no code implementations • 6 Feb 2024 • Tsunehiko Tanaka, Kenshi Abe, Kaito Ariu, Tetsuro Morimura, Edgar Simo-Serra
Traditional approaches in offline reinforcement learning aim to learn the optimal policy that maximizes the cumulative reward, also known as return.
no code implementations • 8 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.
no code implementations • 8 Dec 2023 • Akimichi Ichinose, Taro Hatsutani, Keigo Nakamura, Yoshiro Kitamura, Satoshi Iizuka, Edgar Simo-Serra, Shoji Kido, Noriyuki Tomiyama
Our framework combines two components of 1) anatomical segmentation of images, and 2) report structuring.
no code implementations • 26 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.
no code implementations • 19 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.
1 code implementation • Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2023 • Hernan Carrillo, Michaël Clément, Aurélie Bugeau, Edgar Simo-Serra
Colorization of line art drawings is an important task in illustration and animation workflows.
1 code implementation • CVPR 2023 • Naoto Inoue, Kotaro Kikuchi, Edgar Simo-Serra, Mayu Otani, Kota Yamaguchi
Creative workflows for generating graphical documents involve complex inter-related tasks, such as aligning elements, choosing appropriate fonts, or employing aesthetically harmonious colors.
1 code implementation • CVPR 2023 • Naoto Inoue, Kotaro Kikuchi, Edgar Simo-Serra, Mayu Otani, Kota Yamaguchi
Controllable layout generation aims at synthesizing plausible arrangement of element bounding boxes with optional constraints, such as type or position of a specific element.
1 code implementation • 22 Dec 2022 • Kotaro Kikuchi, Naoto Inoue, Mayu Otani, Edgar Simo-Serra, Kota Yamaguchi
The web page colorization problem is then formalized as a task of estimating plausible color styles for a given web page content with a given hierarchical structure of the elements.
no code implementations • 1 Dec 2022 • Yutaka Momma, Weimin WANG, Edgar Simo-Serra, Satoshi Iizuka, Ryosuke Nakamura, Hiroshi Ishikawa
To remedy this problem, we propose to explicitly train a network to refine these results predicted by an existing segmentation method.
1 code implementation • 2 Aug 2021 • Kotaro Kikuchi, Edgar Simo-Serra, Mayu Otani, Kota Yamaguchi
We optimize using the latent space of an off-the-shelf layout generation model, allowing our approach to be complementary to and used with existing layout generation models.
1 code implementation • Transactions on Graphics (SIGGRAPH) 2021 • Haoran Mo, Edgar Simo-Serra, Chengying Gao, Changqing Zou, Ruomei Wang
Vector line art plays an important role in graphic design, however, it is tedious to manually create.
no code implementations • CVPR 2021 • Lvmin Zhang, Chengze Li, Edgar Simo-Serra, Yi Ji, Tien-Tsin Wong, Chunping Liu
We present a deep learning framework for user-guided line art flat filling that can compute the "influence areas" of the user color scribbles, i. e., the areas where the user scribbles should propagate and influence.
no code implementations • 29 Sep 2020 • Naoto Masuzawa, Yoshiro Kitamura, Keigo Nakamura, Satoshi Iizuka, Edgar Simo-Serra
The input to the second networks have an auxiliary channel in addition to the 3D CT images.
no code implementations • 18 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.
no code implementations • 18 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.
2 code implementations • 25 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.
no code implementations • 9 Sep 2019 • Yosuke Shinya, Edgar Simo-Serra, Taiji Suzuki
Furthermore, we propose a method for automatically determining the widths (the numbers of channels) of object detectors based on the eigenspectrum.
no code implementations • 30 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.
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.
no code implementations • WS 2017 • Antonio Rubio Romano, LongLong Yu, Edgar Simo-Serra, Francesc Moreno-Noguer
Finding a product in the fashion world can be a daunting task.
no code implementations • 27 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.
3 code implementations • ACM Transactions on Graphics 2016 • Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Ishikawa
We present a novel technique to automatically colorize grayscale images that combines both global priors and local image features.
no code implementations • CVPR 2016 • Edgar Simo-Serra, Hiroshi Ishikawa
We propose a novel approach for learning features from weakly-supervised data by joint ranking and classification.
no code implementations • 14 Dec 2015 • Edgar Simo-Serra
Understanding humans from photographs has always been a fundamental goal of computer vision.
1 code implementation • ICCV 2015 • Edgar Simo-Serra, Eduard Trulls, Luis Ferraz, Iasonas Kokkinos, Pascal Fua, Francesc Moreno-Noguer
Deep learning has revolutionalized image-level tasks such as classification, but patch-level tasks, such as correspondence, still rely on hand-crafted features, e. g. SIFT.
Ranked #2 on Satellite Image Classification on SAT-4
no code implementations • NAACL 2016 • Ariadna Quattoni, Arnau Ramisa, Pranava Swaroop Madhyastha, Edgar Simo-Serra, Francesc Moreno-Noguer
We address the task of annotating images with semantic tuples.
no code implementations • Conference 2015 • Edgar Simo-Serra, Sanja Fidler, Francesc Moreno-Noguer, Raquel Urtasun
Importantly, our model is able to give rich feedback back to the user, conveying which garments or even scenery she/he should change in order to improve fashionability.
no code implementations • 19 Dec 2014 • Edgar Simo-Serra, Eduard Trulls, Luis Ferraz, Iasonas Kokkinos, Francesc Moreno-Noguer
In this paper we propose a novel framework for learning local image descriptors in a discriminative manner.
no code implementations • CVPR 2013 • Edgar Simo-Serra, Ariadna Quattoni, Carme Torras, Francesc Moreno-Noguer
We introduce a novel approach to automatically recover 3D human pose from a single image.
Ranked #25 on 3D Human Pose Estimation on HumanEva-I