{"list":"other","total":104,"rows":[{"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":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2501.13928","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","created":"2025-01-23","cited_by_count":367},{"id":"2407.04620","title":"Learning to (Learn at Test Time): RNNs with Expressive Hidden States","created":"2024-07-05","cited_by_count":355},{"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":"2104.04532","title":"Neural RGB-D Surface Reconstruction","created":"2021-04-09","cited_by_count":313},{"id":"1905.02082","title":"ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals","created":"2019-05-06","cited_by_count":181},{"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":"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},{"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":"2210.10716","title":"CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion","created":"2022-10-19","cited_by_count":160},{"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":"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":"2105.11115","title":"Self-Attention Networks Can Process Bounded Hierarchical Languages","created":"2021-05-24","cited_by_count":105},{"id":"2503.24391","title":"Easi3R: Estimating Disentangled Motion from DUSt3R Without Training","created":"2025-03-31","cited_by_count":91},{"id":"2508.10893","title":"STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer","created":"2025-08-14","cited_by_count":82},{"id":"2412.03079","title":"Align3R: Aligned Monocular Depth Estimation for Dynamic Videos","created":"2024-12-04","cited_by_count":79},{"id":"2503.17316","title":"Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors","created":"2025-03-21","cited_by_count":72},{"id":"2504.07961","title":"Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction","created":"2025-04-10","cited_by_count":67},{"id":"2502.17237","title":"MegaLoc: One Retrieval to Place Them All","created":"2025-02-24","cited_by_count":60},{"id":"2601.02281","title":"InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams","created":"2026-01-05","cited_by_count":56},{"id":"2507.16290","title":"Dens3R: A Foundation Model for 3D Geometry Prediction","created":"2025-07-22","cited_by_count":46},{"id":"2507.18255","title":"LONG3R: Long Sequence Streaming 3D Reconstruction","created":"2025-07-24","cited_by_count":45},{"id":"2503.16318","title":"Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction","created":"2025-03-20","cited_by_count":44},{"id":"2603.03269","title":"LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory","created":"2026-03-03","cited_by_count":39},{"id":"2510.06219","title":"Human3R: Everyone Everywhere All at Once","created":"2025-10-07","cited_by_count":37},{"id":"2604.14141","title":"LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction","created":"2026-04-15","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":"2512.10935","title":"Any4D: Unified Feed-Forward Metric 4D Reconstruction","created":"2025-12-11","cited_by_count":35},{"id":"2604.08542","title":"Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction","created":"2026-04-09","cited_by_count":31},{"id":"2510.22706","title":"IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction","created":"2025-10-26","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":"2412.19584","title":"DAS3R: Dynamics-Aware Gaussian Splatting for Static Scene Reconstruction","created":"2024-12-27","cited_by_count":26},{"id":"2603.04385","title":"ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training","created":"2026-03-04","cited_by_count":26},{"id":"2504.05692","title":"POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction","created":"2025-04-08","cited_by_count":25},{"id":"2509.07120","title":"Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers","created":"2025-09-08","cited_by_count":23},{"id":"2602.13172","title":"LongStream: Long-Sequence Streaming Autoregressive Visual Geometry","created":"2026-02-13","cited_by_count":23},{"id":"2511.10560","title":"OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer","created":"2025-11-13","cited_by_count":22},{"id":"2512.04012","title":"Emergent Outlier View Rejection in Visual Geometry Grounded Transformers","created":"2025-12-03","cited_by_count":22},{"id":"2510.27234","title":"MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts","created":"2025-10-31","cited_by_count":21},{"id":"2512.16919","title":"DVGT: Driving Visual Geometry Transformer","created":"2025-12-18","cited_by_count":21},{"id":"2506.13750","title":"Test3R: Learning to Reconstruct 3D at Test Time","created":"2025-06-16","cited_by_count":20},{"id":"2511.20343","title":"AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend","created":"2025-11-25","cited_by_count":20},{"id":"2602.23361","title":"VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale","created":"2026-02-26","cited_by_count":18},{"id":"2509.21302","title":"Quantized Visual Geometry Grounded Transformer","created":"2025-09-25","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":"2512.04939","title":"LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging","created":"2025-12-04","cited_by_count":17},{"id":"2411.12892","title":"Selective Attention: Enhancing Transformer through Principled Context Control","created":"2024-11-19","cited_by_count":16},{"id":"2512.02541","title":"AVGGT: Rethinking Global Attention for Accelerating VGGT","created":"2025-12-02","cited_by_count":16},{"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":"2508.11379","title":"G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration","created":"2025-08-15","cited_by_count":12},{"id":"2602.20160","title":"tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction","created":"2026-02-23","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":"2511.18416","title":"4D-VGGT: A General Foundation Model with SpatioTemporal Awareness for Dynamic Scene Geometry Estimation","created":"2025-11-23","cited_by_count":10},{"id":"2603.08055","title":"Speed3R: Sparse Feed-forward 3D Reconstruction Models","created":"2026-03-09","cited_by_count":10},{"id":"2311.00684","title":"Attention Alignment and Flexible Positional Embeddings Improve Transformer Length Extrapolation","created":"2023-11-01","cited_by_count":9},{"id":"2511.21317","title":"HTTM: Head-wise Temporal Token Merging for Faster VGGT","created":"2025-11-26","cited_by_count":9},{"id":"2603.05078","title":"MoRe: Motion-aware Feed-forward 4D Reconstruction Transformer","created":"2026-03-05","cited_by_count":9},{"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":"2504.13167","title":"ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos","created":"2025-04-17","cited_by_count":8},{"id":"2509.25191","title":"VGGT-X: When VGGT Meets Dense Novel View Synthesis","created":"2025-09-29","cited_by_count":8},{"id":"2601.06874","title":"MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation","created":"2026-01-11","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":"2602.14021","title":"Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow","created":"2026-02-15","cited_by_count":8},{"id":"2603.15330","title":"MeMix: Writing Less, Remembering More for Streaming 3D Reconstruction","created":"2026-03-16","cited_by_count":8},{"id":"2512.03939","title":"MUT3R: Motion-aware Updating Transformer for Dynamic 3D Reconstruction","created":"2025-12-03","cited_by_count":7},{"id":"1702.02175","title":"Keyframe-Based Visual-Inertial Online SLAM with Relocalization","created":"2017-02-07","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":"2512.21691","title":"Analyzing the Mechanism of Attention Collapse in VGGT from a Dynamics Perspective","created":"2025-12-25","cited_by_count":6},{"id":"2603.07552","title":"ReconDrive: Fast Feed-Forward 4D Gaussian Splatting for Autonomous Driving Scene Reconstruction","created":"2026-03-08","cited_by_count":6},{"id":"2603.08254","title":"DynamicVGGT: Learning Dynamic Point Maps for 4D Scene Reconstruction in Autonomous Driving","created":"2026-03-09","cited_by_count":6},{"id":"2603.18943","title":"VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation","created":"2026-03-19","cited_by_count":6},{"id":"2603.25336","title":"HeSS: Head Sensitivity Score for Sparsity Redistribution in VGGT","created":"2026-03-26","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":"2512.05060","title":"4DLangVGGT: 4D Language-Visual Geometry Grounded Transformer","created":"2025-12-04","cited_by_count":5},{"id":"2512.21883","title":"Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer","created":"2025-12-26","cited_by_count":5},{"id":"2604.15237","title":"StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression","created":"2026-04-16","cited_by_count":5},{"id":"2511.18290","title":"SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes","created":"2025-11-23","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":"2602.04439","title":"TrajVG: 3D Trajectory-Coupled Visual Geometry Learning","created":"2026-02-04","cited_by_count":4},{"id":"2603.12265","title":"OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams","created":"2026-03-12","cited_by_count":4},{"id":"2512.13122","title":"DePT3R: Joint Dense Point Tracking and 3D Reconstruction of Dynamic Scenes in a Single Forward Pass","created":"2025-12-15","cited_by_count":3},{"id":"2601.16020","title":"Keyframe-Based Feed-Forward Visual Odometry","created":"2026-01-22","cited_by_count":3},{"id":"2602.00865","title":"Distill3R: A Pipeline for Democratizing 3D Foundation Models on Commodity Hardware","created":"2026-01-31","cited_by_count":3},{"id":"2603.02351","title":"MERG3R: A Divide-and-Conquer Approach to Large-Scale Neural Visual Geometry","created":"2026-03-02","cited_by_count":3},{"id":"2603.18493","title":"FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction","created":"2026-03-19","cited_by_count":3},{"id":"2603.22893","title":"SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenes","created":"2026-03-24","cited_by_count":3},{"id":"2602.01741","title":"Tail-Aware Post-Training Quantization for 3D Geometry Models","created":"2026-02-02","cited_by_count":2},{"id":"2602.23224","title":"UniScale: Unified Scale-Aware 3D Reconstruction for Multi-View Understanding via Prior Injection for Robotic Perception","created":"2026-02-26","cited_by_count":2},{"id":"2603.01194","title":"RnG: A Unified Transformer for Complete 3D Modeling from Partial Observations","created":"2026-03-01","cited_by_count":2},{"id":"2604.02107","title":"HyVGGT-VO: Tightly Coupled Hybrid Dense Visual Odometry with Feed-Forward Models","created":"2026-04-02","cited_by_count":2},{"id":"2604.09366","title":"Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors","created":"2026-04-10","cited_by_count":2},{"id":"2511.16282","title":"Building temporally coherent 3D maps with VGGT for memory-efficient Semantic SLAM","created":"2025-11-20","cited_by_count":1}],"next_cursor":"100"}