Search Results for author: Sai-Kit Yeung

Found 31 papers, 8 papers with code

RFNet-4D: Joint Object Reconstruction and Flow Estimation from 4D Point Clouds

no code implementations30 Mar 2022 Tuan-Anh Vu, Duc-Thanh Nguyen, Binh-Son Hua, Quang-Hieu Pham, Sai-Kit Yeung

Object reconstruction from 3D point clouds has achieved impressive progress in the computer vision and computer graphics research field.

3D Human Reconstruction 3D Reconstruction +3

RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning

1 code implementation26 Feb 2022 Zhiyuan Zhang, Binh-Son Hua, Sai-Kit Yeung

3D point clouds deep learning is a promising field of research that allows a neural network to learn features of point clouds directly, making it a robust tool for solving 3D scene understanding tasks.

3D Point Cloud Classification Point Cloud Segmentation +1

ACNet: Approaching-and-Centralizing Network for Zero-Shot Sketch-Based Image Retrieval

no code implementations24 Nov 2021 Hao Ren, Ziqiang Zheng, Yang Wu, Hong Lu, Yang Yang, Sai-Kit Yeung

The huge domain gap between sketches and photos and the highly abstract sketch representations pose challenges for sketch-based image retrieval (\underline{SBIR}).

Sketch-Based Image Retrieval

Neural Scene Decoration from a Single Photograph

no code implementations4 Aug 2021 Hong-Wing Pang, Yingshu Chen, Binh-Son Hua, Sai-Kit Yeung

Furnishing and rendering an indoor scene is a common but tedious task for interior design: an artist needs to observe the space, create a conceptual design, build a 3D model, and perform rendering.

Image Generation

Dual-SLAM: A framework for robust single camera navigation

no code implementations23 Sep 2020 Huajian Huang, Wen-Yan Lin, Siying Liu, Dong Zhang, Sai-Kit Yeung

As local pose estimation is ill-conditioned, local pose estimation failures happen regularly, making the overall SLAM system brittle.

Pose Estimation Simultaneous Localization and Mapping

Minimal Adversarial Examples for Deep Learning on 3D Point Clouds

no code implementations ICCV 2021 Jaeyeon Kim, Binh-Son Hua, Duc Thanh Nguyen, Sai-Kit Yeung

With recent developments of convolutional neural networks, deep learning for 3D point clouds has shown significant progress in various 3D scene understanding tasks, e. g., object recognition, semantic segmentation.

3D Object Recognition Object Detection +3

Global Context Aware Convolutions for 3D Point Cloud Understanding

no code implementations7 Aug 2020 Zhiyuan Zhang, Binh-Son Hua, Wei Chen, Yibin Tian, Sai-Kit Yeung

We found that a key reason is that compared to point coordinates, rotation-invariant features consumed by point cloud convolution are not as distinctive.

Point Cloud Classification Scene Understanding

LCD: Learned Cross-Domain Descriptors for 2D-3D Matching

1 code implementation21 Nov 2019 Quang-Hieu Pham, Mikaela Angelina Uy, Binh-Son Hua, Duc Thanh Nguyen, Gemma Roig, Sai-Kit Yeung

In this work, we present a novel method to learn a local cross-domain descriptor for 2D image and 3D point cloud matching.

3D Point Cloud Matching Depth Estimation

ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics

1 code implementation ICCV 2019 Zhiyuan Zhang, Binh-Son Hua, Sai-Kit Yeung

Deep learning with 3D data has progressed significantly since the introduction of convolutional neural networks that can handle point order ambiguity in point cloud data.

3D Point Cloud Classification

Rotation Invariant Convolutions for 3D Point Clouds Deep Learning

1 code implementation17 Aug 2019 Zhiyuan Zhang, Binh-Son Hua, David W. Rosen, Sai-Kit Yeung

Our core idea is to use low-level rotation invariant geometric features such as distances and angles to design a convolution operator for point cloud learning.

Scene Understanding Translation

Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data

1 code implementation ICCV 2019 Mikaela Angelina Uy, Quang-Hieu Pham, Binh-Son Hua, Duc Thanh Nguyen, Sai-Kit Yeung

From our comprehensive benchmark, we show that our dataset poses great challenges to existing point cloud classification techniques as objects from real-world scans are often cluttered with background and/or are partial due to occlusions.

3D Object Classification Classification +3

Uncalibrated Photometric Stereo Under Natural Illumination

no code implementations CVPR 2018 Zhipeng Mo, Boxin Shi, Feng Lu, Sai-Kit Yeung, Yasuyuki Matsushita

This paper presents a photometric stereo method that works with unknown natural illuminations without any calibration object.

Real-time Progressive 3D Semantic Segmentation for Indoor Scene

no code implementations1 Apr 2018 Quang-Hieu Pham, Binh-Son Hua, Duc Thanh Nguyen, Sai-Kit Yeung

The widespread adoption of autonomous systems such as drones and assistant robots has created a need for real-time high-quality semantic scene segmentation.

3D Semantic Segmentation Scene Segmentation

Pointwise Convolutional Neural Networks

1 code implementation CVPR 2018 Binh-Son Hua, Minh-Khoi Tran, Sai-Kit Yeung

Deep learning with 3D data such as reconstructed point clouds and CAD models has received great research interests recently.

Object Recognition Semantic Segmentation

Radiometric Calibration for Internet Photo Collections

no code implementations CVPR 2017 Zhipeng Mo, Boxin Shi, Sai-Kit Yeung, Yasuyuki Matsushita

Radiometrically calibrating the images from Internet photo collections brings photometric analysis from lab data to big image data in the wild, but conventional calibration methods cannot be directly applied to such image data.

A Benchmark Dataset and Evaluation for Non-Lambertian and Uncalibrated Photometric Stereo

no code implementations CVPR 2016 Boxin Shi, Zhe Wu, Zhipeng Mo, Dinglong Duan, Sai-Kit Yeung, Ping Tan

Recent progress on photometric stereo extends the technique to deal with general materials and unknown illumination conditions.

A Field Model for Repairing 3D Shapes

no code implementations CVPR 2016 Duc Thanh Nguyen, Binh-Son Hua, Khoi Tran, Quang-Hieu Pham, Sai-Kit Yeung

The proposed method was evaluated on both artificial data and real data obtained from reconstruction of practical scenes.

Towards Building an RGBD-M Scanner

no code implementations12 Mar 2016 Zhe Wu, Sai-Kit Yeung, Ping Tan

We present a portable device to capture both shape and reflectance of an indoor scene.

Segmentation Rectification for Video Cutout via One-Class Structured Learning

no code implementations16 Feb 2016 Junyan Wang, Sai-Kit Yeung, Jue Wang, Kun Zhou

Comprehensive experiments on both RGB and RGB-D data demonstrate that our simple and effective method significantly outperforms the segmentation propagation methods adopted in the state-of-the-art video cutout systems, and the results also suggest the potential usefulness of our method in image cutout system.

A Closed-Form Solution to Tensor Voting: Theory and Applications

no code implementations19 Jan 2016 Tai-Pang Wu, Sai-Kit Yeung, Jiaya Jia, Chi-Keung Tang, Gerard Medioni

We prove a closed-form solution to tensor voting (CFTV): given a point set in any dimensions, our closed-form solution provides an exact, continuous and efficient algorithm for computing a structure-aware tensor that simultaneously achieves salient structure detection and outlier attenuation.

Stereo Matching Stereo Matching Hand

Fill and Transfer: A Simple Physics-Based Approach for Containability Reasoning

no code implementations ICCV 2015 Lap-Fai Yu, Noah Duncan, Sai-Kit Yeung

We apply our approach to reason about the containability of several real-world objects acquired using a consumer-grade depth camera.

Computer Vision

An MRF-Poselets Model for Detecting Highly Articulated Humans

no code implementations ICCV 2015 Duc Thanh Nguyen, Minh-Khoi Tran, Sai-Kit Yeung

The problem of human detection is then formulated as maximum a posteriori (MAP) estimation in the MRF model.

Human Detection

A Compact Linear Programming Relaxation for Binary Sub-modular MRF

no code implementations9 Apr 2014 Junyan Wang, Sai-Kit Yeung

We propose a novel compact linear programming (LP) relaxation for binary sub-modular MRF in the context of object segmentation.

Interactive Segmentation Semantic Segmentation

Shading-Based Shape Refinement of RGB-D Images

no code implementations CVPR 2013 Lap-Fai Yu, Sai-Kit Yeung, Yu-Wing Tai, Stephen Lin

We present a shading-based shape refinement algorithm which uses a noisy, incomplete depth map from Kinect to help resolve ambiguities in shape-from-shading.

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