Search Results for author: Satoshi Iizuka

Found 14 papers, 3 papers with code

Image Synthesis-based Late Stage Cancer Augmentation and Semi-Supervised Segmentation for MRI Rectal Cancer Staging

no code implementations8 Dec 2023 Saeko Sasuga, Akira Kudo, Yoshiro Kitamura, Satoshi Iizuka, Edgar Simo-Serra, Atsushi Hamabe, Masayuki Ishii, Ichiro Takemasa

To tackle this, we propose two kinds of approaches of image synthesis-based late stage cancer augmentation and semi-supervised learning which is designed for T-stage prediction.

Data Augmentation Image Generation +1

Diffusion-based Holistic Texture Rectification and Synthesis

no code implementations26 Sep 2023 Guoqing Hao, Satoshi Iizuka, Kensho Hara, Edgar Simo-Serra, Hirokatsu Kataoka, Kazuhiro Fukui

We present a novel framework for rectifying occlusions and distortions in degraded texture samples from natural images.

Texture Synthesis

Controllable Multi-domain Semantic Artwork Synthesis

no code implementations19 Aug 2023 Yuantian Huang, Satoshi Iizuka, Edgar Simo-Serra, Kazuhiro Fukui

To address this problem, we propose a dataset, which we call ArtSem, that contains 40, 000 images of artwork from 4 different domains with their corresponding semantic label maps.

Generative Adversarial Network

Adaptive occlusion sensitivity analysis for visually explaining video recognition networks

1 code implementation26 Jul 2022 Tomoki Uchiyama, Naoya Sogi, Satoshi Iizuka, Koichiro Niinuma, Kazuhiro Fukui

The key idea here is to occlude a specific volume of data by a 3D mask in an input 3D temporal-spatial data space and then measure the change degree in the output score.

Decision Making Image Classification +2

TopNet: Topology Preserving Metric Learning for Vessel Tree Reconstruction and Labelling

no code implementations18 Sep 2020 Deepak Keshwani, Yoshiro Kitamura, Satoshi Ihara, Satoshi Iizuka, Edgar Simo-Serra

To the best of our knowledge, this is the first deep learning based approach which learns multi-label tree structure connectivity from images.

Metric Learning Segmentation +1

DeepRemaster: Temporal Source-Reference Attention Networks for Comprehensive Video Enhancement

no code implementations18 Sep 2020 Satoshi Iizuka, Edgar Simo-Serra

The remastering of vintage film comprises of a diversity of sub-tasks including super-resolution, noise removal, and contrast enhancement which aim to restore the deteriorated film medium to its original state.

Colorization Diversity +2

Two-stage Discriminative Re-ranking for Large-scale Landmark Retrieval

2 code implementations25 Mar 2020 Shuhei Yokoo, Kohei Ozaki, Edgar Simo-Serra, Satoshi Iizuka

Due to the variance of the images, which include extreme viewpoint changes such as having to retrieve images of the exterior of a landmark from images of the interior, this is very challenging for approaches based exclusively on visual similarity.

Diversity Image Retrieval +4

Virtual Thin Slice: 3D Conditional GAN-based Super-resolution for CT Slice Interval

no code implementations30 Aug 2019 Akira Kudo, Yoshiro Kitamura, Yuanzhong Li, Satoshi Iizuka, Edgar Simo-Serra

In this paper, we present a novel architecture based on conditional Generative Adversarial Networks (cGANs) with the goal of generating high resolution images of main body parts including head, chest, abdomen and legs.

Anatomy Diversity +2

Joint Gap Detection and Inpainting of Line Drawings

no code implementations CVPR 2017 Kazuma Sasaki, Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Ishikawa

We evaluate our method qualitatively on a diverse set of challenging line drawings and also provide quantitative results with a user study, where it significantly outperforms the state of the art.

Mastering Sketching: Adversarial Augmentation for Structured Prediction

no code implementations27 Mar 2017 Edgar Simo-Serra, Satoshi Iizuka, Hiroshi Ishikawa

Our approach augments a simplification network with a discriminator network, training both networks jointly so that the discriminator network discerns whether a line drawing is a real training data or the output of the simplification network, which in turn tries to fool it.

Structured Prediction

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