2.5k citations · 4.8k across the 29 of their papers we have counts for
29 papers
CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-scale Indoor Scene
Haoxiang Chen, Jiahui Huang, Tai-Jiang Mu +1
We present CIRCLE, a framework for large-scale scene completion and geometric refinement based on local implicit signed distance functions. It is based on an end-to-end sparse conv…
Attention Mechanisms in Computer Vision: A Survey
Meng-Hao Guo, Tian-Xing Xu, Jiang-Jiang Liu +7
Humans can naturally and effectively find salient regions in complex scenes. Motivated by this observation, attention mechanisms were introduced into computer vision with the aim o…
Sampling Equivariant Self-attention Networks for Object Detection in Aerial Images
Guo-Ye Yang, Xiang-Li Li, Ralph R. Martin +1
Objects in aerial images have greater variations in scale and orientation than in typical images, so detection is more difficult. Convolutional neural networks use a variety of fre…
Subdivision-Based Mesh Convolution Networks
Shi-Min Hu, Zheng-Ning Liu, Meng-Hao Guo +4
Convolutional neural networks (CNNs) have made great breakthroughs in 2D computer vision. However, their irregular structure makes it hard to harness the potential of CNNs directly…
Can Attention Enable MLPs To Catch Up With CNNs?
Meng-Hao Guo, Zheng-Ning Liu, Tai-Jiang Mu +3
In the first week of May, 2021, researchers from four different institutions: Google, Tsinghua University, Oxford University and Facebook, shared their latest work [16, 7, 12, 17]…
Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks
Meng-Hao Guo, Zheng-Ning Liu, Tai-Jiang Mu +1
Attention mechanisms, especially self-attention, have played an increasingly important role in deep feature representation for visual tasks. Self-attention updates the feature at e…
Recursive-NeRF: An Efficient and Dynamically Growing NeRF
Guo-Wei Yang, Wen-Yang Zhou, Hao-Yang Peng +3
View synthesis methods using implicit continuous shape representations learned from a set of images, such as the Neural Radiance Field (NeRF) method, have gained increasing attenti…
MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization
Jiahui Huang, He Wang, Tolga Birdal +4
We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds. The two non-trivial chal…
PCT: Point cloud transformer
Meng-Hao Guo, Jun-Xiong Cai, Zheng-Ning Liu +3
The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing. This paper presents a novel framework named Point Cloud Tra…
DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors
Jiahui Huang, Shi-Sheng Huang, Haoxuan Song +1
Previous online 3D dense reconstruction methods struggle to achieve the balance between memory storage and surface quality, largely due to the usage of stagnant underlying geometry…
Alternating ConvLSTM: Learning Force Propagation with Alternate State Updates
Congyue Deng, Tai-Jiang Mu, Shi-Min Hu
Data-driven simulation is an important step-forward in computational physics when traditional numerical methods meet their limits. Learning-based simulators have been widely studie…
ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings
Jiahui Huang, Sheng Yang, Tai-Jiang Mu +1
We present ClusterVO, a stereo Visual Odometry which simultaneously clusters and estimates the motion of both ego and surrounding rigid clusters/objects. Unlike previous solutions…
Shallow2Deep: Indoor Scene Modeling by Single Image Understanding
Yinyu Nie, Shihui Guo, Jian Chang +4
Dense indoor scene modeling from 2D images has been bottlenecked due to the absence of depth information and cluttered occlusions. We present an automatic indoor scene modeling app…
Morphing and Sampling Network for Dense Point Cloud Completion
Minghua Liu, Lu Sheng, Sheng Yang +2
3D point cloud completion, the task of inferring the complete geometric shape from a partial point cloud, has been attracting attention in the community. For acquiring high-fidelit…
Example-Guided Style Consistent Image Synthesis from Semantic Labeling
Miao Wang, Guo-Ye Yang, Ruilong Li +4
Example-guided image synthesis aims to synthesize an image from a semantic label map and an exemplary image indicating style. We use the term "style" in this problem to refer to im…
FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing
Sen-Zhe Xu, Hao-Zhi Huang, Shi-Min Hu +1
Existing methods for face image manipulation generally focus on editing the expression, changing some predefined attributes, or applying different filters. However, users lack the…
What and Where: A Context-based Recommendation System for Object Insertion
Song-Hai Zhang, Zhengping Zhou, Bin Liu +4
In this work, we propose a novel topic consisting of two dual tasks: 1) given a scene, recommend objects to insert, 2) given an object category, retrieve suitable background scenes…
TZC: Efficient Inter-Process Communication for Robotics Middleware with Partial Serialization
Yu-Ping Wang, Wende Tan, Xu-Qiang Hu +2
Inter-process communication (IPC) is one of the core functions of modern robotics middleware. We propose an efficient IPC technique called TZC (Towards Zero-Copy). As a core compon…
Temporally Coherent Video Harmonization Using Adversarial Networks
Haozhi Huang, Senzhe Xu, Junxiong Cai +2
Compositing is one of the most important editing operations for images and videos. The process of improving the realism of composite results is often called harmonization. Previous…
Deep Portrait Image Completion and Extrapolation
Xian Wu, Rui-Long Li, Fang-Lue Zhang +4
General image completion and extrapolation methods often fail on portrait images where parts of the human body need to be recovered - a task that requires accurate human body struc…
LineNet: a Zoomable CNN for Crowdsourced High Definition Maps Modeling in Urban Environments
Dun Liang, Yuanchen Guo, Shaokui Zhang +4
High Definition (HD) maps play an important role in modern traffic scenes. However, the development of HD maps coverage grows slowly because of the cost limitation. To efficiently…
Pose2Seg: Detection Free Human Instance Segmentation
Song-Hai Zhang, Ruilong Li, Xin Dong +6
The standard approach to image instance segmentation is to perform the object detection first, and then segment the object from the detection bounding-box. More recently, deep lear…
Chinese Text in the Wild
Tai-Ling Yuan, Zhe Zhu, Kun Xu +2
We introduce Chinese Text in the Wild, a very large dataset of Chinese text in street view images. While optical character recognition (OCR) in document images is well studied and…
Deep Online Video Stabilization
Miao Wang, Guo-Ye Yang, Jin-Kun Lin +4
Video stabilization technique is essential for most hand-held captured videos due to high-frequency shakes. Several 2D-, 2.5D- and 3D-based stabilization techniques are well studie…