{"total":106,"rows":[{"id":"2112.12130","title":"NICE-SLAM: Neural Implicit Scalable Encoding for SLAM","created":"2021-12-22","cited_by_count":589,"area":null},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548,"area":null},{"id":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319,"area":null},{"id":"2303.09551","title":"SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving","created":"2023-03-16","cited_by_count":316,"area":null},{"id":"2306.00989","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","created":"2023-06-01","cited_by_count":290,"area":null},{"id":"2207.14024","title":"Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer","created":"2022-07-28","cited_by_count":212,"area":null},{"id":"2304.04278","title":"Point-SLAM: Dense Neural Point Cloud-based SLAM","created":"2023-04-09","cited_by_count":160,"area":null},{"id":"2211.11704","title":"ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields","created":"2022-11-21","cited_by_count":158,"area":null},{"id":"2312.10070","title":"Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting","created":"2023-12-06","cited_by_count":154,"area":null},{"id":"2204.08721","title":"Multimodal Token Fusion for Vision Transformers","created":"2022-04-19","cited_by_count":136,"area":null},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117,"area":null},{"id":"2410.12781","title":"Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats","created":"2024-10-16","cited_by_count":114,"area":null},{"id":"2203.11283","title":"NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction","created":"2022-03-21","cited_by_count":100,"area":null},{"id":"2208.14743","title":"SimpleRecon: 3D Reconstruction Without 3D Convolutions","created":"2022-08-31","cited_by_count":83,"area":null},{"id":"2205.12955","title":"Neural 3D Reconstruction in the Wild","created":"2022-05-25","cited_by_count":79,"area":null},{"id":"2510.10726","title":"WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting","created":"2025-10-12","cited_by_count":67,"area":null},{"id":"2405.16544","title":"Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians","created":"2024-05-26","cited_by_count":66,"area":null},{"id":"2312.17118","title":"Fully Sparse 3D Occupancy Prediction","created":"2023-12-28","cited_by_count":64,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2312.09866","title":"PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment","created":"2023-12-15","cited_by_count":63,"area":null},{"id":"2206.14735","title":"GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction","created":"2022-06-29","cited_by_count":61,"area":null},{"id":"2403.01807","title":"ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models","created":"2024-03-04","cited_by_count":57,"area":null},{"id":"2203.03609","title":"Human-Aware Object Placement for Visual Environment Reconstruction","created":"2022-03-07","cited_by_count":56,"area":null},{"id":"2204.07346","title":"MVSTER: Epipolar Transformer for Efficient Multi-View Stereo","created":"2022-04-15","cited_by_count":50,"area":null},{"id":"2402.09944","title":"Loopy-SLAM: Dense Neural SLAM with Loop Closures","created":"2024-02-14","cited_by_count":48,"area":null},{"id":"2204.07548","title":"Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation","created":"2022-04-15","cited_by_count":47,"area":null},{"id":"2108.08623","title":"VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction","created":"2021-08-19","cited_by_count":44,"area":null},{"id":"2112.00236","title":"VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and Fusion","created":"2021-12-01","cited_by_count":38,"area":null},{"id":"2306.05407","title":"SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding","created":"2023-06-08","cited_by_count":38,"area":null},{"id":"2403.19549","title":"GlORIE-SLAM: Globally Optimized RGB-only Implicit Encoding Point Cloud SLAM","created":"2024-03-28","cited_by_count":36,"area":null},{"id":"2301.06782","title":"A Large-Scale Outdoor Multi-modal Dataset and Benchmark for Novel View Synthesis and Implicit Scene Reconstruction","created":"2023-01-17","cited_by_count":32,"area":null},{"id":"2112.03243","title":"Input-level Inductive Biases for 3D Reconstruction","created":"2021-12-06","cited_by_count":31,"area":null},{"id":"2304.08971","title":"SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenes","created":"2023-04-18","cited_by_count":30,"area":null},{"id":"2403.20034","title":"NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising","created":"2024-03-29","cited_by_count":30,"area":null},{"id":"2210.05616","title":"Neural Shape Deformation Priors","created":"2022-10-11","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":"2208.04307","title":"PlaneFormers: From Sparse View Planes to 3D Reconstruction","created":"2022-08-08","cited_by_count":26,"area":null},{"id":"2503.22430","title":"MVSAnywhere: Zero-Shot Multi-View Stereo","created":"2025-03-28","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":"2306.00519","title":"DiffInDScene: Diffusion-based High-Quality 3D Indoor Scene Generation","created":"2023-06-01","cited_by_count":23,"area":null},{"id":"2510.27234","title":"MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts","created":"2025-10-31","cited_by_count":21,"area":"moe"},{"id":"2306.00965","title":"BUOL: A Bottom-Up Framework with Occupancy-aware Lifting for Panoptic 3D Scene Reconstruction From A Single Image","created":"2023-06-01","cited_by_count":20,"area":null},{"id":"2303.13018","title":"MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer","created":"2023-03-23","cited_by_count":18,"area":null},{"id":"2408.15235","title":"Learning-based Multi-View Stereo: A Survey","created":"2024-08-27","cited_by_count":18,"area":null},{"id":"2209.15153","title":"MonoNeuralFusion: Online Monocular Neural 3D Reconstruction with Geometric Priors","created":"2022-09-30","cited_by_count":17,"area":null},{"id":"2304.01480","title":"FineRecon: Depth-aware Feed-forward Network for Detailed 3D Reconstruction","created":"2023-04-04","cited_by_count":17,"area":null},{"id":"2308.15536","title":"DebSDF: Delving into the Details and Bias of Neural Indoor Scene Reconstruction","created":"2023-08-29","cited_by_count":17,"area":null},{"id":"2304.14633","title":"CVRecon: Rethinking 3D Geometric Feature Learning For Neural Reconstruction","created":"2023-04-28","cited_by_count":16,"area":null},{"id":"2512.02541","title":"AVGGT: Rethinking Global Attention for Accelerating VGGT","created":"2025-12-02","cited_by_count":16,"area":null},{"id":"2406.19675","title":"Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Survey","created":"2024-06-28","cited_by_count":15,"area":null},{"id":"2404.04869","title":"Prompting Multi-Modal Tokens to Enhance End-to-End Autonomous Driving Imitation Learning with LLMs","created":"2024-04-07","cited_by_count":13,"area":"driving"},{"id":"2406.08960","title":"AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings","created":"2024-06-13","cited_by_count":13,"area":null},{"id":"2408.09104","title":"HybridOcc: NeRF Enhanced Transformer-based Multi-Camera 3D Occupancy Prediction","created":"2024-08-17","cited_by_count":13,"area":null},{"id":"2412.06322","title":"LLaVA-SpaceSGG: Visual Instruct Tuning for Open-vocabulary Scene Graph Generation with Enhanced Spatial Relations","created":"2024-12-09","cited_by_count":13,"area":null},{"id":"2504.10857","title":"ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping","created":"2025-04-15","cited_by_count":13,"area":null},{"id":"2310.11598","title":"Learning Neural Implicit through Volume Rendering with Attentive Depth Fusion Priors","created":"2023-10-17","cited_by_count":11,"area":null},{"id":"2312.05889","title":"SuperPrimitive: Scene Reconstruction at a Primitive Level","created":"2023-12-10","cited_by_count":11,"area":null},{"id":"2505.05591","title":"QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2211.06009","title":"What's the Situation with Intelligent Mesh Generation: A Survey and Perspectives","created":"2022-11-11","cited_by_count":9,"area":null},{"id":"2303.13561","title":"MoGDE: Boosting Mobile Monocular 3D Object Detection with Ground Depth Estimation","created":"2023-03-23","cited_by_count":9,"area":null},{"id":"2403.14628","title":"Zero-Shot Multi-Object Scene Completion","created":"2024-03-21","cited_by_count":9,"area":null},{"id":"2406.18387","title":"DoubleTake: Geometry Guided Depth Estimation","created":"2024-06-26","cited_by_count":9,"area":null},{"id":"2202.01829","title":"HRBF-Fusion: Accurate 3D reconstruction from RGB-D data using on-the-fly implicits","created":"2022-02-03","cited_by_count":8,"area":null},{"id":"2301.13510","title":"3D Former: Monocular Scene Reconstruction with 3D SDF Transformers","created":"2023-01-31","cited_by_count":8,"area":null},{"id":"2304.10687","title":"VisFusion: Visibility-aware Online 3D Scene Reconstruction from Videos","created":"2023-04-21","cited_by_count":8,"area":null},{"id":"2506.02741","title":"VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians","created":"2025-06-03","cited_by_count":8,"area":null},{"id":"2510.04236","title":"Scaling Sequence-to-Sequence Generative Neural Rendering","created":"2025-10-05","cited_by_count":8,"area":null},{"id":"2403.08748","title":"Real-time 3D semantic occupancy prediction for autonomous vehicles using memory-efficient sparse convolution","created":"2024-03-13","cited_by_count":7,"area":null},{"id":"2403.15161","title":"FastCAD: Real-Time CAD Retrieval and Alignment from Scans and Videos","created":"2024-03-22","cited_by_count":7,"area":null},{"id":"2204.03353","title":"Learning Online Multi-Sensor Depth Fusion","created":"2022-04-07","cited_by_count":6,"area":null},{"id":"2305.14918","title":"Incremental Dense Reconstruction from Monocular Video with Guided Sparse Feature Volume Fusion","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2312.11128","title":"Unleashing the Power of CNN and Transformer for Balanced RGB-Event Video Recognition","created":"2023-12-18","cited_by_count":5,"area":null},{"id":"2405.00340","title":"NC-SDF: Enhancing Indoor Scene Reconstruction Using Neural SDFs with View-Dependent Normal Compensation","created":"2024-05-01","cited_by_count":5,"area":null},{"id":"2506.05285","title":"RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion","created":"2025-06-05","cited_by_count":5,"area":null},{"id":"2605.23888","title":"GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction","created":"2026-05-22","cited_by_count":5,"area":null},{"id":"2111.11992","title":"Sparse Fusion for Multimodal Transformers","created":"2021-11-23","cited_by_count":4,"area":null},{"id":"2111.12905","title":"CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-scale Indoor Scene","created":"2021-11-25","cited_by_count":4,"area":null},{"id":"2212.06524","title":"SST: Real-time End-to-end Monocular 3D Reconstruction via Sparse Spatial-Temporal Guidance","created":"2022-12-13","cited_by_count":4,"area":null},{"id":"2306.08648","title":"SimpleMapping: Real-Time Visual-Inertial Dense Mapping with Deep Multi-View Stereo","created":"2023-06-14","cited_by_count":4,"area":null},{"id":"2401.14401","title":"Range-Agnostic Multi-View Depth Estimation With Keyframe Selection","created":"2024-01-25","cited_by_count":4,"area":null},{"id":"2407.12739","title":"GroundUp: Rapid Sketch-Based 3D City Massing","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2408.15524","title":"Ray-Distance Volume Rendering for Neural Scene Reconstruction","created":"2024-08-28","cited_by_count":4,"area":null},{"id":"2604.08532","title":"Self-Improving 4D Perception via Self-Distillation","created":"2026-04-09","cited_by_count":4,"area":"distill"},{"id":"2202.09450","title":"Modern Augmented Reality: Applications, Trends, and Future Directions","created":"2022-02-18","cited_by_count":3,"area":null},{"id":"2304.00054","title":"LivePose: Online 3D Reconstruction from Monocular Video with Dynamic Camera Poses","created":"2023-03-31","cited_by_count":3,"area":null},{"id":"2405.07573","title":"MaskFuser: Masked Fusion of Joint Multi-Modal Tokenization for End-to-End Autonomous Driving","created":"2024-05-13","cited_by_count":3,"area":"driving"},{"id":"2405.19819","title":"Gated Fields: Learning Scene Reconstruction from Gated Videos","created":"2024-05-30","cited_by_count":3,"area":null},{"id":"2503.04059","title":"H3O: Hyper-Efficient 3D Occupancy Prediction with Heterogeneous Supervision","created":"2025-03-06","cited_by_count":3,"area":null},{"id":"2605.30060","title":"Towards Consistent Video Geometry Estimation","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2201.08633","title":"Multi-view Monocular Depth and Uncertainty Prediction with Deep SfM in Dynamic Environments","created":"2022-01-21","cited_by_count":2,"area":null},{"id":"2303.00236","title":"P$^2$SDF for Neural Indoor Scene Reconstruction","created":"2023-03-01","cited_by_count":2,"area":null},{"id":"2409.08277","title":"Depth on Demand: Streaming Dense Depth from a Low Frame Rate Active Sensor","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2503.12572","title":"Deblur Gaussian Splatting SLAM","created":"2025-03-16","cited_by_count":2,"area":null},{"id":"2303.09248","title":"Cross-Dimensional Refined Learning for Real-Time 3D Visual Perception from Monocular Video","created":"2023-03-16","cited_by_count":1,"area":null},{"id":"2603.21055","title":"SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAM","created":"2026-03-22","cited_by_count":1,"area":null},{"id":"2607.03789","title":"G$^2$TAM: Geometry Grounded Track Anything Model","created":"2026-07-04","cited_by_count":1,"area":null},{"id":"2608.03851","title":"LiteMVS: Efficient Multi-View Stereo with Foundation Distillation and Expert Aggregation","created":"2026-08-04","cited_by_count":1,"area":"moe"},{"id":"2208.14738","title":"Scatter Points in Space: 3D Detection from Multi-view Monocular Images","created":"2022-08-31","cited_by_count":0,"area":null},{"id":"2212.11363","title":"Lightweight Monocular Depth Estimation","created":"2022-12-21","cited_by_count":0,"area":null},{"id":"2310.05406","title":"GradientSurf: Gradient-Domain Neural Surface Reconstruction from RGB Video","created":"2023-10-09","cited_by_count":0,"area":null}],"next_cursor":"100"}