1k citations · 3.4k across the 83 of their papers we have counts for
61 papers · 1 filter
Downstream-agnostic Adversarial Examples
Ziqi Zhou, Shengshan Hu, Ruizhi Zhao +4
Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users…
Enhancing Low-light Light Field Images with A Deep Compensation Unfolding Network
Xianqiang Lyu, Junhui Hou
This paper presents a novel and interpretable end-to-end learning framework, called the deep compensation unfolding network (DCUNet), for restoring light field (LF) images captured…
Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackers
Zhiyu Zhu, Junhui Hou, Dapeng Oliver Wu
This paper addresses the problem of cross-modal object tracking from RGB videos and event data. Rather than constructing a complex cross-modal fusion network, we explore the great…
Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection
Yifan Zhang, Zhiyu Zhu, Junhui Hou +1
The Detection Transformer (DETR) has revolutionized the design of CNN-based object detection systems, showcasing impressive performance. However, its potential in the domain of mul…
NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries
Qijian Zhang, Junhui Hou, Yohanes Yudhi Adikusuma +2
Geodesics are essential in many geometry processing applications. However, traditional algorithms for computing geodesic distances and paths on 3D mesh models are often inefficient…
Unleash the Potential of 3D Point Cloud Modeling with A Calibrated Local Geometry-driven Distance Metric
Siyu Ren, Junhui Hou
Quantifying the dissimilarity between two unstructured 3D point clouds is a challenging task, with existing metrics often relying on measuring the distance between corresponding po…
Decoupling Dynamic Monocular Videos for Dynamic View Synthesis
Meng You, Junhui Hou
The challenge of dynamic view synthesis from dynamic monocular videos, i.e., synthesizing novel views for free viewpoints given a monocular video of a dynamic scene captured by a m…
Unleash the Potential of Image Branch for Cross-modal 3D Object Detection
Yifan Zhang, Qijian Zhang, Junhui Hou +2
To achieve reliable and precise scene understanding, autonomous vehicles typically incorporate multiple sensing modalities to capitalize on their complementary attributes. However,…
Deep Diversity-Enhanced Feature Representation of Hyperspectral Images
Jinhui Hou, Zhiyu Zhu, Junhui Hou +3
In this paper, we study the problem of efficiently and effectively embedding the high-dimensional spatio-spectral information of hyperspectral (HS) images, guided by feature divers…
PointVST: Self-Supervised Pre-training for 3D Point Clouds via View-Specific Point-to-Image Translation
Qijian Zhang, Junhui Hou
The past few years have witnessed the great success and prevalence of self-supervised representation learning within the language and 2D vision communities. However, such advanceme…
Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis
Qijian Zhang, Junhui Hou, Yue Qian +3
Point clouds are characterized by irregularity and unstructuredness, which pose challenges in efficient data exploitation and discriminative feature extraction. In this paper, we p…
Leveraging Single-View Images for Unsupervised 3D Point Cloud Completion
Lintai Wu, Qijian Zhang, Junhui Hou +1
Point clouds captured by scanning devices are often incomplete due to occlusion. To overcome this limitation, point cloud completion methods have been developed to predict the comp…
PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples
Shengshan Hu, Junwei Zhang, Wei Liu +5
Point cloud completion, as the upstream procedure of 3D recognition and segmentation, has become an essential part of many tasks such as navigation and scene understanding. While v…
GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation
Siyu Ren, Junhui Hou, Xiaodong Chen +2
We present a learning-based method, namely GeoUDF,to tackle the long-standing and challenging problem of reconstructing a discrete surface from a sparse point cloud.To be specific,…
Learning A Locally Unified 3D Point Cloud for View Synthesis
Meng You, Mantang Guo, Xianqiang Lyu +2
In this paper, we explore the problem of 3D point cloud representation-based view synthesis from a set of sparse source views. To tackle this challenging problem, we propose a new…
CorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondence
Siyu Ren, Yiming Zeng, Junhui Hou +1
Motivated by the intuition that the critical step of localizing a 2D image in the corresponding 3D point cloud is establishing 2D-3D correspondence between them, we propose the fir…
PointMCD: Boosting Deep Point Cloud Encoders via Multi-view Cross-modal Distillation for 3D Shape Recognition
Qijian Zhang, Junhui Hou, Yue Qian
As two fundamental representation modalities of 3D objects, 3D point clouds and multi-view 2D images record shape information from different domains of geometric structures and vis…
GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation
Yifan Zhang, Qijian Zhang, Zhiyu Zhu +2
The inherent ambiguity in ground-truth annotations of 3D bounding boxes, caused by occlusions, signal missing, or manual annotation errors, can confuse deep 3D object detectors dur…
Occlusion-Resistant Instance Segmentation of Piglets in Farrowing Pens Using Center Clustering Network
Endai Huang, Axiu Mao, Junhui Hou +5
Computer vision enables the development of new approaches to monitor the behavior, health, and welfare of animals. Instance segmentation is a high-precision method in computer visi…
Deep Posterior Distribution-based Embedding for Hyperspectral Image Super-resolution
Jinhui Hou, Zhiyu Zhu, Junhui Hou +3
In this paper, we investigate the problem of hyperspectral (HS) image spatial super-resolution via deep learning. Particularly, we focus on how to embed the high-dimensional spatia…
Semi-Supervised Subspace Clustering via Tensor Low-Rank Representation
Yuheng Jia, Guanxing Lu, Hui Liu +1
In this letter, we propose a novel semi-supervised subspace clustering method, which is able to simultaneously augment the initial supervisory information and construct a discrimin…
WarpingGAN: Warping Multiple Uniform Priors for Adversarial 3D Point Cloud Generation
Yingzhi Tang, Yue Qian, Qijian Zhang +3
We propose WarpingGAN, an effective and efficient 3D point cloud generation network. Unlike existing methods that generate point clouds by directly learning the mapping functions b…
IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment
Yiming Zeng, Yue Qian, Qijian Zhang +3
This paper investigates the problem of temporally interpolating dynamic 3D point clouds with large non-rigid deformation. We formulate the problem as estimation of point-wise traje…
PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling
Hao Liu, Hui Yuan, Junhui Hou +2
We propose a generative adversarial network for point cloud upsampling, which can not only make the upsampled points evenly distributed on the underlying surface but also efficient…