{"list":"other","total":88,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"1804.02505","title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","created":"2018-04-07","cited_by_count":788},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2107.02791","title":"Depth-supervised NeRF: Fewer Views and Faster Training for Free","created":"2021-07-06","cited_by_count":735},{"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":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2112.12130","title":"NICE-SLAM: Neural Implicit Scalable Encoding for SLAM","created":"2021-12-22","cited_by_count":589},{"id":"2111.11426","title":"Neural Fields in Visual Computing and Beyond","created":"2021-11-22","cited_by_count":540},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"1812.07179","title":"Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving","created":"2018-12-18","cited_by_count":457},{"id":"1606.00373","title":"Deeper Depth Prediction with Fully Convolutional Residual Networks","created":"2016-06-01","cited_by_count":403},{"id":"1907.10326","title":"From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation","created":"2019-07-24","cited_by_count":382},{"id":"1603.04992","title":"Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue","created":"2016-03-16","cited_by_count":368},{"id":"2111.05849","title":"Advances in Neural Rendering","created":"2021-11-10","cited_by_count":365},{"id":"1703.04309","title":"End-to-End Learning of Geometry and Context for Deep Stereo Regression","created":"2017-03-13","cited_by_count":360},{"id":"2109.07547","title":"RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching","created":"2021-09-15","cited_by_count":353},{"id":"1803.02276","title":"GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose","created":"2018-03-06","cited_by_count":342},{"id":"2104.04532","title":"Neural RGB-D Surface Reconstruction","created":"2021-04-09","cited_by_count":313},{"id":"1804.00650","title":"DeepMVS: Learning Multi-view Stereopsis","created":"2018-04-02","cited_by_count":277},{"id":"2111.14643","title":"Urban Radiance Fields","created":"2021-11-29","cited_by_count":263},{"id":"1908.10553","title":"Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video","created":"2019-08-28","cited_by_count":244},{"id":"2104.00681","title":"NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video","created":"2021-04-01","cited_by_count":241},{"id":"2111.13152","title":"Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations","created":"2021-11-25","cited_by_count":227},{"id":"1704.00390","title":"Geometric Loss Functions for Camera Pose Regression with Deep Learning","created":"2017-04-02","cited_by_count":224},{"id":"2012.09365","title":"Learning to Recover 3D Scene Shape from a Single Image","created":"2020-12-17","cited_by_count":216},{"id":"1612.02401","title":"DeMoN: Depth and Motion Network for Learning Monocular Stereo","created":"2016-12-07","cited_by_count":201},{"id":"2109.01129","title":"NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo","created":"2021-09-02","cited_by_count":192},{"id":"2011.02910","title":"Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers","created":"2020-11-05","cited_by_count":190},{"id":"2012.05901","title":"Robust Consistent Video Depth Estimation","created":"2020-12-10","cited_by_count":188},{"id":"1604.03901","title":"Single-Image Depth Perception in the Wild","created":"2016-04-13","cited_by_count":180},{"id":"1802.05522","title":"Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints","created":"2018-02-15","cited_by_count":179},{"id":"1903.07504","title":"Understanding the Limitations of CNN-based Absolute Camera Pose Regression","created":"2019-03-18","cited_by_count":177},{"id":"1806.04807","title":"BA-Net: Dense Bundle Adjustment Network","created":"2018-06-13","cited_by_count":175},{"id":"1904.04998","title":"Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras","created":"2019-04-10","cited_by_count":170},{"id":"2007.10603","title":"Feature-metric Loss for Self-supervised Learning of Depth and Egomotion","created":"2020-07-21","cited_by_count":140},{"id":"2002.12319","title":"Semantically-Guided Representation Learning for Self-Supervised Monocular Depth","created":"2020-02-27","cited_by_count":134},{"id":"1812.11941","title":"High Quality Monocular Depth Estimation via Transfer Learning","created":"2018-12-31","cited_by_count":133},{"id":"1907.05820","title":"Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Camera","created":"2019-07-12","cited_by_count":130},{"id":"2012.00726","title":"RAFT-3D: Scene Flow using Rigid-Motion Embeddings","created":"2020-12-01","cited_by_count":122},{"id":"2104.07652","title":"Geometry-Free View Synthesis: Transformers and no 3D Priors","created":"2021-04-15","cited_by_count":100},{"id":"1912.00497","title":"Just Go with the Flow: Self-Supervised Scene Flow Estimation","created":"2019-12-01","cited_by_count":98},{"id":"1709.06841","title":"UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning","created":"2017-09-20","cited_by_count":95},{"id":"1704.07804","title":"SfM-Net: Learning of Structure and Motion from Video","created":"2017-04-25","cited_by_count":89},{"id":"1808.01900","title":"DeepTAM: Deep Tracking and Mapping","created":"2018-08-06","cited_by_count":87},{"id":"2004.01314","title":"Towards Better Generalization: Joint Depth-Pose Learning without PoseNet","created":"2020-04-03","cited_by_count":85},{"id":"2008.06534","title":"MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Images","created":"2020-08-14","cited_by_count":64},{"id":"2204.07616","title":"Multi-Frame Self-Supervised Depth with Transformers","created":"2022-04-15","cited_by_count":64},{"id":"2011.13118","title":"Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks","created":"2020-11-26","cited_by_count":59},{"id":"2005.01616","title":"VisualEchoes: Spatial Image Representation Learning through Echolocation","created":"2020-05-04","cited_by_count":55},{"id":"1807.08957","title":"The Double Sphere Camera Model","created":"2018-07-24","cited_by_count":52},{"id":"1904.06504","title":"Visual-Inertial Mapping with Non-Linear Factor Recovery","created":"2019-04-13","cited_by_count":50},{"id":"1911.10444","title":"Normal Assisted Stereo Depth Estimation","created":"2019-11-24","cited_by_count":49},{"id":"2101.03694","title":"Learning to Segment Rigid Motions from Two Frames","created":"2021-01-11","cited_by_count":46},{"id":"1712.01259","title":"A Perceptual Measure for Deep Single Image Camera Calibration","created":"2017-12-02","cited_by_count":45},{"id":"1912.02908","title":"Why Having 10,000 Parameters in Your Camera Model is Better Than Twelve","created":"2019-12-05","cited_by_count":43},{"id":"2004.00845","title":"Occlusion-Aware Depth Estimation with Adaptive Normal Constraints","created":"2020-04-02","cited_by_count":41},{"id":"1905.02706","title":"Learning Unsupervised Multi-View Stereopsis via Robust Photometric Consistency","created":"2019-05-07","cited_by_count":40},{"id":"2003.14030","title":"Distilled Semantics for Comprehensive Scene Understanding from Videos","created":"2020-03-31","cited_by_count":39},{"id":"1911.12408","title":"PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Clouds","created":"2019-11-27","cited_by_count":38},{"id":"1910.04076","title":"FisheyeDistanceNet: Self-Supervised Scale-Aware Distance Estimation using Monocular Fisheye Camera for Autonomous Driving","created":"2019-10-07","cited_by_count":36},{"id":"2112.03243","title":"Input-level Inductive Biases for 3D Reconstruction","created":"2021-12-06","cited_by_count":31},{"id":"2203.15089","title":"Learning Optical Flow, Depth, and Scene Flow without Real-World Labels","created":"2022-03-28","cited_by_count":31},{"id":"1604.02129","title":"Horizon Lines in the Wild","created":"2016-04-07","cited_by_count":30},{"id":"1705.03951","title":"Learning 3D Object Categories by Looking Around Them","created":"2017-05-10","cited_by_count":26},{"id":"2104.04420","title":"SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Cameras","created":"2021-04-09","cited_by_count":25},{"id":"2103.16026","title":"Progressively Complementary Network for Fisheye Image Rectification Using Appearance Flow","created":"2021-03-30","cited_by_count":23},{"id":"2008.06630","title":"Neural Ray Surfaces for Self-Supervised Learning of Depth and Ego-motion","created":"2020-08-15","cited_by_count":20},{"id":"2010.08942","title":"Distortion-aware Monocular Depth Estimation for Omnidirectional Images","created":"2020-10-18","cited_by_count":17},{"id":"2112.03325","title":"Self-Supervised Camera Self-Calibration from Video","created":"2021-12-06","cited_by_count":17},{"id":"1905.07515","title":"Learning Perspective Undistortion of Portraits","created":"2019-05-18","cited_by_count":14},{"id":"2003.08934","title":"NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis","created":"2020-03-19","cited_by_count":14},{"id":"2007.10689","title":"A Deep Ordinal Distortion Estimation Approach for Distortion Rectification","created":"2020-07-21","cited_by_count":13},{"id":"1505.07427","title":"PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization","created":"2015-05-27","cited_by_count":11},{"id":"1812.03368","title":"Unsupervised Learning of Monocular Depth Estimation with Bundle Adjustment, Super-Resolution and Clip Loss","created":"2018-12-08","cited_by_count":9},{"id":"1904.11934","title":"Single Image Reflection Removal with Physically-Based Training Images","created":"2019-04-26","cited_by_count":3}],"next_cursor":null}