{"list":"other","total":89,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"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":"2007.11898","title":"ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM","created":"2020-07-23","cited_by_count":878},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548},{"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},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1911.10127","title":"BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks","created":"2019-11-22","cited_by_count":490},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442},{"id":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"id":"2501.13928","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","created":"2025-01-23","cited_by_count":367},{"id":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319},{"id":"1804.00650","title":"DeepMVS: Learning Multi-view Stereopsis","created":"2018-04-02","cited_by_count":277},{"id":"2408.16061","title":"3D Reconstruction with Spatial Memory","created":"2024-08-28","cited_by_count":277},{"id":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276},{"id":"2501.01005","title":"FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving","created":"2025-01-02","cited_by_count":258},{"id":"2412.12392","title":"MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors","created":"2024-12-16","cited_by_count":205},{"id":"2208.04726","title":"Deep Patch Visual Odometry","created":"2022-08-08","cited_by_count":190},{"id":"2309.16553","title":"MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond","created":"2023-09-28","cited_by_count":185},{"id":"2502.12138","title":"FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views","created":"2025-02-17","cited_by_count":180},{"id":"2303.01943","title":"Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo","created":"2023-03-03","cited_by_count":172},{"id":"2505.20279","title":"VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction","created":"2025-05-26","cited_by_count":166},{"id":"2606.02800","title":"Cosmos 3: Omnimodal World Models for Physical AI","created":"2026-06-01","cited_by_count":165},{"id":"2507.11539","title":"Streaming 4D Visual Geometry Transformer","created":"2025-07-15","cited_by_count":161},{"id":"2311.15937","title":"Optimal Transport Aggregation for Visual Place Recognition","created":"2023-11-27","cited_by_count":152},{"id":"2305.02296","title":"DynamicStereo: Consistent Dynamic Depth from Stereo Videos","created":"2023-05-03","cited_by_count":148},{"id":"2412.06974","title":"MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds","created":"2024-12-09","cited_by_count":141},{"id":"2505.12549","title":"VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold","created":"2025-05-18","cited_by_count":136},{"id":"2510.12276","title":"Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model","created":"2025-10-14","cited_by_count":134},{"id":"2509.26645","title":"TTT3R: 3D Reconstruction as Test-Time Training","created":"2025-09-30","cited_by_count":129},{"id":"2104.03866","title":"SMD-Nets: Stereo Mixture Density Networks","created":"2021-04-08","cited_by_count":120},{"id":"2401.12592","title":"RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos","created":"2024-01-23","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":"2210.05494","title":"Map-free Visual Relocalization: Metric Pose Relative to a Single Image","created":"2022-10-11","cited_by_count":114},{"id":"2412.09401","title":"SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos","created":"2024-12-12","cited_by_count":102},{"id":"2403.13064","title":"SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Model","created":"2024-03-19","cited_by_count":96},{"id":"2507.07982","title":"Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling","created":"2025-07-10","cited_by_count":96},{"id":"2503.24391","title":"Easi3R: Estimating Disentangled Motion from DUSt3R Without Training","created":"2025-03-31","cited_by_count":91},{"id":"2507.02863","title":"Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory","created":"2025-07-03","cited_by_count":87},{"id":"2508.10893","title":"STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer","created":"2025-08-14","cited_by_count":82},{"id":"2408.01654","title":"Deep Patch Visual SLAM","created":"2024-08-03","cited_by_count":71},{"id":"2509.12201","title":"OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling","created":"2025-09-15","cited_by_count":62},{"id":"2601.02281","title":"InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams","created":"2026-01-05","cited_by_count":56},{"id":"2507.18255","title":"LONG3R: Long Sequence Streaming 3D Reconstruction","created":"2025-07-24","cited_by_count":45},{"id":"2511.21688","title":"G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning","created":"2025-11-26","cited_by_count":44},{"id":"1512.08422","title":"Natural Language Inference by Tree-Based Convolution and Heuristic Matching","created":"2015-12-28","cited_by_count":43},{"id":"2603.03269","title":"LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory","created":"2026-03-03","cited_by_count":39},{"id":"2604.14141","title":"LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction","created":"2026-04-15","cited_by_count":37},{"id":"2505.10696","title":"TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigation","created":"2025-05-15","cited_by_count":36},{"id":"2509.05296","title":"WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool","created":"2025-09-05","cited_by_count":35},{"id":"2601.04090","title":"Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction","created":"2026-01-07","cited_by_count":31},{"id":"2411.10546","title":"The Oxford Spires Dataset: Benchmarking Large-Scale LiDAR-Visual Localisation, Reconstruction and Radiance Field Methods","created":"2024-11-15","cited_by_count":28},{"id":"2511.19971","title":"VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction","created":"2025-11-25","cited_by_count":28},{"id":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26},{"id":"2602.13172","title":"LongStream: Long-Sequence Streaming Autoregressive Visual Geometry","created":"2026-02-13","cited_by_count":23},{"id":"2511.20343","title":"AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend","created":"2025-11-25","cited_by_count":20},{"id":"2404.11322","title":"VBR: A Vision Benchmark in Rome","created":"2024-04-17","cited_by_count":16},{"id":"2603.27437","title":"SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoning","created":"2026-03-28","cited_by_count":15},{"id":"2603.12655","title":"VGGT-World: Transforming VGGT into an Autoregressive Geometry World Model","created":"2026-03-13","cited_by_count":13},{"id":"2603.19076","title":"DROID-SLAM in the Wild","created":"2026-03-19","cited_by_count":10},{"id":"2603.20284","title":"STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction","created":"2026-03-18","cited_by_count":9},{"id":"2605.23889","title":"HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction","created":"2026-05-22","cited_by_count":9},{"id":"2604.22482","title":"Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyond","created":"2026-04-24","cited_by_count":7},{"id":"2603.24393","title":"3D-Mix for VLA: A Plug-and-Play Module for Integrating VGGT-based 3D Information into Vision-Language-Action Models","created":"2026-03-25","cited_by_count":6},{"id":"2604.07279","title":"Mem3R: Streaming 3D Reconstruction with Hybrid Memory via Test-Time Training","created":"2026-04-08","cited_by_count":6},{"id":"2510.18714","title":"PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-Forward Planar Splatting","created":"2025-10-21","cited_by_count":5},{"id":"2512.02341","title":"TALO: Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstruction","created":"2025-12-02","cited_by_count":5},{"id":"2605.14984","title":"Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image","created":"2026-05-14","cited_by_count":5},{"id":"2605.23888","title":"GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction","created":"2026-05-22","cited_by_count":5},{"id":"2604.26567","title":"AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision","created":"2026-04-29","cited_by_count":3},{"id":"2605.26519","title":"$R^3$: 3D Reconstruction via Relative Regression","created":"2026-05-26","cited_by_count":2},{"id":"2606.05035","title":"Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping","created":"2026-06-03","cited_by_count":2},{"id":"2606.09967","title":"ABot-Earth 0.5: Generative 3D Earth Model","created":"2026-06-08","cited_by_count":2},{"id":"2608.17988","title":"GS-Voxel: Fitting-Free Structured Latents for Large-Scale 3DGS Generation","created":"2026-08-18","cited_by_count":2},{"id":"2608.03429","title":"SLAMFormer-$\\infty$: Infinite SLAM Transformer for Unbounded Frontend and Backend Processing","created":"2026-08-04","cited_by_count":1}],"next_cursor":null}