-08-21","cited_by_count":40},{"id":"2411.19235","title":"InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception","created":"2024-11-28","cited_by_count":35},{"id":"2502.00173","title":"Lifting by Gaussians: A Simple, Fast and Flexible Method for 3D Instance Segmentation","created":"2025-01-31","cited_by_count":23},{"id":"2407.20853","title":"NIS-SLAM: Neural Implicit Semantic RGB-D SLAM for 3D Consistent Scene Understanding","created":"2024-07-30","cited_by_count":19},{"id":"2410.10659","title":"PCF-Lift: Panoptic Lifting by Probabilistic Contrastive Fusion","created":"2024-10-14","cited_by_count":16},{"id":"2503.18107","title":"PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding","created":"2025-03-23","cited_by_count":16},{"id":"2411.15043","title":"Open-Vocabulary Online Semantic Mapping for SLAM","created":"2024-11-22","cited_by_count":12},{"id":"2503.01309","title":"OnlineAnySeg: Online Zero-Shot 3D Segmentation by Visual Foundation Model Guided 2D Mask Merging","created":"2025-03-03","cited_by_count":12},{"id":"2411.16253","title":"Open-Vocabulary Octree-Graph for 3D Scene Understanding","created":"2024-11-25","cited_by_count":10},{"id":"2404.06836","title":"O2V-Mapping: Online Open-Vocabulary Mapping with Neural Implicit Representation","created":"2024-04-10","cited_by_count":9},{"id":"2403.12536","title":"Vox-Fusion++: Voxel-based Neural Implicit Dense Tracking and Mapping with Multi-maps","created":"2024-03-19","cited_by_count":7},{"id":"2601.14161","title":"One-Shot Refiner: Boosting Feed-forward Novel View Synthesis via One-Step Diffusion","created":"2026-01-20","cited_by_count":6},{"id":"2503.06117","title":"NeuraLoc: Visual Localization in Neural Implicit Map with Dual Complementary Features","created":"2025-03-08","cited_by_count":5},{"id":"2510.25129","title":"AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians","created":"2025-10-29","cited_by_count":4},{"id":"2512.01296","title":"EGG-Fusion: Efficient 3D Reconstruction with Geometry-aware Gaussian Surfel on the Fly","created":"2025-12-01","cited_by_count":3},{"id":"2603.16301","title":"OGScene3D: Incremental Open-Vocabulary 3D Gaussian Scene Graph Mapping for Scene Understanding","created":"2026-03-17","cited_by_count":3}],"next_cursor":null}