Depth completion has attracted extensive attention recently due to the development of autonomous driving, which aims to recover dense depth map from sparse depth measurements. Convolutional spatial propagation network (CSPN) is one of the state-of-the-art methods in this task, which adopt a linear propagation model to refine coarse depth maps with local context. However, the propagation of each pixel occurs in a fixed receptive field. This may not be the optimal for refinement since different pixel needs different local context. To tackle this issue, in this paper, we propose a deformable spatial propagation network (DSPN) to adaptively generates different receptive field and affinity matrix for each pixel. It allows the network obtain information with much fewer but more relevant pixels for propagation. Experimental results on KITTI depth completion benchmark demonstrate that our proposed method achieves the state-of-the-art performance.
Learning Temporal 3D Semantic Scene Completion via Optical Flow Guidance
College of Computer Science and Electronic Engineering, Hunan University（湖南大学计算机科学与电子工程学院）；State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle, Hunan University（车辆先进设计与制造技术国家重点实验室）
SoftVTBench: A Safety-Aware Visuo-Tactile Benchmark for Physically Constrained Robotic Manipulation of Deformable Objects (Early Version)
Tuojing Intelligence（拓景智能）；Tsinghua University（清华大学）；King’s College London（伦敦国王学院）；Southeast University（东南大学）；Stevens Institute of Technology（史蒂文斯理工学院）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；University of Manchester（曼彻斯特大学）；Simple AI（简单人工智能公司）；Imperial College London（伦敦帝国学院）；Carnegie Mellon University（卡内基梅隆大学）；Zhejiang University（浙江大学）；Beihang University（北京航空航天大学）；The University of Hong Kong（香港大学）
VOIC: Visible-Occluded Integrated Guidance for 3D Semantic Scene Completion
Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology（可信自主系统研究院，南方科技大学）；Department of Computer Science and Engineering, Southern University of Science and Technology（计算机科学与工程系，南方科技大学）；School of Computer Science, University of Nottingham Ningbo China（宁波大学计算机学院）；Department of Electronic and Information Engineering, Changchun University（电子与信息工程学院，长春大学）
Tri-Perspective View Decomposition for Geometry-Aware Depth Completion
Nanjing University of Science and Technology（南京理工大学）；Huazhong University of Science and Technology（华中科技大学）；Chinese Academy of Sciences（中国科学院）；Northwestern Polytechnical University（西北工业大学）
Non-Local Spatial Propagation Network for Depth Completion
Korea Advanced Institute of Science and Technology（韩国科学技术院）；Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）；Hikvision Research America（海康威视美国研究院）
Dynamic Spatial Propagation Network for Depth Completion
Huazhong University of Science and Technology（华中科技大学）；Shenzhen Technology University（深圳技术大学）；Tsinghua University（清华大学）；The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））
Deformable Kernel Convolutional Network for Video Extreme Super-Resolution
West Virginia University（西弗吉尼亚大学）；Huazhong University of Science and Technology（华中科技大学）
视频超分辨率是一种将低分辨率视频帧重构为高分辨率视频帧的技术，近年来受到越来越多的关注。大多数现有方法选择使用可变形卷积来在时间上对齐相邻帧，并应用传统的空间注意力机制（基于卷积）来增强重构特征。然而，这种仅空间的策略不能充分利用视频帧之间的时间依赖性。在本文中，我们提出了一种新的深度学习为基础的VSR算法，命名为变形核空间注意力网络（DKSAN）。由于新设计的可变形核卷积对齐（DKC_Align）和可变形核空间注意力（DKSA）模块，DKSAN可以更好地利用空间和时间冗余，以促进跨不同层的信息传播。我们已经在AIM 2020 Video Extreme超分辨率挑战赛上测试了DKSAN，以获得比例因子高达16的超分辨率视频。实验结果表明，我们提出的DKSAN可以实现更好的主观和客观的性能相比，现有的最先进的EDVR的Vid3oC和IntVID数据集。
Scale Propagation Network for Generalizable Depth Completion
Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（西安交通大学人工智能与机器人研究所）；Intelligent Transportation Thrust of the Systems Hub, Hong Kong University of Science and Technology (GZ)（香港科技大学（广州）系统枢纽智能交通方向）；Multimodal Experiences Lab, Dolby Laboratories Inc（杜比实验室公司多模态体验实验室）
Propagating Sparse Depth via Depth Foundation Model for Out-of-Distribution Depth Completion
Dalian University of Technology（大连理工大学）；Beihang University（北京航空航天大学）；College of Computer Science and Engineering, Shandong University of Science and Technology（山东科技大学计算机科学与工程学院）
Continuous sPatial-Temporal Deformable Image Registration (CPT-DIR) for motion modelling in radiotherapy: beyond classic voxel-based methods
Center for Proton Therapy, Paul Scherrer Institut（保罗·施特格研究所质子治疗中心）；Department of Computer Science, ETH Zürich（苏黎世联邦理工学院计算机科学系）；Department of Physics, ETH Zürich（苏黎世联邦理工学院物理系）；Department of Automation, Tsinghua Univeristy（清华大学自动化系）；S-Lab, Nanyang Technological University（南洋理工大学S实验室）
EfficientPENet: Real-Time Depth Completion from Sparse LiDAR via Lightweight Multi-Modal Fusion
Canizaro Livingston Gulf States Center for Environmental Informatics, the University of New Orleans, New Orleans, USA（Canizaro Livingston Gulf States环境信息中心，新奥尔良大学，美国新奥尔良）；US Army Corps of Engineers, Engineer Research and Development Center, Vicksburg, Mississippi, USA（美国陆军工程兵团，工程师研究与发展中心，密西西比州维克斯堡，美国）
ToFormer: Towards Large-scale Scenario Depth Completion for Lightweight ToF Camera
State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, Zhejiang University, Hangzhou, China（浙江大学工业控制技术状态重点实验室，系统与控制研究所，杭州，中国）；Huzhou Institute of Zhejiang University, Huzhou, China（浙江大学湖州研究院，湖州，中国）；The Chinese University of Hong Kong, Shenzhen, China（香港中文大学（深圳））
