{"list":"other","total":70,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"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":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964},{"id":"2112.05131","title":"Plenoxels: Radiance Fields without Neural Networks","created":"2021-12-09","cited_by_count":1613},{"id":"2203.09517","title":"TensoRF: Tensorial Radiance Fields","created":"2022-03-17","cited_by_count":1280},{"id":"2008.02268","title":"NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections","created":"2020-08-05","cited_by_count":1232},{"id":"2111.11215","title":"Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction","created":"2021-11-22","cited_by_count":964},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2103.14024","title":"PlenOctrees for Real-time Rendering of Neural Radiance Fields","created":"2021-03-25","cited_by_count":905},{"id":"2103.13744","title":"KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs","created":"2021-03-25","cited_by_count":673},{"id":"2311.16493","title":"Mip-Splatting: Alias-free 3D Gaussian Splatting","created":"2023-11-27","cited_by_count":667},{"id":"1904.09664","title":"Deep Hough Voting for 3D Object Detection in Point Clouds","created":"2019-04-21","cited_by_count":648},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"2303.12789","title":"Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions","created":"2023-03-22","cited_by_count":484},{"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":"2312.03203","title":"Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields","created":"2023-12-06","cited_by_count":364},{"id":"2311.14521","title":"GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting","created":"2023-11-24","cited_by_count":335},{"id":"2410.13862","title":"DepthSplat: Connecting Gaussian Splatting and Depth","created":"2024-10-17","cited_by_count":286},{"id":"2205.04334","title":"Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation","created":"2022-05-09","cited_by_count":243},{"id":"2401.03890","title":"A Survey on 3D Gaussian Splatting","created":"2024-01-08","cited_by_count":224},{"id":"2311.18482","title":"Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding","created":"2023-11-30","cited_by_count":208},{"id":"2309.03903","title":"Tracking Anything with Decoupled Video Segmentation","created":"2023-09-07","cited_by_count":197},{"id":"2111.13539","title":"GeoNeRF: Generalizing NeRF with Geometry Priors","created":"2021-11-26","cited_by_count":196},{"id":"2107.13421","title":"Neural Rays for Occlusion-aware Image-based Rendering","created":"2021-07-28","cited_by_count":192},{"id":"2406.02058","title":"OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding","created":"2024-06-04","cited_by_count":145},{"id":"2211.12254","title":"SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fields","created":"2022-11-22","cited_by_count":144},{"id":"2305.14093","title":"Weakly Supervised 3D Open-vocabulary Segmentation","created":"2023-05-23","cited_by_count":135},{"id":"2207.10662","title":"Generalizable Patch-Based Neural Rendering","created":"2022-07-21","cited_by_count":122},{"id":"2111.13260","title":"NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes","created":"2021-11-25","cited_by_count":119},{"id":"1906.11109","title":"Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth","created":"2019-06-26","cited_by_count":89},{"id":"2504.16072","title":"Describe Anything: Detailed Localized Image and Video Captioning","created":"2025-04-22","cited_by_count":84},{"id":"2311.11666","title":"OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning","created":"2023-11-20","cited_by_count":75},{"id":"2212.11966","title":"Removing Objects From Neural Radiance Fields","created":"2022-12-22","cited_by_count":66},{"id":"2312.04560","title":"NeRFiller: Completing Scenes via Generative 3D Inpainting","created":"2023-12-07","cited_by_count":62},{"id":"2404.11613","title":"InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior","created":"2024-04-17","cited_by_count":56},{"id":"2409.15310","title":"Visual Prompting in Multimodal Large Language Models: A Survey","created":"2024-09-05","cited_by_count":54},{"id":"2405.17596","title":"GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane","created":"2024-05-27","cited_by_count":53},{"id":"2502.16652","title":"Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration","created":"2025-02-23","cited_by_count":51},{"id":"2404.07977","title":"Gaga: Group Any Gaussians via 3D-aware Memory Bank","created":"2024-04-11","cited_by_count":41},{"id":"2304.09677","title":"Reference-guided Controllable Inpainting of Neural Radiance Fields","created":"2023-04-19","cited_by_count":40},{"id":"2404.13679","title":"GScream: Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removal","created":"2024-04-21","cited_by_count":39},{"id":"2410.14462","title":"LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes","created":"2024-10-18","cited_by_count":37},{"id":"2412.04459","title":"Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering","created":"2024-12-05","cited_by_count":35},{"id":"2305.10503","title":"OR-NeRF: Object Removing from 3D Scenes Guided by Multiview Segmentation with Neural Radiance Fields","created":"2023-05-17","cited_by_count":34},{"id":"2406.01916","title":"FastLGS: Speeding up Language Embedded Gaussians with Feature Grid Mapping","created":"2024-06-04","cited_by_count":34},{"id":"2507.15454","title":"ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting","created":"2025-07-21","cited_by_count":25},{"id":"2405.02859","title":"MVIP-NeRF: Multi-view 3D Inpainting on NeRF Scenes via Diffusion Prior","created":"2024-05-05","cited_by_count":24},{"id":"2502.11801","title":"3D Gaussian Inpainting with Depth-Guided Cross-View Consistency","created":"2025-02-17","cited_by_count":24},{"id":"2409.17958","title":"The Hard Positive Truth about Vision-Language Compositionality","created":"2024-09-26","cited_by_count":22},{"id":"2502.02548","title":"Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation","created":"2025-02-04","cited_by_count":22},{"id":"2404.10765","title":"RefFusion: Reference Adapted Diffusion Models for 3D Scene Inpainting","created":"2024-04-16","cited_by_count":21},{"id":"2502.05176","title":"AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360{\\deg} Unbounded Scene Inpainting","created":"2025-02-07","cited_by_count":21},{"id":"2404.09995","title":"Taming Latent Diffusion Model for Neural Radiance Field Inpainting","created":"2024-04-15","cited_by_count":20},{"id":"2506.07697","title":"OpenSplat3D: Open-Vocabulary 3D Instance Segmentation using Gaussian Splatting","created":"2025-06-09","cited_by_count":20},{"id":"2508.08252","title":"ReferSplat: Referring Segmentation in 3D Gaussian Splatting","created":"2025-08-11","cited_by_count":20},{"id":"2509.18090","title":"GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction","created":"2025-09-22","cited_by_count":17},{"id":"2305.15094","title":"InNeRF360: Text-Guided 3D-Consistent Object Inpainting on 360-degree Neural Radiance Fields","created":"2023-05-24","cited_by_count":16},{"id":"2403.03608","title":"GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding","created":"2024-03-06","cited_by_count":15},{"id":"2403.06403","title":"PointSeg: A Training-Free Paradigm for 3D Scene Segmentation via Foundation Models","created":"2024-03-11","cited_by_count":9},{"id":"2510.18253","title":"OpenInsGaussian: Open-vocabulary Instance Gaussian Segmentation with Context-aware Cross-view Fusion","created":"2025-10-21","cited_by_count":6},{"id":"2509.15871","title":"Zero-Shot Visual Grounding in 3D Gaussians via View Retrieval","created":"2025-09-19","cited_by_count":5}],"next_cursor":null}