{"list":"other","total":94,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"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":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"1610.06475","title":"ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras","created":"2016-10-20","cited_by_count":806},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"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":"2312.12337","title":"pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction","created":"2023-12-19","cited_by_count":684},{"id":"2403.14627","title":"MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images","created":"2024-03-21","cited_by_count":566},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"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":"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":"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":"2410.24207","title":"No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images","created":"2024-10-31","cited_by_count":248},{"id":"2104.00681","title":"NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video","created":"2021-04-01","cited_by_count":241},{"id":"2312.04563","title":"Visual Geometry Grounded Deep Structure From Motion","created":"2023-12-07","cited_by_count":227},{"id":"2407.20219","title":"Global Structure-from-Motion Revisited","created":"2024-07-29","cited_by_count":218},{"id":"2412.12392","title":"MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors","created":"2024-12-16","cited_by_count":205},{"id":"2301.02239","title":"Robust Dynamic Radiance Fields","created":"2023-01-05","cited_by_count":194},{"id":"2408.13912","title":"Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs","created":"2024-08-25","cited_by_count":178},{"id":"2508.10934","title":"ViPE: Video Pose Engine for 3D Geometric Perception","created":"2025-08-12","cited_by_count":170},{"id":"2409.19152","title":"MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion","created":"2024-09-27","cited_by_count":162},{"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":"2412.06974","title":"MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds","created":"2024-12-09","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":"2505.12549","title":"VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold","created":"2025-05-18","cited_by_count":136},{"id":"2509.26645","title":"TTT3R: 3D Reconstruction as Test-Time Training","created":"2025-09-30","cited_by_count":129},{"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":"2303.13791","title":"Progressively Optimized Local Radiance Fields for Robust View Synthesis","created":"2023-03-24","cited_by_count":103},{"id":"2412.09401","title":"SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos","created":"2024-12-12","cited_by_count":102},{"id":"2509.02560","title":"FastVGGT: Training-Free Acceleration of Visual Geometry Transformer","created":"2025-09-02","cited_by_count":98},{"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":"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},{"id":"2508.10893","title":"STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer","created":"2025-08-14","cited_by_count":82},{"id":"2503.17316","title":"Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors","created":"2025-03-21","cited_by_count":72},{"id":"2212.03220","title":"Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning","created":"2022-12-06","cited_by_count":57},{"id":"2401.01887","title":"LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry","created":"2024-01-03","cited_by_count":56},{"id":"2601.02281","title":"InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams","created":"2026-01-05","cited_by_count":56},{"id":"2512.08924","title":"Efficiently Reconstructing Dynamic Scenes One D4RT at a Time","created":"2025-12-09","cited_by_count":54},{"id":"2403.01439","title":"Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis","created":"2024-03-03","cited_by_count":53},{"id":"2501.14914","title":"Light3R-SfM: Towards Feed-forward Structure-from-Motion","created":"2025-01-24","cited_by_count":47},{"id":"2507.18255","title":"LONG3R: Long Sequence Streaming 3D Reconstruction","created":"2025-07-24","cited_by_count":45},{"id":"2310.03059","title":"Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models","created":"2023-10-04","cited_by_count":42},{"id":"2510.06219","title":"Human3R: Everyone Everywhere All at Once","created":"2025-10-07","cited_by_count":37},{"id":"2509.05296","title":"WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool","created":"2025-09-05","cited_by_count":35},{"id":"2601.19887","title":"VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction","created":"2026-01-27","cited_by_count":28},{"id":"2508.03643","title":"Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images","created":"2025-08-05","cited_by_count":26},{"id":"2508.14041","title":"LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos","created":"2025-08-19","cited_by_count":24},{"id":"2402.02242","title":"Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark","created":"2024-02-03","cited_by_count":23},{"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":"2412.07746","title":"LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models","created":"2024-12-10","cited_by_count":18},{"id":"2602.23361","title":"VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale","created":"2026-02-26","cited_by_count":18},{"id":"2505.23694","title":"DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers","created":"2025-05-29","cited_by_count":17},{"id":"2512.01540","title":"FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention","created":"2025-12-01","cited_by_count":17},{"id":"2509.01584","title":"ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association","created":"2025-09-01","cited_by_count":16},{"id":"2512.02541","title":"AVGGT: Rethinking Global Attention for Accelerating VGGT","created":"2025-12-02","cited_by_count":16},{"id":"2402.13252","title":"Improving Robustness for Joint Optimization of Camera Poses and Decomposed Low-Rank Tensorial Radiance Fields","created":"2024-02-20","cited_by_count":15},{"id":"2504.16023","title":"PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning","created":"2025-04-22","cited_by_count":14},{"id":"2509.17650","title":"Evict3R: Training-Free Token Eviction for Memory-Bounded Streaming Visual Geometry Transformers","created":"2025-09-22","cited_by_count":14},{"id":"2505.04119","title":"GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model","created":"2025-05-07","cited_by_count":13},{"id":"2407.15848","title":"BoostMVSNeRFs: Boosting MVS-based NeRFs to Generalizable View Synthesis in Large-scale Scenes","created":"2024-07-22","cited_by_count":12},{"id":"2508.11379","title":"G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration","created":"2025-08-15","cited_by_count":12},{"id":"2601.22615","title":"TTSA3R: Training-Free Temporal-Spatial Adaptive Persistent State for Streaming 3D Reconstruction","created":"2026-01-30","cited_by_count":11},{"id":"2511.14751","title":"Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers","created":"2025-11-18","cited_by_count":10},{"id":"2504.12356","title":"Regist3R: Incremental Registration with Stereo Foundation Model","created":"2025-04-16","cited_by_count":9},{"id":"2509.16909","title":"SLAM-Former: Putting SLAM into One Transformer","created":"2025-09-21","cited_by_count":9},{"id":"2602.20157","title":"Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learning","created":"2026-02-23","cited_by_count":9},{"id":"2505.02178","title":"Sparfels: Fast Reconstruction from Sparse Unposed Imagery","created":"2025-05-04","cited_by_count":8},{"id":"2602.05508","title":"VGGT-Motion: Motion-Aware Calibration-Free Monocular SLAM for Long-Range Consistency","created":"2026-02-05","cited_by_count":8},{"id":"2509.23737","title":"GRS-SLAM3R: Real-Time Dense SLAM with Gated Recurrent State","created":"2025-09-28","cited_by_count":6},{"id":"2512.13680","title":"LASER: Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction","created":"2025-12-15","cited_by_count":6},{"id":"2512.22581","title":"KV-Tracker: Real-Time Pose Tracking with Transformers","created":"2025-12-27","cited_by_count":5},{"id":"2512.15577","title":"MoonSeg3R: Monocular Online Zero-Shot Segment Anything in 3D with Reconstructive Foundation Priors","created":"2025-12-17","cited_by_count":4},{"id":"2601.05208","title":"MoE3D: A Mixture-of-Experts Module for 3D Reconstruction","created":"2026-01-08","cited_by_count":4},{"id":"2601.08831","title":"3AM: 3egment Anything with Geometric Consistency in Videos","created":"2026-01-13","cited_by_count":4},{"id":"2602.04349","title":"VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image","created":"2026-02-04","cited_by_count":4},{"id":"2601.16020","title":"Keyframe-Based Feed-Forward Visual Odometry","created":"2026-01-22","cited_by_count":3},{"id":"2602.04517","title":"S-MUSt3R: Sliding Multi-view 3D Reconstruction","created":"2026-02-04","cited_by_count":3}],"next_cursor":null}