Table of Contents

• Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D ShapesKeyang Zhou, Bharat Lal Bhatnagar, Bernt Schiele, Gerard Pons-Moll. 1-11 [doi]
• On Triangulation as a Form of Self-Supervision for 3D Human Pose EstimationSoumava Kumar Roy, Leonardo Citraro, Sina Honari, Pascal Fua. 1-10 [doi]
• Simultaneous Localisation and Mapping With Quadric SurfacesTristan Laidlow, Andrew J. Davison. 1-9 [doi]
• Controllable Radiance Fields for Dynamic Face SynthesisPeiye Zhuang, Liqian Ma, Sanmi Koyejo, Alexander G. Schwing. 1-11 [doi]
• Spectral Teacher for a Spatial Student: Spectrum-Aware Real-Time Dense Shape CorrespondenceOmri Efroni, Dvir Ginzburg, Dan Raviv. 1-10 [doi]
• Dual-Space NeRF: Learning Animatable Avatars and Scene Lighting in Separate SpacesYiHao Zhi, Shenhan Qian, Xinhao Yan, Shenghua Gao. 1-10 [doi]
• Push-the-Boundary: Boundary-aware Feature Propagation for Semantic Segmentation of 3D Point CloudsShenglan Du, Nail Ibrahimli, Jantien E. Stoter, Julian Kooij, Liangliang Nan. 1-10 [doi]
• Efficient Human Pose Estimation via 3D Event Point CloudJiaan Chen, Hao Shi, Yaozu Ye, Kailun Yang 0001, Lei Sun 0009, Kaiwei Wang. 1-10 [doi]
• Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene SegmentationXiao Fu, Shangzhan Zhang, Tianrun Chen, Yichong Lu, Lanyun Zhu, Xiaowei Zhou, Andreas Geiger 0001, Yiyi Liao. 1-11 [doi]
• Message from the Program Chairs: 3DV 2022Angela Dai, Jana Kosecka, Gin Hee Lee, Konrad Schindler. 1 [doi]
• LC-NAS: Latency Constrained Neural Architecture Search for Point Cloud NetworksGuohao Li, Mengmeng Xu, Silvio Giancola, Ali K. Thabet, Bernard Ghanem. 1-11 [doi]
• The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTsChris Rockwell, Justin Johnson 0001, David F. Fouhey. 1-11 [doi]
• SphereDepth: Panorama Depth Estimation from Spherical DomainQingsong Yan, Qiang Wang 0022, Kaiyong Zhao, Bo Li 0001, Xiaoweo Chu, Fei Deng. 1-10 [doi]
• MoCapDeform: Monocular 3D Human Motion Capture in Deformable ScenesZhi Li, Soshi Shimada, Bernt Schiele, Christian Theobalt, Vladislav Golyanik. 1-11 [doi]
• Benchmarking Pedestrian Odometry: The Brown Pedestrian Odometry Dataset (BPOD)David Charatan, Hongyi Fan, Benjamin B. Kimia. 1-11 [doi]
• Long Term Motion Prediction Using KeyposesSena Kiciroglu, Wei Wang 0108, Mathieu Salzmann, Pascal Fua. 12-21 [doi]
• Garment Ideation: Iterative View-Aware Sketch-Based Garment ModelingPinaki Nath Chowdhury, Tuanfeng Y. Wang, Duygu Ceylan, Yi-Zhe Song, Yulia Gryaditskaya. 22-31 [doi]
• Point Discriminative Learning for Data-efficient 3D Point Cloud AnalysisFayao Liu, Guosheng Lin, Chuan-Sheng Foo, Chaitanya K. Joshi, Jie Lin 0001. 42-51 [doi]
• ACDet: Attentive Cross-view Fusion for LiDAR-based 3D Object DetectionJiaolong Xu, Guojun Wang, Xiao Zhang, Guowei Wan. 74-83 [doi]
• ManiFlow: Implicitly Representing Manifolds with Normalizing FlowsJanis Postels, Martin Danelljan, Luc Van Gool, Federico Tombari. 84-93 [doi]
• CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-RepresentationsElona Dupont, Kseniya Cherenkova, Anis Kacem 0001, Sk Aziz Ali, Ilya Arzhannikov, Gleb Gusev, Djamila Aouada. 114-123 [doi]
• Distortion-aware Depth Estimation with Gradient Priors from Panoramas of Indoor ScenesRuihong Yin, Sezer Karaoglu, Theo Gevers. 134-143 [doi]
• SRFeat: Learning Locally Accurate and Globally Consistent Non-Rigid Shape CorrespondenceLei Li 0038, Souhaib Attaiki, Maks Ovsjanikov. 144-154 [doi]
• GNPM: Geometric-Aware Neural Parametric ModelsMirgahney Mohamed, Lourdes Agapito. 166-175 [doi]
• Keypoint Cascade Voting for Point Cloud Based 6DoF Pose EstimationYangzheng Wu, Alireza Javaheri, Mohsen Zand, Michael A. Greenspan. 176-186 [doi]
• There and Back Again: 3D Sign Language Generation from Text Using Back-TranslationStephanie Stoll, Armin Mustafa, Jean-Yves Guillemaut. 187-196 [doi]
• HVTR: Hybrid Volumetric-Textural Rendering for Human AvatarsTao Hu, Tao Yu 0007, Zerong Zheng, He Zhang, Yebin Liu, Matthias Zwicker. 197-208 [doi]
• The Surprising Positive Knowledge Transfer in Continual 3D Object Shape ReconstructionAnh Thai, Stefan Stojanov, Zixuan Huang, James M. Rehg. 209-218 [doi]
• Human Body Measurement Estimation with Adversarial AugmentationNataniel Ruiz, Miriam Bellver, Timo Bolkart, Ambuj Arora, Ming C. Lin, Javier Romero 0002, Raja Bala. 219-230 [doi]
• Progressive Multi-Scale Light Field NetworksDavid Li, Amitabh Varshney. 231-241 [doi]
• MonoNHR: Monocular Neural Human RendererHongsuk Choi, Gyeongsik Moon, Matthieu Armando, Vincent Leroy 0003, Kyoung Mu Lee, Grégory Rogez. 242-251 [doi]
• Domain Adaptive 3D Pose Augmentation for In-the-Wild Human Mesh RecoveryZhenzhen Weng, Kuan-Chieh Wang, Angjoo Kanazawa, Serena Yeung. 261-270 [doi]
• SHRAG: Semantic Hierarchical Graph for Floorplan RepresentationJiongchao Jin, Zhou Xue, Biao Leng. 271-279 [doi]
• SO(3) Rotation Equivariant Point Cloud Completion using Attention-based Vector NeuronsHang Wu, Yubin Miao. 280-290 [doi]
• High-Speed and Low-Latency 3D Sensing with a Parallel-Bus PatternLeo Miyashita, Satoshi Tabata, Masatoshi Ishikawa. 291-300 [doi]
• Articulated 3D Human-Object Interactions From RGB Videos: An Empirical Analysis of Approaches and ChallengesSanjay Haresh, Xiaohao Sun, Hanxiao Jiang 0001, Angel X. Chang, Manolis Savva. 312-321 [doi]
• A Flexible Multi-view Multi-modal Imaging System for Outdoor ScenesMeng Zhang, Wenxuan Guo, Bohao Fan, Yifan Chen, Jianjiang Feng, Jie Zhou 0001. 322-331 [doi]
• Cut-and-Paste Object Insertion by Enabling Deep Image Prior for ReshadingAnand Bhattad, David A. Forsyth. 332-341 [doi]
• 3inGAN: Learning a 3D Generative Model from Images of a Self-similar SceneAnimesh Karnewar, Oliver Wang, Tobias Ritschel 0001, Niloy J. Mitra. 342-352 [doi]
• Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge PriorsXi Wang, Gen Li, Yen-ling Kuo, Muhammed Kocabas, Emre Aksan, Otmar Hilliges. 353-362 [doi]
• Fast Gradient Descent for Surface Capture Via Differentiable RenderingBriac Toussaint, Maxime Genisson, Jean-Sébastien Franco. 373-382 [doi]
• Structure-Aware 3D VR Sketch to 3D Shape RetrievalLing Luo, Yulia Gryaditskaya, Tao Xiang, Yi-Zhe Song. 383-392 [doi]
• Visual Localization via Few-Shot Scene Region ClassificationSiyan Dong, Shuzhe Wang, Yixin Zhuang, Juho Kannala, Marc Pollefeys, Baoquan Chen. 393-402 [doi]
• Robust RGB-D Fusion for Saliency DetectionZongwei Wu, Shriarulmozhivarman Gobichettipalayam, Brahim Tamadazte, Guillaume Allibert, Danda Pani Paudel, Cédric Demonceaux. 403-413 [doi]
• TEACH: Temporal Action Composition for 3D HumansNikos Athanasiou, Mathis Petrovich, Michael J. Black, Gül Varol. 414-423 [doi]
• Temporal Shape Transfer Network for 3D Human MotionJoão Regateiro, Edmond Boyer. 424-432 [doi]
• GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface ReconstructionJingwen Wang, Tymoteusz Bleja, Lourdes Agapito. 433-442 [doi]
• Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image RepresentationsVadim Tschernezki, Iro Laina, Diane Larlus, Andrea Vedaldi. 443-453 [doi]
• Dimensions of Motion: Monocular Prediction through Flow SubspacesRichard Strong Bowen, Richard Tucker 0001, Ramin Zabih, Noah Snavely. 454-464 [doi]
• Arbitrary Point Cloud Upsampling with Spherical Mixture of GaussiansAnthony Dell'Eva, Marco Orsingher, Massimo Bertozzi. 465-474 [doi]
• Guided Co-Modulated GAN for 360° Field of View ExtrapolationMohammad Reza Karimi Dastjerdi, Yannick Hold-Geoffroy, Jonathan Eisenmann, Siavash Khodadadeh, Jean-François Lalonde. 475-485 [doi]
• SDA-SNE: Spatial Discontinuity-Aware Surface Normal Estimation via Multi-Directional Dynamic ProgrammingNan Ming, Yi Feng, Rui Fan. 486-494 [doi]
• Smooth Non-Rigid Shape Matching via Effective Dirichlet Energy OptimizationRobin Magnet, Jing Ren, Olga Sorkine-Hornung, Maks Ovsjanikov. 495-504 [doi]
• Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud ScenesYongqiang Mao, Zonghao Guo, Xiaonan Lu, Zhiqiang Yuan, Haowen Guo. 505-514 [doi]
• PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF TrackingVan Nguyen Nguyen, Yuming Du, Yang Xiao 0007, Michaël Ramamonjisoa, Vincent Lepetit. 515-525 [doi]
• Any-Shot GIN: Generalizing Implicit Networks for Reconstructing Novel ClassesYongqin Xian, Julian Chibane, Bharat Lal Bhatnagar, Bernt Schiele, Zeynep Akata, Gerard Pons-Moll. 526-535 [doi]
• SC6D: Symmetry-agnostic and Correspondence-free 6D Object Pose EstimationDingding Cai, Janne Heikkilä, Esa Rahtu. 536-546 [doi]
• SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud RepresentationZhuo Su 0002, Max Welling, Matti Pietikäinen, Li Liu 0002. 547-556 [doi]
• A Structured Latent Space for Human Body Motion GenerationMathieu Marsot, Stefanie Wuhrer, Jean-Sébastien Franco, Stephane Durocher. 557-566 [doi]
• gCoRF: Generative Compositional Radiance FieldsMallikarjun B. R. 0001, Ayush Tewari, Xingang Pan, Mohamed Elgharib, Christian Theobalt. 567-576 [doi]
• Pose Guided Human Motion Transfer by Exploiting 2D and 3D InformationYahui Zhang, Shaodi You, Sezer Karaoglu, Theo Gevers. 587-595 [doi]
• HoW-3D: Holistic 3D Wireframe Perception from a Single ImageWenchao Ma, Bin Tan, Nan Xue 0001, Tianfu Wu 0001, Xianwei Zheng, Gui-Song Xia. 596-605 [doi]
• Cross-Spectral Neural Radiance FieldsMatteo Poggi, Pierluigi Zama Ramirez, Fabio Tosi, Samuele Salti, Stefano Mattoccia, Luigi di Stefano. 606-616 [doi]
• HybridSDF: Combining Deep Implicit Shapes and Geometric Primitives for 3D Shape Representation and ManipulationSubeesh Vasu, Nicolas Talabot, Artem Lukoianov, Pierre Baqué, Jonathan Donier, Pascal Fua. 617-626 [doi]
• TempCLR: Reconstructing Hands via Time-Coherent Contrastive LearningAndrea Ziani, Zicong Fan, Muhammed Kocabas, Sammy Christen, Otmar Hilliges. 627-636 [doi]
• A Benchmark and a Baseline for Robust Multi-view Depth EstimationPhilipp Schröppel, Jan Bechtold, Artemij Amiranashvili, Thomas Brox. 637-645 [doi]
• MonoViT: Self-Supervised Monocular Depth Estimation with a Vision TransformerChaoqiang Zhao, Youmin Zhang 0008, Matteo Poggi, Fabio Tosi, Xianda Guo, Zheng Zhu, Guan Huang, Yang Tang, Stefano Mattoccia. 668-678 [doi]
• Neural Point-based Shape Modeling of Humans in Challenging ClothingQianli Ma, Jinlong Yang, Michael J. Black, Siyu Tang 0001. 679-689 [doi]
• Polar-Photometric Stereo Under Natural IlluminationYuqi Ding, Yu Ji 0001, Jinwei Ye. 690-699 [doi]
• Interactive Sketching of Mannequin PosesGizem Ünlü, Mohamed Sayed, Gabriel J. Brostow. 700-710 [doi]
• GAN2X: Non-Lambertian Inverse Rendering of Image GANsXingang Pan, Ayush Tewari, Lingjie Liu, Christian Theobalt. 711-721 [doi]
• OoD-Pose: Camera Pose Regression From Out-of-Distribution Synthetic ViewsTony Ng, Adrián López Rodríguez, Vassileios Balntas, Krystian Mikolajczyk. 722-732 [doi]