Search Results for author: Junhui Hou

Found 99 papers, 61 papers with code

DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstruction

no code implementations18 Mar 2024 Yuxin Yao, Siyu Ren, Junhui Hou, Zhi Deng, Juyong Zhang, Wenping Wang

Furthermore, we propose a learnable deformation representation based on the learnable control points and blending weights, which can deform the template surface non-rigidly while maintaining the consistency of the local shape.

Surface Reconstruction

ParaPoint: Learning Global Free-Boundary Surface Parameterization of 3D Point Clouds

no code implementations15 Mar 2024 Qijian Zhang, Junhui Hou, Ying He

To the best of our knowledge, this work makes the first attempt to investigate neural point cloud parameterization that pursues both global mappings and free boundaries.

Superpixel Graph Contrastive Clustering with Semantic-Invariant Augmentations for Hyperspectral Images

no code implementations4 Mar 2024 Jianhan Qi, Yuheng Jia, Hui Liu, Junhui Hou

The state-of-the-art (SOTA) methods usually rely on superpixels, however, they do not fully utilize the spatial and spectral information in HSI 3-D structure, and their optimization targets are not clustering-oriented.

Clustering Contrastive Learning +1

Towards Calibrated Deep Clustering Network

no code implementations4 Mar 2024 Yuheng Jia, Jianhong Cheng, Hui Liu, Junhui Hou

Deep clustering has exhibited remarkable performance; however, the overconfidence problem, i. e., the estimated confidence for a sample belonging to a particular cluster greatly exceeds its actual prediction accuracy, has been overlooked in prior research.

Clustering Deep Clustering

Dynamic 3D Point Cloud Sequences as 2D Videos

no code implementations2 Mar 2024 Yiming Zeng, Junhui Hou, Qijian Zhang, Siyu Ren, Wenping Wang

The structured nature of our SPCV representation allows for the seamless adaptation of well-established 2D image/video techniques, enabling efficient and effective processing and analysis of 3D point cloud sequences.

Action Recognition Self-Supervised Learning

Unsupervised Learning of High-resolution Light Field Imaging via Beam Splitter-based Hybrid Lenses

no code implementations29 Feb 2024 Jianxin Lei, Chengcai Xu, Langqing Shi, Junhui Hou, Ping Zhou

In this paper, we design a beam splitter-based hybrid light field imaging prototype to record 4D light field image and high-resolution 2D image simultaneously, and make a hybrid light field dataset.

Super-Resolution

Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration

no code implementations23 Jan 2024 Yifan Zhang, Siyu Ren, Junhui Hou, Jinjian Wu, Guangming Shi

First, we propose the learnable transformation alignment to bridge the domain gap between image and point cloud data, converting features into a unified representation space for effective comparison and matching.

3D Semantic Segmentation Autonomous Driving +4

3D Shape Completion on Unseen Categories:A Weakly-supervised Approach

no code implementations19 Jan 2024 Lintai Wu, Junhui Hou, Linqi Song, Yong Xu

Specifically, we construct a prior bank consisting of representative shapes from the seen categories.

Measuring the Discrepancy between 3D Geometric Models using Directional Distance Fields

no code implementations18 Jan 2024 Siyu Ren, Junhui Hou, Xiaodong Chen, Hongkai Xiong, Wenping Wang

We then transfer the discrepancy between two 3D geometric models as the discrepancy between their DDFs defined on an identical domain, naturally establishing model correspondence.

Scene Flow Estimation

On Optimal Sampling for Learning SDF Using MLPs Equipped with Positional Encoding

no code implementations2 Jan 2024 Guying Lin, Lei Yang, YuAn Liu, Congyi Zhang, Junhui Hou, Xiaogang Jin, Taku Komura, John Keyser, Wenping Wang

Sampling against this intrinsic frequency following the Nyquist-Sannon sampling theorem allows us to determine an appropriate training sampling rate.

Segment Any Events via Weighted Adaptation of Pivotal Tokens

1 code implementation24 Dec 2023 Zhiwen Chen, Zhiyu Zhu, Yifan Zhang, Junhui Hou, Guangming Shi, Jinjian Wu

One pivotal issue at the heart of this endeavor is the precise alignment and calibration of embeddings derived from event-centric data such that they harmoniously coincide with those originating from RGB imagery.

Event-based Object Segmentation

Cross-BERT for Point Cloud Pretraining

no code implementations8 Dec 2023 Xin Li, Peng Li, Zeyong Wei, Zhe Zhu, Mingqiang Wei, Junhui Hou, Liangliang Nan, Jing Qin, Haoran Xie, Fu Lee Wang

By performing cross-modal interaction, Cross-BERT can smoothly reconstruct the masked tokens during pretraining, leading to notable performance enhancements for downstream tasks.

Self-Supervised Learning

Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Images

1 code implementation6 Nov 2023 Yingzhi Tang, Qijian Zhang, Junhui Hou, Yebin Liu

The latest trends in the research field of single-view human reconstruction devote to learning deep implicit functions constrained by explicit body shape priors.

3D Human Reconstruction

Global Structure-Aware Diffusion Process for Low-Light Image Enhancement

1 code implementation NeurIPS 2023 Jinhui Hou, Zhiyu Zhu, Junhui Hou, Hui Liu, Huanqiang Zeng, Hui Yuan

To harness the capabilities of diffusion models, we delve into this intricate process and advocate for the regularization of its inherent ODE-trajectory.

Low-Light Image Enhancement

Enhancing Low-light Light Field Images with A Deep Compensation Unfolding Network

1 code implementation10 Aug 2023 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 under low-light conditions.

Downstream-agnostic Adversarial Examples

1 code implementation ICCV 2023 Ziqi Zhou, Shengshan Hu, Ruizhi Zhao, Qian Wang, Leo Yu Zhang, Junhui Hou, Hai Jin

AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder.

Self-Supervised Learning

Spatial-Temporal Enhanced Transformer Towards Multi-Frame 3D Object Detection

1 code implementation1 Jul 2023 Yifan Zhang, Zhiyu Zhu, Junhui Hou, Dapeng Wu

Specifically, to model the inter-object spatial interaction and complex temporal dependencies, we introduce the spatial-temporal graph attention network, which represents queries as nodes in a graph and enables effective modeling of object interactions within a social context.

3D Object Detection Graph Attention +2

Probabilistic-based Feature Embedding of 4-D Light Fields for Compressive Imaging and Denoising

1 code implementation15 Jun 2023 Xianqiang Lyu, Junhui Hou

The high-dimensional nature of the 4-D light field (LF) poses great challenges in achieving efficient and effective feature embedding, that severely impacts the performance of downstream tasks.

Denoising

NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries

1 code implementation NeurIPS 2023 Qijian Zhang, Junhui Hou, Yohanes Yudhi Adikusuma, Wenping Wang, Ying He

To bridge this gap, this paper presents the first attempt to represent geodesics on 3D mesh models using neural implicit functions.

Unleash the Potential of 3D Point Cloud Modeling with A Calibrated Local Geometry-driven Distance Metric

1 code implementation1 Jun 2023 Siyu Ren, Junhui Hou

By associating each reference point with two given point clouds through computing its directional distances to them, the difference in directional distances of an identical reference point characterizes the geometric difference between a typical local region of the two point clouds.

Scene Flow Estimation

Decoupling Dynamic Monocular Videos for Dynamic View Synthesis

no code implementations4 Apr 2023 Meng You, Junhui Hou

Such a fine-grained motion formulation can alleviate the learning difficulty for the network, thus enabling it to produce not only novel views with higher quality but also more accurate scene flows and depth than existing methods requiring extra supervision.

Optical Flow Estimation

GQE-Net: A Graph-based Quality Enhancement Network for Point Cloud Color Attribute

1 code implementation24 Mar 2023 Jinrui Xing, Hui Yuan, Raouf Hamzaoui, Hao liu, Junhui Hou

To reduce color distortion in point clouds, we propose a graph-based quality enhancement network (GQE-Net) that uses geometry information as an auxiliary input and graph convolution blocks to extract local features efficiently.

Attribute Graph Attention

Unleash the Potential of Image Branch for Cross-modal 3D Object Detection

1 code implementation NeurIPS 2023 Yifan Zhang, Qijian Zhang, Junhui Hou, Yixuan Yuan, Guoliang Xing

To achieve reliable and precise scene understanding, autonomous vehicles typically incorporate multiple sensing modalities to capitalize on their complementary attributes.

3D Object Detection Autonomous Vehicles +2

Deep Diversity-Enhanced Feature Representation of Hyperspectral Images

1 code implementation15 Jan 2023 Jinhui Hou, Zhiyu Zhu, Junhui Hou, Hui Liu, Huanqiang Zeng, Deyu Meng

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 diversity.

Denoising Super-Resolution

PointVST: Self-Supervised Pre-training for 3D Point Clouds via View-Specific Point-to-Image Translation

1 code implementation29 Dec 2022 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.

Contrastive Learning Image Generation +3

A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attacks

1 code implementation20 Dec 2022 Yifan Zhang, Junhui Hou, Yixuan Yuan

Specifically, we extend three distinct adversarial attacks to the 3D object detection task, benchmarking the robustness of state-of-the-art LiDAR-based 3D object detectors against attacks on the KITTI and Waymo datasets.

3D Object Detection Benchmarking +2

Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis

1 code implementation17 Dec 2022 Qijian Zhang, Junhui Hou, Yue Qian, Yiming Zeng, Juyong Zhang, Ying He

In this paper, we present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology as a completely regular 2D point geometry image (PGI) structure, in which coordinates of spatial points are captured in colors of image pixels.

Leveraging Single-View Images for Unsupervised 3D Point Cloud Completion

1 code implementation1 Dec 2022 Lintai Wu, Qijian Zhang, Junhui Hou, Yong Xu

The experimental results of our method are superior to those of the state-of-the-art unsupervised methods by a large margin.

Point Cloud Completion

GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation

1 code implementation ICCV 2023 Siyu Ren, Junhui Hou, Xiaodong Chen, Ying He, Wenping Wang

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, we propose a geometry-guided learning method for UDF and its gradient estimation that explicitly formulates the unsigned distance of a query point as the learnable affine averaging of its distances to the tangent planes of neighboring points on the surface.

Surface Reconstruction

PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples

no code implementations22 Nov 2022 Shengshan Hu, Junwei Zhang, Wei Liu, Junhui Hou, Minghui Li, Leo Yu Zhang, Hai Jin, Lichao Sun

In addition, existing attack approaches towards point cloud classifiers cannot be applied to the completion models due to different output forms and attack purposes.

Adversarial Attack Point Cloud Classification +2

EGRC-Net: Embedding-induced Graph Refinement Clustering Network

1 code implementation19 Nov 2022 Zhihao Peng, Hui Liu, Yuheng Jia, Junhui Hou

To begin, we leverage both semantic and topological information by employing a vanilla auto-encoder and a graph convolution network, respectively, to learn a latent feature representation.

Clustering Graph Clustering

Learning A Locally Unified 3D Point Cloud for View Synthesis

1 code implementation12 Sep 2022 Meng You, Mantang Guo, Xianqiang Lyu, Hui Liu, Junhui Hou

To tackle this challenging problem, we propose a new deep learning-based view synthesis paradigm that learns a locally unified 3D point cloud from source views.

Image Restoration

Ecsnet: Spatio-temporal feature learning for event camera

1 code implementation IEEE Transactions on Circuits and Systems for Video Technology 2022 Zhiwen Chen, Jinjian Wu, Junhui Hou, Leida Li, Weisheng Dong, Guangming Shi

To fully exploit their inherent sparsity with reconciling the spatio-temporal information, we introduce a compact event representation, namely 2D-1T event cloud sequence (2D-1T ECS).

Action Recognition Event-based vision +2

CorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondence

1 code implementation12 Jul 2022 Siyu Ren, Yiming Zeng, Junhui Hou, Xiaodong Chen

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 first feature-based dense correspondence framework for addressing the image-to-point cloud registration problem, dubbed CorrI2P, which consists of three modules, i. e., feature embedding, symmetric overlapping region detection, and pose estimation through the established correspondence.

Image to Point Cloud Registration Pose Estimation

PointMCD: Boosting Deep Point Cloud Encoders via Multi-view Cross-modal Distillation for 3D Shape Recognition

1 code implementation7 Jul 2022 Qijian Zhang, Junhui Hou, Yue Qian

In this paper, we explore the possibility of boosting deep 3D point cloud encoders by transferring visual knowledge extracted from deep 2D image encoders under a standard teacher-student distillation workflow.

3D Shape Classification 3D Shape Recognition +1

GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation

1 code implementation6 Jul 2022 Yifan Zhang, Qijian Zhang, Zhiyu Zhu, Junhui Hou, Yixuan Yuan

The label uncertainty generated by GLENet is a plug-and-play module and can be conveniently integrated into existing deep 3D detectors to build probabilistic detectors and supervise the learning of the localization uncertainty.

3D Object Detection

Occlusion-Resistant Instance Segmentation of Piglets in Farrowing Pens Using Center Clustering Network

no code implementations4 Jun 2022 Endai Huang, Axiu Mao, Junhui Hou, Yongjian Wu, Weitao Xu, Maria Camila Ceballos, Thomas D. Parsons, Kai Liu

Specifically, CClusnet-Inseg uses each pixel to predict object centers and trace these centers to form masks based on clustering results, which consists of a network for segmentation and center offset vector map, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, Centers-to-Mask (C2M), and Remain-Centers-to-Mask (RC2M) algorithms.

Clustering Instance Segmentation +4

Deep Posterior Distribution-based Embedding for Hyperspectral Image Super-resolution

1 code implementation30 May 2022 Jinhui Hou, Zhiyu Zhu, Junhui Hou, Huanqiang Zeng, Jinjian Wu, Jiantao Zhou

Then, we incorporate the proposed feature embedding scheme into a source-consistent super-resolution framework that is physically-interpretable, producing lightweight PDE-Net, in which high-resolution (HR) HS images are iteratively refined from the residuals between input low-resolution (LR) HS images and pseudo-LR-HS images degenerated from reconstructed HR-HS images via probability-inspired HS embedding.

Hyperspectral Image Super-Resolution Image Super-Resolution

Semi-Supervised Subspace Clustering via Tensor Low-Rank Representation

1 code implementation21 May 2022 Yuheng Jia, Guanxing Lu, Hui Liu, Junhui Hou

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 discriminative affinity matrix.

Clustering

Light Field Depth Estimation via Stitched Epipolar Plane Images

1 code implementation29 Mar 2022 Ping Zhou, Langqing Shi, Xiaoyang Liu, Jing Jin, Yuting Zhang, Junhui Hou

This strategy involves determining the depth of such regions by progressing from the edges towards the interior, prioritizing accurate regions over coarse regions.

Depth Estimation

IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment

1 code implementation CVPR 2022 Yiming Zeng, Yue Qian, Qijian Zhang, Junhui Hou, Yixuan Yuan, Ying He

This paper investigates the problem of temporally interpolating dynamic 3D point clouds with large non-rigid deformation.

3D Point Cloud Interpolation

PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling

no code implementations2 Mar 2022 Hao liu, Hui Yuan, Junhui Hou, Raouf Hamzaoui, Wei Gao

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 efficiently generate clean high frequency regions.

Descriptive Generative Adversarial Network

Content-aware Warping for View Synthesis

1 code implementation22 Jan 2022 Mantang Guo, Junhui Hou, Jing Jin, Hui Liu, Huanqiang Zeng, Jiwen Lu

To this end, we propose content-aware warping, which adaptively learns the interpolation weights for pixels of a relatively large neighborhood from their contextual information via a lightweight neural network.

Novel View Synthesis

Deep Attention-guided Graph Clustering with Dual Self-supervision

1 code implementation10 Nov 2021 Zhihao Peng, Hui Liu, Yuheng Jia, Junhui Hou

Existing deep embedding clustering works only consider the deepest layer to learn a feature embedding and thus fail to well utilize the available discriminative information from cluster assignments, resulting performance limitation.

Clustering Deep Attention +1

Adaptive Attribute and Structure Subspace Clustering Network

1 code implementation28 Sep 2021 Zhihao Peng, Hui Liu, Yuheng Jia, Junhui Hou

In this paper, we propose a novel adaptive attribute and structure subspace clustering network (AASSC-Net) to simultaneously consider the attribute and structure information in an adaptive graph fusion manner.

Attribute Clustering

Superpixel-guided Discriminative Low-rank Representation of Hyperspectral Images for Classification

1 code implementation25 Aug 2021 Shujun Yang, Junhui Hou, Yuheng Jia, Shaohui Mei, Qian Du

Specifically, by utilizing the local spatial information and incorporating the predictions from a typical classifier, the first module segments pixels of an input HSI (or its restoration generated by the second module) into superpixels.

Superpixels

Learning Dynamic Interpolation for Extremely Sparse Light Fields with Wide Baselines

1 code implementation ICCV 2021 Mantang Guo, Jing Jin, Hui Liu, Junhui Hou

In this paper, we tackle the problem of dense light field (LF) reconstruction from sparsely-sampled ones with wide baselines and propose a learnable model, namely dynamic interpolation, to replace the commonly-used geometry warping operation.

SSIM

Semantic-embedded Unsupervised Spectral Reconstruction from Single RGB Images in the Wild

1 code implementation ICCV 2021 Zhiyu Zhu, Hui Liu, Junhui Hou, Huanqiang Zeng, Qingfu Zhang

Specifically, on the basis of the intrinsic imaging degradation model of RGB images from HS images, we progressively spread the differences between input RGB images and re-projected RGB images from recovered HS images via effective unsupervised camera spectral response function estimation.

Image Reconstruction Spectral Reconstruction +1

Deep Amended Gradient Descent for Efficient Spectral Reconstruction from Single RGB Images

1 code implementation12 Aug 2021 Zhiyu Zhu, Hui Liu, Junhui Hou, Sen Jia, Qingfu Zhang

Then, we design a lightweight neural network with a multi-stage architecture to mimic the formed amended gradient descent process, in which efficient convolution and novel spectral zero-mean normalization are proposed to effectively extract spatial-spectral features for regressing an initialization, a basic gradient, and an incremental gradient.

Spectral Reconstruction

Attention-driven Graph Clustering Network

2 code implementations12 Aug 2021 Zhihao Peng, Hui Liu, Yuheng Jia, Junhui Hou

The combination of the traditional convolutional network (i. e., an auto-encoder) and the graph convolutional network has attracted much attention in clustering, in which the auto-encoder extracts the node attribute feature and the graph convolutional network captures the topological graph feature.

Attribute Clustering +2

PU-Flow: a Point Cloud Upsampling Network with Normalizing Flows

1 code implementation13 Jul 2021 Aihua Mao, Zihui Du, Junhui Hou, Yaqi Duan, Yong-Jin Liu, Ying He

Point cloud upsampling aims to generate dense point clouds from given sparse ones, which is a challenging task due to the irregular and unordered nature of point sets.

Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restoration

no code implementations13 Jul 2021 Jie Chen, Zaifeng Yang, Tsz Nam Chan, Hui Li, Junhui Hou, Lap-Pui Chau

A progressive texture blending module is designed to blend the encoded two-stream features in a multi-scale and progressive manner.

Image Restoration Vocal Bursts Intensity Prediction

Occlusion-aware Unsupervised Learning of Depth from 4-D Light Fields

1 code implementation6 Jun 2021 Jing Jin, Junhui Hou

Experimental results on synthetic data show that our method can significantly shrink the performance gap between the previous unsupervised method and supervised ones, and produce depth maps with comparable accuracy to traditional methods with obviously reduced computational cost.

Depth Estimation Depth Prediction

Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding

5 code implementations27 Apr 2021 Chongyi Li, Saeed Anwar, Junhui Hou, Runmin Cong, Chunle Guo, Wenqi Ren

As a result, our network can effectively improve the visual quality of underwater images by exploiting multiple color spaces embedding and the advantages of both physical model-based and learning-based methods.

Ranked #2 on Underwater Image Restoration on LSUI (using extra training data)

Image Enhancement Underwater Image Restoration

Self-supervised Symmetric Nonnegative Matrix Factorization

1 code implementation2 Mar 2021 Yuheng Jia, Hui Liu, Junhui Hou, Sam Kwong, Qingfu Zhang

Inspired by ensemble clustering that aims to seek a better clustering result from a set of clustering results, we propose self-supervised SNMF (S$^3$NMF), which is capable of boosting clustering performance progressively by taking advantage of the sensitivity to initialization characteristic of SNMF, without relying on any additional information.

Clustering

Light Field Reconstruction via Deep Adaptive Fusion of Hybrid Lenses

1 code implementation14 Feb 2021 Jing Jin, Mantang Guo, Junhui Hou, Hui Liu, Hongkai Xiong

Besides, to promote the effectiveness of our method trained with simulated hybrid data on real hybrid data captured by a hybrid LF imaging system, we carefully design the network architecture and the training strategy.

CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds

1 code implementation CVPR 2021 Yiming Zeng, Yue Qian, Zhiyu Zhu, Junhui Hou, Hui Yuan, Ying He

The symmetric deformer, with an additional regularized loss, transforms the two permuted point clouds to each other to drive the unsupervised learning of the correspondence.

Ranked #6 on 3D Dense Shape Correspondence on SHREC'19 (using extra training data)

3D Dense Shape Correspondence

Clustering Ensemble Meets Low-rank Tensor Approximation

1 code implementation16 Dec 2020 Yuheng Jia, Hui Liu, Junhui Hou, Qingfu Zhang

The existing clustering ensemble methods generally construct a co-association matrix, which indicates the pairwise similarity between samples, as the weighted linear combination of the connective matrices from different base clusterings, and the resulting co-association matrix is then adopted as the input of an off-the-shelf clustering algorithm, e. g., spectral clustering.

Clustering Clustering Ensemble

Maximum Entropy Subspace Clustering Network

2 code implementations6 Dec 2020 Zhihao Peng, Yuheng Jia, Hui Liu, Junhui Hou, Qingfu Zhang

Furthermore, we design a novel framework to explicitly decouple the auto-encoder module and the self-expressiveness module.

Clustering

ParaNet: Deep Regular Representation for 3D Point Clouds

no code implementations5 Dec 2020 Qijian Zhang, Junhui Hou, Yue Qian, Juyong Zhang, Ying He

Although convolutional neural networks have achieved remarkable success in analyzing 2D images/videos, it is still non-trivial to apply the well-developed 2D techniques in regular domains to the irregular 3D point cloud data.

Reduced Reference Perceptual Quality Model and Application to Rate Control for 3D Point Cloud Compression

no code implementations25 Nov 2020 Qi Liu, Hui Yuan, Raouf Hamzaoui, Honglei Su, Junhui Hou, Huan Yang

In rate-distortion optimization, the encoder settings are determined by maximizing a reconstruction quality measure subject to a constraint on the bit rate.

Quantization

Deep Magnification-Flexible Upsampling over 3D Point Clouds

1 code implementation25 Nov 2020 Yue Qian, Junhui Hou, Sam Kwong, Ying He

In addition, we propose a simple yet effective training strategy to drive such a flexible ability.

Recurrent Multi-view Alignment Network for Unsupervised Surface Registration

1 code implementation CVPR 2021 Wanquan Feng, Juyong Zhang, Hongrui Cai, Haofei Xu, Junhui Hou, Hujun Bao

Learning non-rigid registration in an end-to-end manner is challenging due to the inherent high degrees of freedom and the lack of labeled training data.

Deformable Object Manipulation Neural Rendering +1

CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection

1 code implementation NeurIPS 2020 Qijian Zhang, Runmin Cong, Junhui Hou, Chongyi Li, Yao Zhao

In the first stage, we propose a group-attentional semantic aggregation module that models inter-image relationships to generate the group-wise semantic representations.

Co-Salient Object Detection object-detection +1

Deep Selective Combinatorial Embedding and Consistency Regularization for Light Field Super-resolution

no code implementations26 Sep 2020 Jing Jin, Junhui Hou, Zhiyu Zhu, Jie Chen, Sam Kwong

To preserve the parallax structure among the reconstructed SAIs, we subsequently append a consistency regularization network trained over a structure-aware loss function to refine the parallax relationships over the coarse estimation.

Disparity Estimation Super-Resolution

A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds

2 code implementations25 Jul 2020 Yi Wang, Junhui Hou, Xinyu Hou, Lap-Pui Chau

In this paper, we propose a novel self-training approach named Crowd-SDNet that enables a typical object detector trained only with point-level annotations (i. e., objects are labeled with points) to estimate both the center points and sizes of crowded objects.

Crowd Counting Object +2

Deep Spatial-angular Regularization for Compressive Light Field Reconstruction over Coded Apertures

1 code implementation ECCV 2020 Mantang Guo, Junhui Hou, Jing Jin, Jie Chen, Lap-Pui Chau

Coded aperture is a promising approach for capturing the 4-D light field (LF), in which the 4-D data are compressively modulated into 2-D coded measurements that are further decoded by reconstruction algorithms.

Image and Video Processing

Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual Learning

1 code implementation18 Jun 2020 Zhiyu Zhu, Junhui Hou, Jie Chen, Huanqiang Zeng, Jiantao Zhou

Specifically, PZRes-Net learns a high resolution and \textit{zero-centric} residual image, which contains high-frequency spatial details of the scene across all spectral bands, from both inputs in a progressive fashion along the spectral dimension.

Hyperspectral Image Super-Resolution Hyperspectral Unmixing +1

MOPS-Net: A Matrix Optimization-driven Network forTask-Oriented 3D Point Cloud Downsampling

1 code implementation1 May 2020 Yue Qian, Junhui Hou, Qijian Zhang, Yiming Zeng, Sam Kwong, Ying He

This paper explores the problem of task-oriented downsampling over 3D point clouds, which aims to downsample a point cloud while maintaining the performance of subsequent applications applied to the downsampled sparse points as much as possible.

Point Cloud Classification

Multi-View Spectral Clustering Tailored Tensor Low-Rank Representation

no code implementations30 Apr 2020 Yuheng Jia, Hui Liu, Junhui Hou, Sam Kwong, Qingfu Zhang

On the basis of the novel tensor low-rank norm, we formulate MVSC as a convex low-rank tensor recovery problem, which is then efficiently solved with an augmented Lagrange multiplier based method iteratively.

Clustering

When Residual Learning Meets Dense Aggregation: Rethinking the Aggregation of Deep Neural Networks

no code implementations19 Apr 2020 Zhiyu Zhu, Zhen-Peng Bian, Junhui Hou, Yi Wang, Lap-Pui Chau

However, the existing networks usually suffer from either redundancy of convolutional layers or insufficient utilization of parameters.

Neural Architecture Search

Light Field Spatial Super-resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization

1 code implementation CVPR 2020 Jing Jin, Junhui Hou, Jie Chen, Sam Kwong

Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution as the limited sampling resources have to be shared with the angular dimension.

Super-Resolution

PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling

1 code implementation ECCV 2020 Yue Qian, Junhui Hou, Sam Kwong, Ying He

Matrix $\mathbf T$ approximates the augmented Jacobian matrix of a local parameterization and builds a one-to-one correspondence between the 2D parametric domain and the 3D tangent plane so that we can lift the adaptively distributed 2D samples (which are also learned from data) to 3D space.

Point Cloud Super Resolution Surface Reconstruction

Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement

9 code implementations CVPR 2020 Chunle Guo, Chongyi Li, Jichang Guo, Chen Change Loy, Junhui Hou, Sam Kwong, Runmin Cong

The paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network.

Color Constancy Face Detection +1

An Ensemble Rate Adaptation Framework for Dynamic Adaptive Streaming Over HTTP

no code implementations26 Dec 2019 Hui Yuan, Xiaoqian Hu, Junhui Hou, Xuekai Wei, Sam Kwong

Specifically, the proposed framework is composed of two modules, i. e., the method pool and method controller.

Spatial and Temporal Consistency-Aware Dynamic Adaptive Streaming for 360-Degree Videos

no code implementations20 Dec 2019 Hui Yuan, Shiyun Zhao, Junhui Hou, Xuekai Wei, Sam Kwong

That is, our method preserves both the quality and the smoothness of tiles in FoV, thus providing the best QoE for users.

A Comprehensive Study and Comparison of Core Technologies for MPEG 3D Point Cloud Compression

no code implementations20 Dec 2019 Hao Liu, Hui Yuan, Qi Liu, Junhui Hou, Ju Liu

Point cloud based 3D visual representation is becoming popular due to its ability to exhibit the real world in a more comprehensive and immersive way.

Hyperspectral Image Classification via Sparse Representation With Incremental Dictionaries

1 code implementation journal 2019 Shujun Yang, Junhui Hou, Yuheng Jia, Shaohui Mei, and Qian Du

In this letter, we propose a new sparse representation (SR)-based method for hyperspectral image (HSI) classification, namely SR with incremental dictionaries (SRID).

Classification Hyperspectral Image Classification

Convolutional Neural Networks with Dynamic Regularization

no code implementations26 Sep 2019 Yi Wang, Zhen-Peng Bian, Junhui Hou, Lap-Pui Chau

That is, the regularization strength is fixed to a predefined schedule, and manual adjustments are required to adapt to various network architectures.

Deep Coarse-to-fine Dense Light Field Reconstruction with Flexible Sampling and Geometry-aware Fusion

1 code implementation31 Aug 2019 Jing Jin, Junhui Hou, Jie Chen, Huanqiang Zeng, Sam Kwong, Jingyi Yu

Specifically, the coarse sub-aperture image (SAI) synthesis module first explores the scene geometry from an unstructured sparsely-sampled LF and leverages it to independently synthesize novel SAIs, in which a confidence-based blending strategy is proposed to fuse the information from different input SAIs, giving an intermediate densely-sampled LF.

Computational Efficiency Depth Estimation

Light Field Super-resolution via Attention-Guided Fusion of Hybrid Lenses

1 code implementation23 Jul 2019 Jing Jin, Junhui Hou, Jie Chen, Sam Kwong, Jingyi Yu

To the best of our knowledge, this is the first end-to-end deep learning method for reconstructing a high-resolution LF image with a hybrid input.

Super-Resolution

Single Image based Head Pose Estimation with Spherical Parameterization and 3D Morphing

no code implementations22 Jul 2019 Hui Yuan, Mengyu Li, Junhui Hou, Jimin Xiao

Specifically, the rectangular coordinates of only four non-coplanar feature points from a predefined 3D facial model as well as the corresponding ones automatically/ manually extracted from a 2D face image are first normalized to exclude the effect of external factors (i. e., scale factor and translation parameters).

Head Pose Estimation

Nested Network with Two-Stream Pyramid for Salient Object Detection in Optical Remote Sensing Images

no code implementations20 Jun 2019 Chongyi Li, Runmin Cong, Junhui Hou, Sanyi Zhang, Yue Qian, Sam Kwong

Arising from the various object types and scales, diverse imaging orientations, and cluttered backgrounds in optical remote sensing image (RSI), it is difficult to directly extend the success of salient object detection for nature scene image to the optical RSI.

Object object-detection +2

Clustering-aware Graph Construction: A Joint Learning Perspective

no code implementations4 May 2019 Yuheng Jia, Hui Liu, Junhui Hou, Sam Kwong

Graph-based clustering methods have demonstrated the effectiveness in various applications.

Clustering Graph Clustering +1

Stratified Labeling for Surface Consistent Parallax Correction and Occlusion Completion

no code implementations7 Mar 2019 Jie Chen, Lap-Pui Chau, Junhui Hou

A stratified synthesis strategy is adopted which parses the scene content based on stratified disparity layers and across a varying range of spatial granularities.

Generative Adversarial Network Novel View Synthesis

An Underwater Image Enhancement Benchmark Dataset and Beyond

1 code implementation11 Jan 2019 Chongyi Li, Chunle Guo, Wenqi Ren, Runmin Cong, Junhui Hou, Sam Kwong, DaCheng Tao

In this paper, we construct an Underwater Image Enhancement Benchmark (UIEB) including 950 real-world underwater images, 890 of which have the corresponding reference images.

Ranked #5 on Underwater Image Restoration on LSUI (using extra training data)

Image Enhancement Underwater Image Restoration

Fast Light Field Reconstruction With Deep Coarse-To-Fine Modeling of Spatial-Angular Clues

1 code implementation ECCV 2018 Henry Wing Fung Yeung, Junhui Hou, Jie Chen, Yuk Ying Chung, Xiaoming Chen

Specifically, our end-to-end model first synthesizes a set of intermediate novel sub-aperture images (SAIs) by exploring the coarse characteristics of the sparsely-sampled LF input with spatial-angular alternating convolutions.

Light Field Denoising via Anisotropic Parallax Analysis in a CNN Framework

no code implementations31 May 2018 Jie Chen, Junhui Hou, Lap-Pui Chau

Light field (LF) cameras provide perspective information of scenes by taking directional measurements of the focusing light rays.

Denoising

Robust Video Content Alignment and Compensation for Clear Vision Through the Rain

no code implementations24 Apr 2018 Jie Chen, Cheen-Hau Tan, Junhui Hou, Lap-Pui Chau, He Li

Extensive evaluations show that advantage of up to 5dB is achieved on the scene restoration PSNR over state-of-the-art methods, and the advantage is especially obvious with highly complex and dynamic scenes.

Rain Removal

Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework

no code implementations CVPR 2018 Jie Chen, Cheen-Hau Tan, Junhui Hou, Lap-Pui Chau, He Li

Visual inspection shows that much cleaner rain removal is achieved especially for highly dynamic scenes with heavy and opaque rainfall from a fast moving camera.

Rain Removal

Accurate Light Field Depth Estimation with Superpixel Regularization over Partially Occluded Regions

no code implementations7 Aug 2017 Jie Chen, Junhui Hou, Yun Ni, Lap-Pui Chau

Significant improvements have been made in terms of overall depth estimation error; however, current state-of-the-art methods still show limitations in handling intricate occluding structures and complex scenes with multiple occlusions.

Depth Estimation

Light Field Compression with Disparity Guided Sparse Coding based on Structural Key Views

no code implementations12 Oct 2016 Jie Chen, Junhui Hou, Lap-Pui Chau

Recent imaging technologies are rapidly evolving for sampling richer and more immersive representations of the 3D world.

Cannot find the paper you are looking for? You can Submit a new open access paper.