Table of Contents

• MVS2: Deep Unsupervised Multi-View Stereo with Multi-View SymmetryYuchao Dai, Zhidong Zhu, Zhibo Rao, Bo Li 0004. 1-8 [doi]
• Fast Stereo Disparity Maps Refinement By Fusion of Data-Based And Model-Based EstimationsMaxime Ferrera, Alexandre Boulch, Julien Moras. 9-17 [doi]
• Structured Coupled Generative Adversarial Networks for Unsupervised Monocular Depth EstimationMihai Marian Puscas, Dan Xu 0002, Andrea Pilzer, Nicu Sebe. 18-26 [doi]
• DispVoxNets: Non-Rigid Point Set Alignment with Supervised Learning ProxiesSoshi Shimada, Vladislav Golyanik, Edgar Tretschk, Didier Stricker, Christian Theobalt. 27-36 [doi]
• Correspondence-Free Region Localization for Partial Shape Similarity via Hamiltonian Spectrum AlignmentArianna Rampini, Irene Tallini, Maks Ovsjanikov, Alexander M. Bronstein, Emanuele Rodolà. 37-46 [doi]
• Effective Rotation-Invariant Point CNN with Spherical Harmonics KernelsAdrien Poulenard, Marie-Julie Rakotosaona, Yann Ponty, Maks Ovsjanikov. 47-56 [doi]
• Structured Domain Adaptation for 3D Keypoint EstimationLevi O. Vasconcelos, Massimiliano Mancini, Davide Boscaini, Barbara Caputo, Elisa Ricci 0001. 57-66 [doi]
• Learning Point Embeddings from Shape Repositories for Few-Shot SegmentationGopal Sharma, Evangelos Kalogerakis, Subhransu Maji. 67-75 [doi]
• Pano Popups: Indoor 3D Reconstruction with a Plane-Aware NetworkMarc Eder, Pierre Moulon, Li Guan. 76-84 [doi]
• IoU Loss for 2D/3D Object DetectionDingfu Zhou, Jin Fang, Xibin Song, Chenye Guan, Junbo Yin, Yuchao Dai, Ruigang Yang. 85-94 [doi]
• Pixel-Accurate Depth Evaluation in Realistic Driving ScenariosTobias Gruber, Mario Bijelic, Felix Heide, Werner Ritter, Klaus Dietmayer. 95-105 [doi]
• SyDPose: Object Detection and Pose Estimation in Cluttered Real-World Depth Images Trained using Only Synthetic DataStefan Thalhammer, Timothy Patten, Markus Vincze. 106-115 [doi]
• NoVA: Learning to See in Novel Viewpoints and DomainsBenjamin Coors, Alexandru Paul Condurache, Andreas Geiger. 116-125 [doi]
• Learning Depth from Endoscopic ImagesJu Hong Yoon, Min-Gyu Park, Youngbae Hwang, Kuk-Jin Yoon. 126-134 [doi]
• Pairwise Attention Encoding for Point Cloud Feature LearningYunxiao Shi, Haoyu Fang, Jing Zhu, Yi Fang. 135-144 [doi]
• PC-Net: Unsupervised Point Correspondence Learning with Neural NetworksXiang Li, Lingjing Wang, Yi Fang. 145-154 [doi]
• A Unified Point-Based Framework for 3D SegmentationHungYueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu. 155-163 [doi]
• Optimising for Scale in Globally Multiply-Linked Gravitational Point Set Registration Leads to SingularitiesVladislav Golyanik, Christian Theobalt. 164-172 [doi]
• 3D Neighborhood Convolution: Learning Depth-Aware Features for RGB-D and RGB Semantic SegmentationYunlu Chen, Thomas Mensink, Efstratios Gavves. 173-182 [doi]
• To Complete or to Estimate, That is the Question: A Multi-Task Approach to Depth Completion and Monocular Depth EstimationAmir Atapour Abarghouei, Toby P. Breckon. 183-193 [doi]
• Frequency Shift Triangulation: A Robust Fringe Projection Technique for 3D Shape Acquisition in the Presence of Strong InterreflectionsFrank Billy Djupkep Dizeu, Jonathan Boisvert, Marc-Antoine Drouin, Guy Godin, Maxime Rivard, Guy Lamouche. 194-203 [doi]
• Rotation Invariant Convolutions for 3D Point Clouds Deep LearningZhiyuan Zhang, Binh-Son Hua, David W. Rosen, Sai Kit Yeung. 204-213 [doi]
• Accurate and Real-Time Object Detection Based on Bird's Eye View on 3D Point CloudsYi Zhang, Zhiyu Xiang, Chengyu Qiao, Shuya Chen. 214-221 [doi]
• Photometric Segmentation: Simultaneous Photometric Stereo and MaskingBjoern Haefner, Yvain Quéau, Daniel Cremers. 222-229 [doi]
• High-Resolution Augmentation for Automatic Template-Based Matching of Human ModelsRiccardo Marin, Simone Melzi, Emanuele Rodolà, Umberto Castellani. 230-239 [doi]
• V-NAS: Neural Architecture Search for Volumetric Medical Image SegmentationZhuotun Zhu, Chenxi Liu, Dong Yang, Alan L. Yuille, Daguang Xu. 240-248 [doi]
• Learning to Think Outside the Box: Wide-Baseline Light Field Depth Estimation with EPI-ShiftTitus Leistner, Hendrik Schilling, Radek Mackowiak, Stefan Gumhold, Carsten Rother. 249-257 [doi]
• 360° Surface Regression with a Hyper-Sphere LossAntonis Karakottas, Nikolaos Zioulis, Stamatis Samaras, Dimitrios Ataloglou, Vasileios Gkitsas, Dimitrios Zarpalas, Petros Daras. 258-268 [doi]
• Asynchronous Multi-Hypothesis Tracking of Features with Event CamerasIgnacio Alzugaray, Margarita Chli. 269-278 [doi]
• Towards Accurate 3D Human Body Reconstruction from SilhouettesBrandon M. Smith, Visesh Chari, Amit Agrawal, James M. Rehg, Ram Sever. 279-288 [doi]
• Progression Modelling for Online and Early Gesture DetectionVikram Gupta, Sai Kumar Dwivedi, Rishabh Dabral, Arjun Jain. 289-297 [doi]
• Predicting Animation Skeletons for 3D Articulated Models via Volumetric NetsZhan Xu, Yang Zhou, Evangelos Kalogerakis, Karan Singh. 298-307 [doi]
• Motion Capture from Pan-Tilt Cameras with Unknown OrientationRoman Bachmann, Jörg Spörri, Pascal Fua, Helge Rhodin. 308-317 [doi]
• Convex Optimisation for Inverse KinematicsTarun Yenamandra, Florian Bernard, Jiayi Wang, Franziska Mueller 0001, Christian Theobalt. 318-327 [doi]
• Revisiting Depth Image Fusion with Variational Message PassingDiego Thomas, Ekaterina Sirazitdinova, Akihiro Sugimoto, Rin-ichiro Taniguchi. 328-337 [doi]
• Distributed Surface Reconstruction from Point Cloud for City-Scale ScenesJiali Han, Shuhan Shen. 338-347 [doi]
• Web Stereo Video Supervision for Depth Prediction from Dynamic ScenesChaoyang Wang, Simon Lucey, Federico Perazzi, Oliver Wang. 348-357 [doi]
• Learning to Refine 3D Human Pose SequencesJieru Mei, Xingyu Chen, Chunyu Wang, Alan L. Yuille, Xuguang Lan, Wenjun Zeng. 358-366 [doi]
• Reconstruction of As-is Semantic 3D Models of Unorganised StorehousesAntonio Adán, David de la Rubia. 367-375 [doi]
• Dynamic Surface Animation using Generative NetworksJoão Regateiro, Adrian Hilton, Marco Volino. 376-385 [doi]
• Decoupled Hybrid 360° Panoramic Stereo VideoKevin Kyunghwan Ra, James J. Clark. 386-394 [doi]
• Unsupervised Feature Learning for Point Cloud Understanding by Contrasting and Clustering Using Graph Convolutional Neural NetworksLing Zhang, Zhigang Zhu. 395-404 [doi]
• Multi-Person 3D Human Pose Estimation from Monocular ImagesRishabh Dabral, Nitesh B. Gundavarapu, Rahul Mitra, Abhishek Sharma, Ganesh Ramakrishnan, Arjun Jain. 405-414 [doi]
• Optimal, Non-Rigid Alignment for Feature-Preserving Mesh DenoisingFlorian Gawrilowicz, J. Andreas Bærentzen. 415-423 [doi]
• Enhancing Self-Supervised Monocular Depth Estimation with Traditional Visual OdometryLorenzo Andraghetti, Panteleimon Myriokefalitakis, Pier Luigi Dovesi, Belén Luque, Matteo Poggi, Alessandro Pieropan, Stefano Mattoccia. 424-433 [doi]
• Creating Realistic Ground Truth Data for the Evaluation of Calibration Methods for Plenoptic and Conventional CamerasTim Michels, Arne Petersen, Reinhard Koch. 434-442 [doi]
• Multi-Spectral Visual Odometry without Explicit Stereo MatchingWeichen Dai, Yu Zhang, Donglei Sun, Naira Hovakimyan, Ping Li. 443-452 [doi]
• Simultaneous Shape Registration and Active Stereo Shape Reconstruction using Modified Bundle AdjustmentRyo Furukawa, Genki Nagamatsu, Hiroshi Kawasaki. 453-462 [doi]
• Semantic Segmentation of Sparsely Annotated 3D Point Clouds by Pseudo-LabellingKatie Xu, Yasuhiro Yao, Kazuhiko Murasaki, Shingo Ando, Atsushi Sagata. 463-471 [doi]
• SIR-Net: Scene-Independent End-to-End Trainable Visual RelocalizerRyo Nakashima, Akihito Seki. 472-481 [doi]
• Light Field Compression using Eigen TexturesMarco Volino, Armin Mustafa, Jean-Yves Guillemaut, Adrian Hilton. 482-490 [doi]
• Res3ATN - Deep 3D Residual Attention Network for Hand Gesture Recognition in VideosNaina Dhingra, Andreas Kunz. 491-501 [doi]
• Physics-Aware 3D Mesh SynthesisJianren Wang, Yihui He. 502-512 [doi]
• Sparse-to-Dense Hypercolumn Matching for Long-Term Visual LocalizationHugo Germain, Guillaume Bourmaud, Vincent Lepetit. 513-523 [doi]
• Unified Underwater Structure-from-MotionKazuto Ichimaru, Yuichi Taguchi, Hiroshi Kawasaki. 524-532 [doi]
• Learned Multi-View Texture Super-ResolutionAudrey Richard, Ian Cherabier, Martin R. Oswald, Vagia Tsiminaki, Marc Pollefeys, Konrad Schindler. 533-543 [doi]
• Online Stability Improvement of Gröbner Basis Solvers using Deep LearningWanting Xu, Lan Hu, Manolis C. Tsakiris, Laurent Kneip. 544-552 [doi]
• Surface Reconstruction from 3D Line SegmentsPierre-Alain Langlois, Alexandre Boulch, Renaud Marlet. 553-563 [doi]
• Let's Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera RelocalisationTommaso Cavallari, Luca Bertinetto, Jishnu Mukhoti, Philip H. S. Torr, Stuart Golodetz. 564-573 [doi]
• Mobile Photometric Stereo with Keypoint-Based SLAM for Dense 3D ReconstructionRemy Maxence, Hideaki Uchiyama, Hiroshi Kawasaki, Diego Thomas, Vincent Nozick, Hideo Saito. 574-582 [doi]
• Location Field Descriptors: Single Image 3D Model Retrieval in the WildAlexander Grabner, Peter M. Roth, Vincent Lepetit. 583-593 [doi]
• On the Redundancy Detection in Keyframe-Based SLAMPatrik Schmuck, Margarita Chli. 594-603 [doi]
• SIPs: Succinct Interest Points from Unsupervised Inlierness Probability LearningTitus Cieslewski, Konstantinos G. Derpanis, Davide Scaramuzza. 604-613 [doi]
• On Object Symmetries and 6D Pose Estimation from ImagesGiorgia Pitteri, Michaël Ramamonjisoa, Slobodan Ilic, Vincent Lepetit. 614-622 [doi]
• AlignNet-3D: Fast Point Cloud Registration of Partially Observed ObjectsJohannes Groß, Aljosa Osep, Bastian Leibe. 623-632 [doi]
• UnDispNet: Unsupervised Learning for Multi-Stage Monocular Depth PredictionVinay Kaushik, Brejesh Lall. 633-642 [doi]
• 360-Degree Textures of People in Clothing from a Single ImageVerica Lazova, Eldar Insafutdinov, Gerard Pons-Moll. 643-653 [doi]
• Adaptive-Resolution Octree-Based Volumetric SLAMEmanuele Vespa, Nils Funk, Paul H. J. Kelly, Stefan Leutenegger. 654-662 [doi]
• Multimodal 3D Human Pose Estimation from a Single ImageScott Spurlock, Richard Souvenir. 663-670 [doi]
• Effective Convolutional Neural Network Layers in Flow Estimation for Omni-Directional ImagesShuang Xie, Po Kong Lai, Robert Laganière, Jochen Lang 0001. 671-680 [doi]
• Learning to Translate Between Real World and Simulated 3D Sensors While Transferring Task ModelsMichael Essich, Dennis Ludl, Thomas Gulde, Cristóbal Curio. 681-689 [doi]
• Spherical View Synthesis for Self-Supervised 360° Depth EstimationNikolaos Zioulis, Antonis Karakottas, Dimitrios Zarpalas, Federico Alvarez, Petros Daras. 690-699 [doi]
• Adaptive Mesh Texture for Multi-View Appearance ModelingMatthieu Armando, Jean-Sébastien Franco, Edmond Boyer. 700-708 [doi]
• Real-Time Multi-Material Reflectance Reconstruction for Large-Scale Scenes Under Uncontrolled Illumination from RGB-D Image SequencesLukas Bode, Sebastian Merzbach, Patrick Stotko, Michael Weinmann, Reinhard Klein. 709-718 [doi]
• Language2Pose: Natural Language Grounded Pose ForecastingChaitanya Ahuja, Louis-Philippe Morency. 719-728 [doi]
• Synthesizing Diverse Lung Nodules Wherever Massively: 3D Multi-Conditional GAN-Based CT Image Augmentation for Object DetectionChanghee Han, Yoshiro Kitamura, Akira Kudo, Akimichi Ichinose, Leonardo Rundo, Yujiro Furukawa, Kazuki Umemoto, Yuanzhong Li, Hideki Nakayama. 729-737 [doi]
• Multiple Point Light Estimation from Low-Quality 3D ReconstructionsMike Kasper, Christoffer Heckman. 738-746 [doi]
• Fast Non-Convex Hull ComputationJulián Bayardo Spadafora, Francisco Gómez Fernández, Gabriel Taubin. 747-755 [doi]
• Incorporating 3D Information Into Visual Question AnsweringYue Qiu, Yutaka Satoh, Ryota Suzuki 0006, Hirokatsu Kataoka. 756-765 [doi]