{"list":"other","total":53,"rows":[{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"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":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"1904.09664","title":"Deep Hough Voting for 3D Object Detection in Point Clouds","created":"2019-04-21","cited_by_count":648},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"2211.06220","title":"OneFormer: One Transformer to Rule Universal Image Segmentation","created":"2022-11-10","cited_by_count":328},{"id":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319},{"id":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314},{"id":"2408.16061","title":"3D Reconstruction with Spatial Memory","created":"2024-08-28","cited_by_count":277},{"id":"2412.12392","title":"MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors","created":"2024-12-16","cited_by_count":205},{"id":"2409.19152","title":"MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion","created":"2024-09-27","cited_by_count":162},{"id":"2309.05251","title":"Multi3DRefer: Grounding Text Description to Multiple 3D Objects","created":"2023-09-11","cited_by_count":146},{"id":"2103.01128","title":"InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring","created":"2021-03-01","cited_by_count":141},{"id":"2503.01661","title":"MUSt3R: Multi-view Network for Stereo 3D Reconstruction","created":"2025-03-03","cited_by_count":141},{"id":"2204.02174","title":"Multi-View Transformer for 3D Visual Grounding","created":"2022-04-05","cited_by_count":140},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115},{"id":"2507.16443","title":"VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences","created":"2025-07-22","cited_by_count":115},{"id":"2204.06272","title":"3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection","created":"2022-04-13","cited_by_count":110},{"id":"2509.02560","title":"FastVGGT: Training-Free Acceleration of Visual Geometry Transformer","created":"2025-09-02","cited_by_count":98},{"id":"2108.02388","title":"TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding","created":"2021-08-05","cited_by_count":86},{"id":"2103.16381","title":"Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud","created":"2021-03-30","cited_by_count":81},{"id":"2303.16894","title":"ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance","created":"2023-03-29","cited_by_count":70},{"id":"2501.01163","title":"3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer","created":"2025-01-02","cited_by_count":68},{"id":"2111.09571","title":"Person Re-identification Method Based on Color Attack and Joint Defence","created":"2021-11-18","cited_by_count":56},{"id":"2412.19806","title":"Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing","created":"2024-10-08","cited_by_count":49},{"id":"2501.14914","title":"Light3R-SfM: Towards Feed-forward Structure-from-Motion","created":"2025-01-24","cited_by_count":47},{"id":"2308.16632","title":"3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation","created":"2023-08-31","cited_by_count":36},{"id":"2407.13761","title":"SegPoint: Segment Any Point Cloud via Large Language Model","created":"2024-07-18","cited_by_count":35},{"id":"2103.07894","title":"Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images","created":"2021-03-14","cited_by_count":33},{"id":"2501.14607","title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","created":"2025-01-24","cited_by_count":30},{"id":"2405.17427","title":"Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model","created":"2024-05-27","cited_by_count":28},{"id":"2504.20040","title":"MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion","created":"2025-04-28","cited_by_count":26},{"id":"2407.18244","title":"RefMask3D: Language-Guided Transformer for 3D Referring Segmentation","created":"2024-07-25","cited_by_count":25},{"id":"2108.02417","title":"Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval","created":"2021-08-05","cited_by_count":23},{"id":"2509.07120","title":"Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers","created":"2025-09-08","cited_by_count":23},{"id":"2407.20664","title":"3D-GRES: Generalized 3D Referring Expression Segmentation","created":"2024-07-30","cited_by_count":18},{"id":"2511.07222","title":"Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images","created":"2025-11-10","cited_by_count":17},{"id":"2503.18135","title":"MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation","created":"2025-03-23","cited_by_count":16},{"id":"2507.02705","title":"SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment","created":"2025-07-03","cited_by_count":16},{"id":"2302.11683","title":"MVTrans: Multi-View Perception of Transparent Objects","created":"2023-02-22","cited_by_count":14},{"id":"2412.02402","title":"RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation","created":"2024-12-03","cited_by_count":11},{"id":"2308.11887","title":"A Unified Framework for 3D Point Cloud Visual Grounding","created":"2023-08-23","cited_by_count":6},{"id":"2410.13294","title":"LESS: Label-Efficient and Single-Stage Referring 3D Segmentation","created":"2024-10-17","cited_by_count":5},{"id":"2509.23541","title":"OVSeg3R: Learn Open-vocabulary Instance Segmentation from 2D via 3D Reconstruction","created":"2025-09-28","cited_by_count":4},{"id":"2302.09027","title":"CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension","created":"2023-02-17","cited_by_count":3},{"id":"2504.12599","title":"3DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentation","created":"2025-04-17","cited_by_count":2},{"id":"2509.07825","title":"Point Linguist Model: Segment Any Object via Bridged Large 3D-Language Model","created":"2025-09-09","cited_by_count":2}],"next_cursor":null}