{"total":69,"rows":[{"id":"2407.20229","title":"Improving 2D Feature Representations by 3D-Aware Fine-Tuning","created":"2024-07-29","cited_by_count":71,"area":null},{"id":"2408.10154","title":"LoopSplat: Loop Closure by Registering 3D Gaussian Splats","created":"2024-08-19","cited_by_count":60,"area":null},{"id":"2503.19199","title":"Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces","created":"2025-03-24","cited_by_count":54,"area":null},{"id":"2502.16652","title":"Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration","created":"2025-02-23","cited_by_count":51,"area":null},{"id":"2412.10231","title":"SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians","created":"2024-12-13","cited_by_count":33,"area":null},{"id":"2409.18431","title":"Search3D: Hierarchical Open-Vocabulary 3D Segmentation","created":"2024-09-27","cited_by_count":31,"area":null},{"id":"2410.07577","title":"3D Vision-Language Gaussian Splatting","created":"2024-10-10","cited_by_count":31,"area":"mllm"},{"id":"2510.12764","title":"AnyUp: Universal Feature Upsampling","created":"2025-10-14","cited_by_count":28,"area":null},{"id":"2503.06271","title":"SplatTalk: 3D VQA with Gaussian Splatting","created":"2025-03-08","cited_by_count":24,"area":null},{"id":"2503.07909","title":"FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction","created":"2025-03-10","cited_by_count":23,"area":null},{"id":"2506.07697","title":"OpenSplat3D: Open-Vocabulary 3D Instance Segmentation using Gaussian Splatting","created":"2025-06-09","cited_by_count":20,"area":null},{"id":"2607.05352","title":"Multiplayer Interactive World Models with Representation Autoencoders","created":"2026-07-06","cited_by_count":19,"area":"wm"},{"id":"2408.16325","title":"P2P-Bridge: Diffusion Bridges for 3D Point Cloud Denoising","created":"2024-08-29","cited_by_count":18,"area":null},{"id":"2411.16310","title":"Functionality understanding and segmentation in 3D scenes","created":"2024-11-25","cited_by_count":17,"area":null},{"id":"2412.13652","title":"RelationField: Relate Anything in Radiance Fields","created":"2024-12-18","cited_by_count":16,"area":"mllm"},{"id":"2404.12440","title":"Spot-Compose: A Framework for Open-Vocabulary Object Retrieval and Drawer Manipulation in Point Clouds","created":"2024-04-18","cited_by_count":15,"area":null},{"id":"2508.03227","title":"Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracing","created":"2025-08-05","cited_by_count":13,"area":null},{"id":"2408.07416","title":"Rethinking Open-Vocabulary Segmentation of Radiance Fields in 3D Space","created":"2024-08-14","cited_by_count":12,"area":null},{"id":"2411.15043","title":"Open-Vocabulary Online Semantic Mapping for SLAM","created":"2024-11-22","cited_by_count":12,"area":null},{"id":"2504.06827","title":"IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments","created":"2025-04-09","cited_by_count":11,"area":null},{"id":"2507.22052","title":"Ov3R: Open-Vocabulary Semantic 3D Reconstruction from RGB Videos","created":"2025-07-29","cited_by_count":10,"area":null},{"id":"2503.07507","title":"PE3R: Perception-Efficient 3D Reconstruction","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2509.05515","title":"Visibility-Aware Language Aggregation for Open-Vocabulary Segmentation in 3D Gaussian Splatting","created":"2025-09-05","cited_by_count":9,"area":null},{"id":"2510.20238","title":"COS3D: Collaborative Open-Vocabulary 3D Segmentation","created":"2025-10-23","cited_by_count":9,"area":null},{"id":"2512.14364","title":"Unified Semantic Transformer for 3D Scene Understanding","created":"2025-12-16","cited_by_count":8,"area":null},{"id":"2410.13924","title":"ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding","created":"2024-10-17","cited_by_count":7,"area":null},{"id":"2405.20141","title":"OpenDAS: Open-Vocabulary Domain Adaptation for 2D and 3D Segmentation","created":"2024-05-30","cited_by_count":6,"area":"mllm"},{"id":"2506.06862","title":"Multimodal Spatial Language Maps for Robot Navigation and Manipulation","created":"2025-06-07","cited_by_count":6,"area":null},{"id":"2603.17605","title":"ReLaGS: Relational Language Gaussian Splatting","created":"2026-03-18","cited_by_count":6,"area":null},{"id":"2510.21441","title":"OpenHype: Hyperbolic Embeddings for Hierarchical Open-Vocabulary Radiance Fields","created":"2025-10-24","cited_by_count":5,"area":null},{"id":"2512.14126","title":"Consistent Instance Field for Dynamic Scene Understanding","created":"2025-12-16","cited_by_count":5,"area":null},{"id":"2411.07848","title":"Zero-shot Object-Centric Instruction Following: Integrating Foundation Models with Traditional Navigation","created":"2024-11-12","cited_by_count":4,"area":null},{"id":"2412.10972","title":"DCSEG: Decoupled 3D Open-Set Segmentation using Gaussian Splatting","created":"2024-12-14","cited_by_count":4,"area":null},{"id":"2505.08124","title":"SLAG: Scalable Language-Augmented Gaussian Splatting","created":"2025-05-12","cited_by_count":4,"area":null},{"id":"2601.08831","title":"3AM: 3egment Anything with Geometric Consistency in Videos","created":"2026-01-13","cited_by_count":4,"area":null},{"id":"2603.26541","title":"OVI-MAP:Open-Vocabulary Instance-Semantic Mapping","created":"2026-03-27","cited_by_count":4,"area":null},{"id":"2503.16776","title":"OpenCity3D: What do Vision-Language Models know about Urban Environments?","created":"2025-03-21","cited_by_count":3,"area":"mllm"},{"id":"2504.06003","title":"econSG: Efficient and Multi-view Consistent Open-Vocabulary 3D Semantic Gaussians","created":"2025-04-08","cited_by_count":3,"area":null},{"id":"2506.21884","title":"UnMix-NeRF: Spectral Unmixing Meets Neural Radiance Fields","created":"2025-06-27","cited_by_count":3,"area":null},{"id":"2606.08980","title":"EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2408.09928","title":"Enforcing View-Consistency in Class-Agnostic 3D Segmentation Fields","created":"2024-08-19","cited_by_count":2,"area":null},{"id":"2412.02449","title":"BYE: Build Your Encoder with One Sequence of Exploration Data for Long-Term Dynamic Scene Understanding","created":"2024-12-03","cited_by_count":2,"area":null},{"id":"2412.05969","title":"Efficient Semantic Splatting for Remote Sensing Multi-view Segmentation","created":"2024-12-08","cited_by_count":2,"area":null},{"id":"2507.14596","title":"DiSCO-3D : Discovering and segmenting Sub-Concepts from Open-vocabulary queries in NeRF","created":"2025-07-19","cited_by_count":2,"area":null},{"id":"2509.24528","title":"CORE-3D: Context-aware Open-vocabulary Retrieval by Embeddings in 3D","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2601.02905","title":"LOST-3DSG: Lightweight Open-Vocabulary 3D Scene Graphs with Semantic Tracking in Dynamic Environments","created":"2026-01-06","cited_by_count":2,"area":null},{"id":"2603.13383","title":"Taming Vision Priors for Data Efficient mmWave Channel Modeling","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2606.05975","title":"T-FunS3D: Task-Driven Hierarchical Open-Vocabulary 3D Functionality Segmentation","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2412.12772","title":"Optimize the Unseen -- Fast NeRF Cleanup with Free Space Prior","created":"2024-12-17","cited_by_count":1,"area":null},{"id":"2505.00378","title":"Cues3D: Unleashing the Power of Sole NeRF for Consistent and Unique Instances in Open-Vocabulary 3D Panoptic Segmentation","created":"2025-05-01","cited_by_count":1,"area":null},{"id":"2511.16454","title":"LLaVA$^3$: Representing 3D Scenes like a Cubist Painter to Boost 3D Scene Understanding of VLMs","created":"2025-11-20","cited_by_count":1,"area":"mllm"},{"id":"2512.01889","title":"KM-ViPE: Online Tightly Coupled Vision-Language-Geometry Fusion for Open-Vocabulary Semantic SLAM","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2603.04254","title":"EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2604.26262","title":"Semantic Foam: Unifying Spatial and Semantic Scene Decomposition","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2605.15753","title":"Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2607.01140","title":"Relation-Centric Open-Vocabulary 3D Gaussian Segmentation","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2608.04560","title":"OutLangSplat: 3D Language Gaussian Splatting for UAV Outdoor Scenes","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2609.38177","title":"Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering","created":"2026-09-29","cited_by_count":1,"area":"mllm"},{"id":"2503.15712","title":"SPNeRF: Open Vocabulary 3D Neural Scene Segmentation with Superpoints","created":"2025-03-19","cited_by_count":0,"area":null},{"id":"2504.14638","title":"NVSMask3D: Hard Visual Prompting with Camera Pose Interpolation for 3D Open Vocabulary Instance Segmentation","created":"2025-04-20","cited_by_count":0,"area":"mllm"},{"id":"2603.23478","title":"UniFunc3D: Unified Active Spatial-Temporal Grounding for 3D Affordance Segmentation","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2603.27970","title":"AffordMatcher: Affordance Learning in 3D Scenes from Visual Signifiers","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.12551","title":"Cross-Attentive Multiview Fusion of Vision-Language Embeddings","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"id":"2604.17155","title":"Instant Colorization of Gaussian Splats","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.08925","title":"ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.11967","title":"H2G: Hierarchy-Aware Hyperbolic Grouping for 3D Scenes","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.20044","title":"OP2GS: Object-Aware 3D Gaussian Splatting with Dual-Opacity Primitives","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2609.11616","title":"LangStreet: Persistent Language Fields for Anchor-Decoded Street Gaussians","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2610.20610","title":"Can Learning to Answer Spatial Questions Improve Novel-View Generation?","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}