{"total":454,"rows":[{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793,"area":"mllm"},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764,"area":null},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692,"area":null},{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611,"area":"lr"},{"id":"2312.16256","title":"DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision","created":"2023-12-26","cited_by_count":537,"area":null},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404,"area":null},{"id":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319,"area":null},{"id":"2406.01584","title":"SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models","created":"2024-06-03","cited_by_count":311,"area":"lr"},{"id":"2408.16061","title":"3D Reconstruction with Spatial Memory","created":"2024-08-28","cited_by_count":277,"area":null},{"id":"2507.02546","title":"MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details","created":"2025-07-03","cited_by_count":261,"area":null},{"id":"2505.23716","title":"AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views","created":"2025-05-29","cited_by_count":243,"area":null},{"id":"2505.23747","title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","created":"2025-05-29","cited_by_count":217,"area":"mllm"},{"id":"2502.12138","title":"FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views","created":"2025-02-17","cited_by_count":180,"area":null},{"id":"2502.20110","title":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","created":"2025-02-27","cited_by_count":173,"area":null},{"id":"2508.10934","title":"ViPE: Video Pose Engine for 3D Geometric Perception","created":"2025-08-12","cited_by_count":170,"area":null},{"id":"2211.10408","title":"CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow","created":"2022-11-18","cited_by_count":166,"area":null},{"id":"2505.20279","title":"VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction","created":"2025-05-26","cited_by_count":166,"area":"mllm"},{"id":"2507.11539","title":"Streaming 4D Visual Geometry Transformer","created":"2025-07-15","cited_by_count":161,"area":null},{"id":"2207.10660","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","created":"2022-07-21","cited_by_count":160,"area":null},{"id":"2503.01661","title":"MUSt3R: Multi-view Network for Stereo 3D Reconstruction","created":"2025-03-03","cited_by_count":141,"area":null},{"id":"2412.07825","title":"3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark","created":"2024-12-10","cited_by_count":139,"area":"lr"},{"id":"2503.22976","title":"From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D","created":"2025-03-29","cited_by_count":138,"area":"mllm"},{"id":"2406.11824","title":"Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation","created":"2024-06-17","cited_by_count":137,"area":null},{"id":"2207.13751","title":"GAUDI: A Neural Architect for Immersive 3D Scene Generation","created":"2022-07-27","cited_by_count":136,"area":null},{"id":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133,"area":null},{"id":"2311.18159","title":"CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization","created":"2023-11-30","cited_by_count":130,"area":null},{"id":"2310.07204","title":"State of the Art on Diffusion Models for Visual Computing","created":"2023-10-11","cited_by_count":127,"area":"diffusion"},{"id":"2404.09465","title":"PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI","created":"2024-04-15","cited_by_count":125,"area":null},{"id":"2304.06906","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","created":"2023-04-14","cited_by_count":113,"area":null},{"id":"2210.05633","title":"Habitat-Matterport 3D Semantics Dataset","created":"2022-10-11","cited_by_count":110,"area":null},{"id":"2503.16429","title":"Sonata: Self-Supervised Learning of Reliable Point Representations","created":"2025-03-20","cited_by_count":110,"area":null},{"id":"2501.01428","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","created":"2025-01-02","cited_by_count":109,"area":"mllm"},{"id":"2404.06609","title":"GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation","created":"2024-04-09","cited_by_count":94,"area":null},{"id":"2510.08531","title":"SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models","created":"2025-10-09","cited_by_count":90,"area":"lr"},{"id":"2511.05491","title":"Visual Spatial Tuning","created":"2025-11-07","cited_by_count":89,"area":null},{"id":"2507.02863","title":"Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory","created":"2025-07-03","cited_by_count":87,"area":null},{"id":"2308.09718","title":"Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training","created":"2023-08-18","cited_by_count":86,"area":null},{"id":"2412.08376","title":"Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization","created":"2024-12-11","cited_by_count":82,"area":null},{"id":"2412.14015","title":"Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation","created":"2024-12-18","cited_by_count":74,"area":null},{"id":"2503.13111","title":"MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs","created":"2025-03-17","cited_by_count":73,"area":"mllm"},{"id":"2308.04758","title":"Bird's-Eye-View Scene Graph for Vision-Language Navigation","created":"2023-08-09","cited_by_count":72,"area":null},{"id":"2503.17316","title":"Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors","created":"2025-03-21","cited_by_count":72,"area":null},{"id":"2404.03650","title":"OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views","created":"2024-04-04","cited_by_count":69,"area":"mllm"},{"id":"2510.10726","title":"WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting","created":"2025-10-12","cited_by_count":67,"area":null},{"id":"2212.11966","title":"Removing Objects From Neural Radiance Fields","created":"2022-12-22","cited_by_count":66,"area":null},{"id":"2504.01017","title":"Scaling Language-Free Visual Representation Learning","created":"2025-04-01","cited_by_count":66,"area":null},{"id":"2506.07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","created":"2025-06-09","cited_by_count":65,"area":null},{"id":"2312.17232","title":"Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels","created":"2023-12-28","cited_by_count":64,"area":null},{"id":"2503.16591","title":"UniK3D: Universal Camera Monocular 3D Estimation","created":"2025-03-20","cited_by_count":62,"area":null},{"id":"2509.12201","title":"OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling","created":"2025-09-15","cited_by_count":62,"area":"wm"},{"id":"2303.14191","title":"Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning","created":"2023-03-24","cited_by_count":56,"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":"2305.11337","title":"RoomDreamer: Text-Driven 3D Indoor Scene Synthesis with Coherent Geometry and Texture","created":"2023-05-18","cited_by_count":53,"area":"diffusion"},{"id":"2406.09406","title":"4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities","created":"2024-06-13","cited_by_count":52,"area":null},{"id":"2503.18052","title":"SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining","created":"2025-03-23","cited_by_count":52,"area":"mllm"},{"id":"2307.14620","title":"NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection","created":"2023-07-27","cited_by_count":51,"area":null},{"id":"2409.02389","title":"Multi-modal Situated Reasoning in 3D Scenes","created":"2024-09-04","cited_by_count":51,"area":"lr"},{"id":"2311.18610","title":"DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB Image","created":"2023-11-30","cited_by_count":48,"area":null},{"id":"2601.00393","title":"NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos","created":"2026-01-01","cited_by_count":46,"area":"wm"},{"id":"2507.18255","title":"LONG3R: Long Sequence Streaming 3D Reconstruction","created":"2025-07-24","cited_by_count":45,"area":null},{"id":"2510.23607","title":"Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations","created":"2025-10-27","cited_by_count":45,"area":null},{"id":"2405.10255","title":"When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models","created":"2024-05-16","cited_by_count":43,"area":"mllm"},{"id":"2406.09401","title":"MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations","created":"2024-06-13","cited_by_count":40,"area":null},{"id":"2502.07685","title":"Matrix3D: Large Photogrammetry Model All-in-One","created":"2025-02-11","cited_by_count":40,"area":null},{"id":"2412.04458","title":"Cubify Anything: Scaling Indoor 3D Object Detection","created":"2024-12-05","cited_by_count":39,"area":null},{"id":"2603.03269","title":"LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory","created":"2026-03-03","cited_by_count":39,"area":null},{"id":"2412.01292","title":"LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences","created":"2024-12-02","cited_by_count":38,"area":"mllm"},{"id":"2502.08636","title":"Spatial457: A Diagnostic Benchmark for 6D Spatial Reasoning of Large Multimodal Models","created":"2025-02-12","cited_by_count":38,"area":"lr"},{"id":"2505.00788","title":"SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models","created":"2025-05-01","cited_by_count":38,"area":"lr"},{"id":"2505.10565","title":"Depth Anything with Any Prior","created":"2025-05-15","cited_by_count":36,"area":null},{"id":"2506.09278","title":"UFM: A Simple Path towards Unified Dense Correspondence with Flow","created":"2025-06-10","cited_by_count":36,"area":null},{"id":"2509.05296","title":"WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool","created":"2025-09-05","cited_by_count":35,"area":null},{"id":"2306.10988","title":"Tame a Wild Camera: In-the-Wild Monocular Camera Calibration","created":"2023-06-19","cited_by_count":34,"area":null},{"id":"2504.07958","title":"Detect Anything 3D in the Wild","created":"2025-04-10","cited_by_count":33,"area":null},{"id":"2505.21327","title":"MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs","created":"2025-05-27","cited_by_count":33,"area":"lr"},{"id":"2509.13317","title":"3D Aware Region Prompted Vision Language Model","created":"2025-09-16","cited_by_count":33,"area":"mllm"},{"id":"2411.04999","title":"DynaMem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulation","created":"2024-11-07","cited_by_count":32,"area":"mllm"},{"id":"2503.14405","title":"DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers","created":"2025-03-18","cited_by_count":32,"area":"distill"},{"id":"2303.14541","title":"UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes","created":"2023-03-25","cited_by_count":31,"area":null},{"id":"2405.03685","title":"Language-Image Models with 3D Understanding","created":"2024-05-06","cited_by_count":31,"area":"mllm"},{"id":"2503.18944","title":"DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation","created":"2025-03-24","cited_by_count":31,"area":null},{"id":"2204.09341","title":"OutCast: Outdoor Single-image Relighting with Cast Shadows","created":"2022-04-20","cited_by_count":30,"area":null},{"id":"2411.19278","title":"OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration","created":"2024-11-28","cited_by_count":30,"area":null},{"id":"2303.17342","title":"PMatch: Paired Masked Image Modeling for Dense Geometric Matching","created":"2023-03-30","cited_by_count":29,"area":null},{"id":"2505.05495","title":"Learning 3D Persistent Embodied World Models","created":"2025-05-05","cited_by_count":29,"area":"wm"},{"id":"2511.04655","title":"Benchmark Designers Should \"Train on the Test Set\" to Expose Exploitable Non-Visual Shortcuts","created":"2025-11-06","cited_by_count":29,"area":"mllm"},{"id":"2512.16561","title":"N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models","created":"2025-12-18","cited_by_count":29,"area":"lr"},{"id":"2303.16570","title":"Point2Vec for Self-Supervised Representation Learning on Point Clouds","created":"2023-03-29","cited_by_count":28,"area":null},{"id":"2410.08208","title":"SPA: 3D Spatial-Awareness Enables Effective Embodied Representation","created":"2024-10-10","cited_by_count":28,"area":null},{"id":"2411.16877","title":"PreF3R: Pose-Free Feed-Forward 3D Gaussian Splatting from Variable-length Image Sequence","created":"2024-11-25","cited_by_count":28,"area":null},{"id":"2506.03642","title":"Spatial Understanding from Videos: Structured Prompts Meet Simulation Data","created":"2025-06-04","cited_by_count":28,"area":null},{"id":"2601.17895","title":"Masked Depth Modeling for Spatial Perception","created":"2026-01-25","cited_by_count":28,"area":null},{"id":"2504.17788","title":"Dynamic Camera Poses and Where to Find Them","created":"2025-04-24","cited_by_count":27,"area":null},{"id":"2507.14501","title":"Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey","created":"2025-07-19","cited_by_count":27,"area":null},{"id":"2311.04391","title":"3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features","created":"2023-11-07","cited_by_count":26,"area":"diffusion"},{"id":"2406.10224","title":"EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models","created":"2024-06-14","cited_by_count":26,"area":null},{"id":"2603.04385","title":"ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training","created":"2026-03-04","cited_by_count":26,"area":null},{"id":"2406.09613","title":"ImageNet3D: Towards General-Purpose Object-Level 3D Understanding","created":"2024-06-13","cited_by_count":25,"area":null},{"id":"2507.07984","title":"OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding","created":"2025-07-10","cited_by_count":24,"area":"mllm"},{"id":"2204.07183","title":"Interactive Object Segmentation in 3D Point Clouds","created":"2022-04-14","cited_by_count":23,"area":null}],"next_cursor":"100"}