Search Results for author: Yasuyuki Matsushita

Found 40 papers, 10 papers with code

An Analysis of Sketched IRLS for Accelerated Sparse Residual Regression

no code implementations ECCV 2020 Daichi Iwata, Michael Waechter, Wen-Yan Lin, Yasuyuki Matsushita

This paper studies the problem of sparse residual regression, i. e., learning a linear model using a norm that favors solutions in which the residuals are sparsely distributed.

regression

What is Learned in Deep Uncalibrated Photometric Stereo?

no code implementations ECCV 2020 Guan-Ying Chen, Michael Waechter, Boxin Shi, Kwan-Yee K. Wong, Yasuyuki Matsushita

Based on this insight, we propose a guided calibration network, named GCNet, that explicitly leverages object shape and shading information for improved lighting estimation.

Lighting Estimation Surface Normal Estimation

Edge-preserving Near-light Photometric Stereo with Neural Surfaces

no code implementations11 Jul 2022 Heng Guo, Hiroaki Santo, Boxin Shi, Yasuyuki Matsushita

This paper presents a near-light photometric stereo method that faithfully preserves sharp depth edges in the 3D reconstruction.

3D Reconstruction

Normal Integration via Inverse Plane Fitting With Minimum Point-to-Plane Distance

1 code implementation CVPR 2021 Xu Cao, Boxin Shi, Fumio Okura, Yasuyuki Matsushita

Experimental results on analytically computed, synthetic, and real-world surfaces show that our method yields accurate and stable reconstruction for both orthographic and perspective normal maps.

Surface Reconstruction

Multispectral Photometric Stereo for Spatially-Varying Spectral Reflectances: A Well Posed Problem?

1 code implementation CVPR 2021 Heng Guo, Fumio Okura, Boxin Shi, Takuya Funatomi, Yasuhiro Mukaigawa, Yasuyuki Matsushita

To make the problem well-posed, existing MPS methods rely on restrictive assumptions, such as shape prior, surfaces having a monochromatic with uniform albedo.

Lighting, Reflectance and Geometry Estimation From 360deg Panoramic Stereo

no code implementations CVPR 2021 Junxuan Li, Hongdong Li, Yasuyuki Matsushita

We propose a method for estimating high-definition spatially-varying lighting, reflectance, and geometry of a scene from 360deg stereo images.

Shell Theory: A Statistical Model of Reality

1 code implementation IEEE Transactions on Pattern Analysis and Machine Intelligence 2021 Wen-Yan Lin, Siying Liu, Changhao Ren, Ngai-Man Cheung, Hongdong Li, Yasuyuki Matsushita

The foundational assumption of machine learning is that the data under consideration is separable into classes; while intuitively reasonable, separability constraints have proven remarkably difficult to formulate mathematically.

Anomaly Detection BIG-bench Machine Learning +6

Lighting, Reflectance and Geometry Estimation from 360$^{\circ}$ Panoramic Stereo

no code implementations20 Apr 2021 Junxuan Li, Hongdong Li, Yasuyuki Matsushita

We propose a method for estimating high-definition spatially-varying lighting, reflectance, and geometry of a scene from 360$^{\circ}$ stereo images.

Generalized Shuffled Linear Regression

no code implementations ICCV 2021 Feiran Li, Kent Fujiwara, Fumio Okura, Yasuyuki Matsushita

Therefore, in this work, we generalize the formulation of shuffled linear regression to a broader range of conditions where only part of the data should correspond.

regression

A Closer Look at Rotation-Invariant Deep Point Cloud Analysis

no code implementations ICCV 2021 Feiran Li, Kent Fujiwara, Fumio Okura, Yasuyuki Matsushita

Recent progress in rotation-invariant point cloud analysis is mainly driven by converting point clouds into their respective canonical poses, and principal component analysis (PCA) is a practical tool to achieve this.

Deep Photometric Stereo for Non-Lambertian Surfaces

1 code implementation26 Jul 2020 Guan-Ying Chen, Kai Han, Boxin Shi, Yasuyuki Matsushita, Kwan-Yee K. Wong

To deal with the uncalibrated scenario where light directions are unknown, we introduce a new convolutional network, named LCNet, to estimate light directions from input images.

Self-calibrating Deep Photometric Stereo Networks

1 code implementation CVPR 2019 Guan-Ying Chen, Kai Han, Boxin Shi, Yasuyuki Matsushita, Kwan-Yee K. Wong

This paper proposes an uncalibrated photometric stereo method for non-Lambertian scenes based on deep learning.

Shape-conditioned Image Generation by Learning Latent Appearance Representation from Unpaired Data

no code implementations29 Nov 2018 Yutaro Miyauchi, Yusuke Sugano, Yasuyuki Matsushita

Conditional image generation is effective for diverse tasks including training data synthesis for learning-based computer vision.

Conditional Image Generation Object

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.

Probabilistic Plant Modeling via Multi-View Image-to-Image Translation

no code implementations CVPR 2018 Takahiro Isokane, Fumio Okura, Ayaka Ide, Yasuyuki Matsushita, Yasushi Yagi

This paper describes a method for inferring three-dimensional (3D) plant branch structures that are hidden under leaves from multi-view observations.

Image-to-Image Translation Translation

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 Pseudo-Bayesian Algorithm for Robust PCA

no code implementations NeurIPS 2016 Tae-Hyun Oh, Yasuyuki Matsushita, In Kweon, David Wipf

Commonly used in many applications, robust PCA represents an algorithmic attempt to reduce the sensitivity of classical PCA to outliers.

Recovering Transparent Shape From Time-Of-Flight Distortion

no code implementations CVPR 2016 Kenichiro Tanaka, Yasuhiro Mukaigawa, Hiroyuki Kubo, Yasuyuki Matsushita, Yasushi Yagi

This paper presents a method for recovering shape and normal of a transparent object from a single viewpoint using a Time-of-Flight (ToF) camera.

Object

Multiview Rectification of Folded Documents

no code implementations1 Jun 2016 Shaodi You, Yasuyuki Matsushita, Sudipta Sinha, Yusuke Bou, Katsushi Ikeuchi

Digitally unwrapping images of paper sheets is crucial for accurate document scanning and text recognition.

3D Reconstruction

Continuous 3D Label Stereo Matching using Local Expansion Moves

2 code implementations28 Mar 2016 Tatsunori Taniai, Yasuyuki Matsushita, Yoichi Sato, Takeshi Naemura

The local expansion moves extend traditional expansion moves by two ways: localization and spatial propagation.

Patch Matching Stereo Matching +1

RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints

1 code implementation CVPR 2018 Asako Kanezaki, Yasuyuki Matsushita, Yoshifumi Nishida

We propose a Convolutional Neural Network (CNN)-based model "RotationNet," which takes multi-view images of an object as input and jointly estimates its pose and object category.

3D Object Classification Object +2

Pseudo-Bayesian Robust PCA: Algorithms and Analyses

no code implementations7 Dec 2015 Tae-Hyun Oh, Yasuyuki Matsushita, In So Kweon, David Wipf

Commonly used in computer vision and other applications, robust PCA represents an algorithmic attempt to reduce the sensitivity of classical PCA to outliers.

Matrix Completion

Photometric Stereo With Small Angular Variations

no code implementations ICCV 2015 Jian Wang, Yasuyuki Matsushita, Boxin Shi, Aswin C. Sankaranarayanan

This paper studies the effect of small angular variations in illumination directions to photometric stereo.

Fast Randomized Singular Value Thresholding for Low-rank Optimization

no code implementations1 Sep 2015 Tae-Hyun Oh, Yasuyuki Matsushita, Yu-Wing Tai, In So Kweon

The problems related to NNM, or WNNM, can be solved iteratively by applying a closed-form proximal operator, called Singular Value Thresholding (SVT), or Weighted SVT, but they suffer from high computational cost of Singular Value Decomposition (SVD) at each iteration.

Clustering

Superdifferential Cuts for Binary Energies

no code implementations CVPR 2015 Tatsunori Taniai, Yasuyuki Matsushita, Takeshi Naemura

We then present our method as generalization of SSP, which is further shown to generalize several state-of-the-art techniques for higher-order and pairwise non-submodular functions [Ayed13, Gorelick14, Tang14].

Binarization Image Segmentation +1

Fast Randomized Singular Value Thresholding for Nuclear Norm Minimization

no code implementations CVPR 2015 Tae-Hyun Oh, Yasuyuki Matsushita, Yu-Wing Tai, In So Kweon

The problems related to NNM (or WNNM) can be solved iteratively by applying a closed-form proximal operator, called Singular Value Thresholding (SVT) (or Weighted SVT), but they suffer from high computational cost to compute a Singular Value Decomposition (SVD) at each iteration.

Clustering

Calibrating a Non-isotropic Near Point Light Source using a Plane

no code implementations CVPR 2014 Jaesik Park, Sudipta N. Sinha, Yasuyuki Matsushita, Yu-Wing Tai, In So Kweon

We show that a non-isotropic near point light source rigidly attached to a camera can be calibrated using multiple images of a weakly textured planar scene.

Position

Learning-by-Synthesis for Appearance-based 3D Gaze Estimation

no code implementations CVPR 2014 Yusuke Sugano, Yasuyuki Matsushita, Yoichi Sato

Unlike existing appearance-based methods that assume person-specific training data, we use a large amount of cross-subject training data to train a 3D gaze estimator.

3D Reconstruction Gaze Estimation +1

Graph Cut based Continuous Stereo Matching using Locally Shared Labels

no code implementations CVPR 2014 Tatsunori Taniai, Yasuyuki Matsushita, Takeshi Naemura

We present an accurate and efficient stereo matching method using locally shared labels, a new labeling scheme that enables spatial propagation in MRF inference using graph cuts.

Disparity Estimation Stereo Matching +1

Uncalibrated Photometric Stereo for Unknown Isotropic Reflectances

no code implementations CVPR 2013 Feng Lu, Yasuyuki Matsushita, Imari Sato, Takahiro Okabe, Yoichi Sato

We propose an uncalibrated photometric stereo method that works with general and unknown isotropic reflectances.

Bayesian Depth-from-Defocus with Shading Constraints

no code implementations CVPR 2013 Chen Li, Shuochen Su, Yasuyuki Matsushita, Kun Zhou, Stephen Lin

We present a method that enhances the performance of depth-from-defocus (DFD) through the use of shading information.

Depth Estimation

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