Search Results for author: Ko Nishino

Found 19 papers, 2 papers with code

View Birdification in the Crowd: Ground-Plane Localization from Perceived Movements

no code implementations9 Nov 2021 Mai Nishimura, Shohei Nobuhara, Ko Nishino

We introduce view birdification, the problem of recovering ground-plane movements of people in a crowd from an ego-centric video captured from an observer (e. g., a person or a vehicle) also moving in the crowd.


Shape From Sky: Polarimetric Normal Recovery Under the Sky

no code implementations CVPR 2021 Tomoki Ichikawa, Matthew Purri, Ryo Kawahara, Shohei Nobuhara, Kristin Dana, Ko Nishino

That is, we show that the unique polarization pattern encoded in the polarimetric appearance of an object captured under the sky can be decoded to reveal the surface normal at each pixel.

Polarimetric Normal Stereo

no code implementations CVPR 2021 Yoshiki Fukao, Ryo Kawahara, Shohei Nobuhara, Ko Nishino

Our key idea is to introduce a polarimetric cost volume of distance defined on the polarimetric observations and the polarization state computed from the surface normal.


Differential Viewpoints for Ground Terrain Material Recognition

1 code implementation22 Sep 2020 Jia Xue, Hang Zhang, Ko Nishino, Kristin J. Dana

A key concept is differential angular imaging, where small angular variations in image capture enables angular-gradient features for an enhanced appearance representation that improves recognition.

Autonomous Driving Material Recognition +1

Video Region Annotation with Sparse Bounding Boxes

no code implementations17 Aug 2020 Yuzheng Xu, Yang Wu, Nur Sabrina binti Zuraimi, Shohei Nobuhara, Ko Nishino

Video analysis has been moving towards more detailed interpretation (e. g. segmentation) with encouraging progresses.

Invertible Neural BRDF for Object Inverse Rendering

1 code implementation ECCV 2020 Zhe Chen, Shohei Nobuhara, Ko Nishino

We introduce a novel neural network-based BRDF model and a Bayesian framework for object inverse rendering, i. e., joint estimation of reflectance and natural illumination from a single image of an object of known geometry.

3D-GMNet: Single-View 3D Shape Recovery as A Gaussian Mixture

no code implementations10 Dec 2019 Kohei Yamashita, Shohei Nobuhara, Ko Nishino

In this paper, we introduce 3D-GMNet, a deep neural network for 3D object shape reconstruction from a single image.

3D Reconstruction Density Estimation +1

Appearance and Shape from Water Reflection

no code implementations25 Jun 2019 Ryo Kawahara, Meng-Yu Jennifer Kuo, Shohei Nobuhara, Ko Nishino

In other words, for the first time, we show that capturing a direct and water-reflected scene in a single exposure forms a self-calibrating HDR catadioptric stereo camera.

3D Scene Reconstruction Stereo Matching +1

Variable Ring Light Imaging: Capturing Transient Subsurface Scattering with An Ordinary Camera

no code implementations ECCV 2018 Ko Nishino, Art Subpa-Asa, Yuta Asano, Mihoko Shimano, Imari Sato

We show that the path length of light captured in each of these observations is naturally lower-bounded by the ring light radius.

Wetness and Color From a Single Multispectral Image

no code implementations CVPR 2017 Mihoko Shimano, Hiroki Okawa, Yuta Asano, Ryoma Bise, Ko Nishino, Imari Sato

We derive an analytical spectral appearance model of wet surfaces that expresses the characteristic spectral sharpening due to multiple scattering and absorption in the surface.

Autonomous Vehicles

Differential Angular Imaging for Material Recognition

no code implementations CVPR 2017 Jia Xue, Hang Zhang, Kristin Dana, Ko Nishino

We realize this by developing a framework for differential angular imaging, where small angular variations in image capture provide an enhanced appearance representation and significant recognition improvement.

Material Recognition

Material Recognition from Local Appearance in Global Context

no code implementations28 Nov 2016 Gabriel Schwartz, Ko Nishino

We achieve this by training a fully-convolutional material recognition network end-to-end with only material category supervision.

Material Recognition

Integrating Local Material Recognition with Large-Scale Perceptual Attribute Discovery

no code implementations5 Apr 2016 Gabriel Schwartz, Ko Nishino

In this paper, we introduce a novel material category recognition network architecture to show that perceptual attributes can, in fact, be automatically discovered inside a local material recognition framework.

Material Recognition

Radiometric Scene Decomposition: Scene Reflectance, Illumination, and Geometry from RGB-D Images

no code implementations5 Apr 2016 Stephen Lombardi, Ko Nishino

Recovering the radiometric properties of a scene (i. e., the reflectance, illumination, and geometry) is a long-sought ability of computer vision that can provide invaluable information for a wide range of applications.

Scene Understanding

Automatically Discovering Local Visual Material Attributes

no code implementations CVPR 2015 Gabriel Schwartz, Ko Nishino

We argue that it would be ideal to recognize materials without relying on object cues such as shape.

Object Recognition

Reflectance Hashing for Material Recognition

no code implementations CVPR 2015 Hang Zhang, Kristin Dana, Ko Nishino

Reflectance offers a unique signature of the material but is challenging to measure and use for recognizing materials due to its high-dimensionality.

Dictionary Learning Material Recognition

Multiview Shape and Reflectance from Natural Illumination

no code implementations CVPR 2014 Geoffrey Oxholm, Ko Nishino

To this end, we derive a probabilistic geometry estimation method that fully exploits the rich signal embedded in complex appearance.

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