151 citations · 219 across the 13 of their papers we have counts for
15 papers
Multi-View Azimuth Stereo via Tangent Space Consistency
Xu Cao, Hiroaki Santo, Fumio Okura +1
We present a method for 3D reconstruction only using calibrated multi-view surface azimuth maps. Our method, multi-view azimuth stereo, is effective for textureless or specular sur…
Edge-preserving Near-light Photometric Stereo with Neural Surfaces
Heng Guo, Hiroaki Santo, Boxin Shi +1
This paper presents a near-light photometric stereo method that faithfully preserves sharp depth edges in the 3D reconstruction. Unlike previous methods that rely on finite differe…
Lighting, Reflectance and Geometry Estimation from 360 Panoramic Stereo
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 stereo images. Our model takes advantage of t…
Descriptor-Free Multi-View Region Matching for Instance-Wise 3D Reconstruction
Takuma Doi, Fumio Okura, Toshiki Nagahara +2
This paper proposes a multi-view extension of instance segmentation without relying on texture or shape descriptor matching. Multi-view instance segmentation becomes challenging fo…
Deep Photometric Stereo for Non-Lambertian Surfaces
Guanying Chen, Kai Han, Boxin Shi +2
This paper addresses the problem of photometric stereo, in both calibrated and uncalibrated scenarios, for non-Lambertian surfaces based on deep learning. We first introduce a full…
Self-calibrating Deep Photometric Stereo Networks
Guanying Chen, Kai Han, Boxin Shi +2
This paper proposes an uncalibrated photometric stereo method for non-Lambertian scenes based on deep learning. Unlike previous approaches that heavily rely on assumptions of speci…
Shape-conditioned Image Generation by Learning Latent Appearance Representation from Unpaired Data
Yutaro Miyauchi, Yusuke Sugano, Yasuyuki Matsushita
Conditional image generation is effective for diverse tasks including training data synthesis for learning-based computer vision. However, despite the recent advances in generative…
Probabilistic Plant Modeling via Multi-View Image-to-Image Translation
Takahiro Isokane, Fumio Okura, Ayaka Ide +2
This paper describes a method for inferring three-dimensional (3D) plant branch structures that are hidden under leaves from multi-view observations. Unlike previous geometric appr…
Dimensionality's Blessing: Clustering Images by Underlying Distribution
Wen-Yan Lin, Siying Liu, Jian-Huang Lai +1
Many high dimensional vector distances tend to a constant. This is typically considered a negative "contrast-loss" phenomenon that hinders clustering and other machine learning tec…
High-Performance Out-of-core Block Randomized Singular Value Decomposition on GPU
Yuechao Lu, Fumihiko Ino, Yasuyuki Matsushita
Fast computation of singular value decomposition (SVD) is of great interest in various machine learning tasks. Recently, SVD methods based on randomized linear algebra have shown s…
Multiview Rectification of Folded Documents
Shaodi You, Yasuyuki Matsushita, Sudipta Sinha +2
Digitally unwrapping images of paper sheets is crucial for accurate document scanning and text recognition. This paper presents a method for automatically rectifying curved or fold…
Continuous 3D Label Stereo Matching using Local Expansion Moves
Tatsunori Taniai, Yasuyuki Matsushita, Yoichi Sato +1
We present an accurate stereo matching method using local expansion moves based on graph cuts. This new move-making scheme is used to efficiently infer per-pixel 3D plane labels on…
RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints
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. U…
Pseudo-Bayesian Robust PCA: Algorithms and Analyses
Tae-Hyun Oh, Yasuyuki Matsushita, In So Kweon +1
Commonly used in computer vision and other applications, robust PCA represents an algorithmic attempt to reduce the sensitivity of classical PCA to outliers. The basic idea is to l…
Fast Randomized Singular Value Thresholding for Low-rank Optimization
Tae-Hyun Oh, Yasuyuki Matsushita, Yu-Wing Tai +1
Rank minimization can be converted into tractable surrogate problems, such as Nuclear Norm Minimization (NNM) and Weighted NNM (WNNM). The problems related to NNM, or WNNM, can be…