{"total":124,"rows":[{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440,"area":null},{"id":"2212.02499","title":"Images Speak in Images: A Generalist Painter for In-Context Visual Learning","created":"2022-12-05","cited_by_count":318,"area":null},{"id":"2204.00987","title":"BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation","created":"2022-04-03","cited_by_count":168,"area":null},{"id":"2203.14211","title":"DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation","created":"2022-03-27","cited_by_count":118,"area":null},{"id":"2203.15132","title":"LocalBins: Improving Depth Estimation by Learning Local Distributions","created":"2022-03-28","cited_by_count":94,"area":null},{"id":"2309.14616","title":"NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space","created":"2023-09-26","cited_by_count":90,"area":null},{"id":"2205.10337","title":"UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes","created":"2022-05-20","cited_by_count":78,"area":null},{"id":"2108.13962","title":"DepthTrack : Unveiling the Power of RGBD Tracking","created":"2021-08-31","cited_by_count":67,"area":null},{"id":"2103.04216","title":"Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction","created":"2021-03-07","cited_by_count":48,"area":null},{"id":"2103.16690","title":"Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completion","created":"2021-03-30","cited_by_count":39,"area":null},{"id":"2110.00087","title":"Seeing Glass: Joint Point Cloud and Depth Completion for Transparent Objects","created":"2021-09-30","cited_by_count":39,"area":null},{"id":"2106.02022","title":"Single Image Depth Prediction with Wavelet Decomposition","created":"2021-06-03","cited_by_count":34,"area":null},{"id":"2209.12358","title":"UDepth: Fast Monocular Depth Estimation for Visually-guided Underwater Robots","created":"2022-09-26","cited_by_count":27,"area":null},{"id":"2103.08573","title":"RoRD: Rotation-Robust Descriptors and Orthographic Views for Local Feature Matching","created":"2021-03-15","cited_by_count":19,"area":null},{"id":"2105.08630","title":"Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report","created":"2021-05-17","cited_by_count":19,"area":null},{"id":"2210.01044","title":"SPARC: Sparse Render-and-Compare for CAD model alignment in a single RGB image","created":"2022-10-03","cited_by_count":19,"area":null},{"id":"2307.11261","title":"SimCol3D -- 3D Reconstruction during Colonoscopy Challenge","created":"2023-07-20","cited_by_count":19,"area":null},{"id":"2105.03211","title":"NeRD: Neural 3D Reflection Symmetry Detector","created":"2021-04-19","cited_by_count":18,"area":null},{"id":"2108.12655","title":"DenseLiDAR: A Real-Time Pseudo Dense Depth Guided Depth Completion Network","created":"2021-08-28","cited_by_count":17,"area":null},{"id":"2204.01268","title":"Improving Monocular Visual Odometry Using Learned Depth","created":"2022-04-04","cited_by_count":17,"area":null},{"id":"2203.04206","title":"Lightweight Monocular Depth Estimation through Guided Decoding","created":"2022-03-08","cited_by_count":14,"area":null},{"id":"2106.06629","title":"Mirror3D: Depth Refinement for Mirror Surfaces","created":"2021-06-11","cited_by_count":13,"area":null},{"id":"2201.01367","title":"DenseTact: Optical Tactile Sensor for Dense Shape Reconstruction","created":"2022-01-04","cited_by_count":13,"area":null},{"id":"2308.11513","title":"TrackFlow: Multi-Object Tracking with Normalizing Flows","created":"2023-08-22","cited_by_count":13,"area":null},{"id":"2309.12842","title":"SRFNet: Monocular Depth Estimation with Fine-grained Structure via Spatial Reliability-oriented Fusion of Frames and Events","created":"2023-09-22","cited_by_count":13,"area":null},{"id":"2203.04895","title":"Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction","created":"2022-03-09","cited_by_count":12,"area":null},{"id":"2304.04672","title":"Deep Image Matting: A Comprehensive Survey","created":"2023-04-10","cited_by_count":12,"area":null},{"id":"2305.01732","title":"High-Resolution Synthetic RGB-D Datasets for Monocular Depth Estimation","created":"2023-05-02","cited_by_count":10,"area":null},{"id":"2106.02594","title":"Self-Supervised Learning of Domain Invariant Features for Depth Estimation","created":"2021-06-04","cited_by_count":9,"area":null},{"id":"2110.06427","title":"Dense Uncertainty Estimation","created":"2021-10-13","cited_by_count":9,"area":null},{"id":"2201.08131","title":"GeoFill: Reference-Based Image Inpainting with Better Geometric Understanding","created":"2022-01-20","cited_by_count":9,"area":null},{"id":"2206.03666","title":"Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking","created":"2022-06-08","cited_by_count":9,"area":null},{"id":"2410.08567","title":"Diffusion-Based Depth Inpainting for Transparent and Reflective Objects","created":"2024-10-11","cited_by_count":9,"area":null},{"id":"2104.05309","title":"Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search","created":"2021-04-12","cited_by_count":8,"area":null},{"id":"2107.11001","title":"Photon-Starved Scene Inference using Single Photon Cameras","created":"2021-07-23","cited_by_count":8,"area":null},{"id":"2110.14347","title":"CamLessMonoDepth: Monocular Depth Estimation with Unknown Camera Parameters","created":"2021-10-27","cited_by_count":8,"area":null},{"id":"2111.01715","title":"Absolute distance prediction based on deep learning object detection and monocular depth estimation models","created":"2021-11-02","cited_by_count":8,"area":null},{"id":"2309.16486","title":"HTC-DC Net: Monocular Height Estimation from Single Remote Sensing Images","created":"2023-09-28","cited_by_count":8,"area":null},{"id":"2406.10068","title":"DurLAR: A High-fidelity 128-channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-modal Autonomous Driving Applications","created":"2024-06-14","cited_by_count":8,"area":null},{"id":"2503.16709","title":"QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge","created":"2025-03-20","cited_by_count":8,"area":null},{"id":"2107.00372","title":"Egocentric Image Captioning for Privacy-Preserved Passive Dietary Intake Monitoring","created":"2021-07-01","cited_by_count":7,"area":null},{"id":"2108.04584","title":"UniNet: A Unified Scene Understanding Network and Exploring Multi-Task Relationships through the Lens of Adversarial Attacks","created":"2021-08-10","cited_by_count":7,"area":null},{"id":"2206.15170","title":"LiDAR-as-Camera for End-to-End Driving","created":"2022-06-30","cited_by_count":7,"area":null},{"id":"2208.13714","title":"SphereDepth: Panorama Depth Estimation from Spherical Domain","created":"2022-08-29","cited_by_count":7,"area":null},{"id":"2305.00664","title":"EvoluNet: Advancing Dynamic Non-IID Transfer Learning on Graphs","created":"2023-05-01","cited_by_count":7,"area":null},{"id":"2403.08368","title":"METER: a mobile vision transformer architecture for monocular depth estimation","created":"2024-03-13","cited_by_count":7,"area":null},{"id":"2106.06927","title":"Inverting Adversarially Robust Networks for Image Synthesis","created":"2021-06-13","cited_by_count":6,"area":null},{"id":"2211.05094","title":"3D Scene Inference from Transient Histograms","created":"2022-11-09","cited_by_count":6,"area":null},{"id":"2301.04037","title":"ROBUSfT: Robust Real-Time Shape-from-Template, a C++ Library","created":"2023-01-10","cited_by_count":6,"area":null},{"id":"2310.05837","title":"A Real-time Method for Inserting Virtual Objects into Neural Radiance Fields","created":"2023-10-09","cited_by_count":5,"area":null},{"id":"2402.11791","title":"SDGE: Stereo Guided Depth Estimation for 360$^\\circ$ Camera Sets","created":"2024-02-19","cited_by_count":5,"area":null},{"id":"2403.01440","title":"Pyramid Feature Attention Network for Monocular Depth Prediction","created":"2024-03-03","cited_by_count":5,"area":null},{"id":"2107.13263","title":"Learning-Based Depth and Pose Estimation for Monocular Endoscope with Loss Generalization","created":"2021-07-28","cited_by_count":4,"area":null},{"id":"2110.10415","title":"Depth360: Self-supervised Learning for Monocular Depth Estimation using Learnable Camera Distortion Model","created":"2021-10-20","cited_by_count":4,"area":null},{"id":"2204.07076","title":"End-to-end Learning for Joint Depth and Image Reconstruction from Diffracted Rotation","created":"2022-04-14","cited_by_count":4,"area":null},{"id":"2110.03278","title":"Virtual Multi-Modality Self-Supervised Foreground Matting for Human-Object Interaction","created":"2021-10-07","cited_by_count":3,"area":null},{"id":"2110.11679","title":"Depth-only Object Tracking","created":"2021-10-22","cited_by_count":3,"area":null},{"id":"2111.03039","title":"Towards Panoptic 3D Parsing for Single Image in the Wild","created":"2021-11-04","cited_by_count":3,"area":null},{"id":"2203.06457","title":"3D-GIF: 3D-Controllable Object Generation via Implicit Factorized Representations","created":"2022-03-12","cited_by_count":3,"area":null},{"id":"2204.11045","title":"Investigating Neural Architectures by Synthetic Dataset Design","created":"2022-04-23","cited_by_count":3,"area":null},{"id":"2210.05479","title":"Frequency-Aware Self-Supervised Monocular Depth Estimation","created":"2022-10-11","cited_by_count":3,"area":null},{"id":"2210.07140","title":"U-HRNet: Delving into Improving Semantic Representation of High Resolution Network for Dense Prediction","created":"2022-10-13","cited_by_count":3,"area":null},{"id":"2301.09315","title":"AI-Based Framework for Understanding Car Following Behaviors of Drivers in A Naturalistic Driving Environment","created":"2023-01-23","cited_by_count":3,"area":null},{"id":"2310.11184","title":"Sparse Multi-Object Render-and-Compare","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2103.12297","title":"Adaptive Illumination based Depth Sensing using Deep Superpixel and Soft Sampling Approximation","created":"2021-03-23","cited_by_count":2,"area":null},{"id":"2105.10129","title":"A Novel 3D-UNet Deep Learning Framework Based on High-Dimensional Bilateral Grid for Edge Consistent Single Image Depth Estimation","created":"2021-05-21","cited_by_count":2,"area":null},{"id":"2110.02405","title":"Echo-Reconstruction: Audio-Augmented 3D Scene Reconstruction","created":"2021-10-05","cited_by_count":2,"area":null},{"id":"2205.08668","title":"Learning Monocular Depth Estimation via Selective Distillation of Stereo Knowledge","created":"2022-05-18","cited_by_count":2,"area":null},{"id":"2211.08608","title":"LightDepth: A Resource Efficient Depth Estimation Approach for Dealing with Ground Truth Sparsity via Curriculum Learning","created":"2022-11-16","cited_by_count":2,"area":null},{"id":"2311.05021","title":"Leveraging a realistic synthetic database to learn Shape-from-Shading for estimating the colon depth in colonoscopy images","created":"2023-11-08","cited_by_count":2,"area":null},{"id":"2410.19336","title":"DECADE: Towards Designing Efficient-yet-Accurate Distance Estimation Modules for Collision Avoidance in Mobile Advanced Driver Assistance Systems","created":"2024-10-25","cited_by_count":2,"area":null},{"id":"2502.05859","title":"SphereFusion: Efficient Panorama Depth Estimation via Gated Fusion","created":"2025-02-09","cited_by_count":2,"area":null},{"id":"2103.05158","title":"Deep Learning-based High-precision Depth Map Estimation from Missing Viewpoints for 360 Degree Digital Holography","created":"2021-03-09","cited_by_count":1,"area":null},{"id":"2110.09380","title":"Learning multiplane images from single views with self-supervision","created":"2021-10-18","cited_by_count":1,"area":null},{"id":"2111.01878","title":"Discovering Supply Chain Links with Augmented Intelligence","created":"2021-11-02","cited_by_count":1,"area":null},{"id":"2201.04485","title":"Depth Estimation from Single-shot Monocular Endoscope Image Using Image Domain Adaptation And Edge-Aware Depth Estimation","created":"2022-01-12","cited_by_count":1,"area":null},{"id":"2208.13441","title":"Rethinking Skip Connections in Encoder-decoder Networks for Monocular Depth Estimation","created":"2022-08-29","cited_by_count":1,"area":null},{"id":"2210.13646","title":"Depth Monocular Estimation with Attention-based Encoder-Decoder Network from Single Image","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2301.00555","title":"Scene Structure Guidance Network: Unfolding Graph Partitioning into Pixel-Wise Feature Learning","created":"2023-01-02","cited_by_count":1,"area":null},{"id":"2301.06184","title":"LitAR: Visually Coherent Lighting for Mobile Augmented Reality","created":"2023-01-15","cited_by_count":1,"area":null},{"id":"2307.09929","title":"Measuring and Modeling Uncertainty Degree for Monocular Depth Estimation","created":"2023-07-19","cited_by_count":1,"area":null},{"id":"2308.06628","title":"Fusion-GRU: A Deep Learning Model for Future Bounding Box Prediction of Traffic Agents in Risky Driving Videos","created":"2023-08-12","cited_by_count":1,"area":null},{"id":"2309.13516","title":"InSpaceType: Reconsider Space Type in Indoor Monocular Depth Estimation","created":"2023-09-24","cited_by_count":1,"area":null},{"id":"2311.11604","title":"CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage Refinement","created":"2023-11-20","cited_by_count":1,"area":null},{"id":"2401.03191","title":"Monocular Per-Object Distance Estimation with Masked Object Modeling","created":"2024-01-06","cited_by_count":1,"area":null},{"id":"2404.07686","title":"Depth Estimation using Weighted-loss and Transfer Learning","created":"2024-04-11","cited_by_count":1,"area":null},{"id":"2409.15006","title":"Generalizing monocular colonoscopy image depth estimation by uncertainty-based global and local fusion network","created":"2024-09-23","cited_by_count":1,"area":null},{"id":"2504.01988","title":"NeoARCADE: Robust Calibration for Distance Estimation to Support Assistive Drones for the Visually Impaired","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2507.18656","title":"ShrinkBox: Backdoor Attack on Object Detection to Disrupt Collision Avoidance in Machine Learning-based Advanced Driver Assistance Systems","created":"2025-07-22","cited_by_count":1,"area":null},{"id":"2510.01665","title":"Non-Rigid Structure-from-Motion via Differential Geometry with Recoverable Conformal Scale","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2512.13147","title":"StarryGazer: Leveraging Monocular Depth Estimation Models for Domain-Agnostic Single Depth Image Completion","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2102.09142","title":"Improved Point Transformation Methods For Self-Supervised Depth Prediction","created":"2021-02-18","cited_by_count":0,"area":null},{"id":"2102.10514","title":"Progressive Depth Learning for Single Image Dehazing","created":"2021-02-21","cited_by_count":0,"area":null},{"id":"2103.08297","title":"GRIHA: Synthesizing 2-Dimensional Building Layouts from Images Captured using a Smart Phone","created":"2021-03-15","cited_by_count":0,"area":null},{"id":"2103.12996","title":"Resonant Scanning Design and Control for Fast Spatial Sampling","created":"2021-03-24","cited_by_count":0,"area":null},{"id":"2104.10874","title":"Focusing on Shadows for Predicting Heightmaps from Single Remotely Sensed RGB Images with Deep Learning","created":"2021-04-22","cited_by_count":0,"area":null},{"id":"2107.04819","title":"A Weakly-Supervised Depth Estimation Network Using Attention Mechanism","created":"2021-07-10","cited_by_count":0,"area":null},{"id":"2107.06445","title":"MSFNet:Multi-scale features network for monocular depth estimation","created":"2021-07-14","cited_by_count":0,"area":null},{"id":"2111.10984","title":"Topological Regularization for Dense Prediction","created":"2021-11-22","cited_by_count":0,"area":null},{"id":"2203.03405","title":"Depth-SIMS: Semi-Parametric Image and Depth Synthesis","created":"2022-03-07","cited_by_count":0,"area":null}],"next_cursor":"100"}