Computer Vision

Understand visual input.

Perceiving and gaining semantic understanding of our world via visual sensors. Automating this type of understanding is crucial for applications such as personal robotics, autonomous driving and factory automation.

Publications

Hierarchical Lovász Embeddings for Proposal-free Panoptic Segmentation

CVPR 2021

By : Tommi Kerola, Jie Li, Atsushi Kanehira, Yasunori Kudo, Alexis Vallet, Adrien Gaidon

Surrogate Gradient Field for Latent Space Manipulation

CVPR 2021

By : Minjun Li, Yanghua Jin, Huachun Zhu

Deep Visuo-Tactile Learning: Estimation of Tactile Properties from Images (Extended Abstract)

IJCAI2020

By : Kuniyuki Takahashi, Jethro Tan

Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN

IJCV 2020

By : Masaki Saito, Shunta Saito, Masanori Koyama, Sosuke Kobayashi

View All

Blog

A Brief Introduction to 3D Cameras

2020.02.03

Engineering

A Brief Introduction to 3D Cameras

By : Mihai Morariu

Team PFDet won the 3rd place in the Kaggle Open Images Challenge 2019

2019.10.04

Team PFDet won the 3rd place in the Kaggle Open Images Challenge 2019

By : Yusuke Niitani

A Brief History of Object Detection – from Haar-like features to losing anchors

2019.09.27

Research

A Brief History of Object Detection – from Haar-like features to losing anchors

By : Tommi Kerola

View All

Other Area

View All