研究プロジェクト

	Diffusion-based Holistic Texture Rectification and Synthesis —拡散モデルを用いたテクスチャの歪み補正と欠損除去— Guoqing Hao, Satoshi Iizuka, Kensho Hara, Edgar Simo-Serra, Hirokatsu Kataoka, Kazuhiro Fukui SIGGRAPH Asia 2023 (Conference Papers) [プロジェクトページ]
	Controllable Multi-domain Semantic Artwork Synthesis —レイアウト情報からの高品質絵画生成— Yuantian Huang, Satoshi Iizuka, Edgar Simo-Serra, Kazuhiro Fukui Computational Visual Media 2023 [プロジェクトページ]
	Diffusion-based Semantic Image Synthesis from Sparse Layouts —スパースなレイアウト情報からの画像生成— Yuantian Huang, Satoshi Iizuka, Kazuhiro Fukui Computer Graphics International 2023 [プロジェクトページ]
	Free-View Expressive Talking Head Video Editing —動画中の発話している人物の自由な顔編集— Yuantian Huang, Satoshi Iizuka, Kazuhiro Fukui ICASSP 2023 (top 3% paper) [プロジェクトページ]
	Visual Grounding of Whole Radiology Reports for 3D CT Images Akimichi Ichinose, Taro Hatsutani, Keigo Nakamura, Yoshiro Kitamura, Satoshi Iizuka, Edgar Simo-Serra, Shoji Kido, Noriyuki Tomiyama MICCAI 2023 [論文]
	Skeleton-aware Text Image Super-Resolution —スケルトンロスを用いたテキスト画像の超解像— Shimon Nakaune, Satoshi Iizuka, Kazuhiro Fukui BMVC 2021
	Automatic Segmentation, Localization, and Identiﬁcation of Vertebrae in 3D CT Images Using Cascaded Convolutional Neural Networks —3次元CT画像のセグメンテーション、ローカライゼーション、および識別の同時推定— Naoto Masuzawa, Yoshiro Kitamura, Keigo Nakamura, Satoshi Iizuka, Edgar Simo-Serra MICCAI 2020
	TopNet: Topology Preserving Metric Learning for Vessel Tree Reconstruction and Labelling —トポロジーを保持した距離学習による血管樹の再構成とラベリング— Deepak Keshwani, Yoshiro Kitamura, Satoshi Ihara, Satoshi Iizuka, Edgar Simo-Serra MICCAI 2020
	Image Harmonization with Attention-based Deep Feature Modulation —注意機構ベースの特徴マップ補正による自然な画像合成— Hao Guoqing, Satoshi Iizuka, Kazuhiro Fukui BMVC 2020 [プロジェクトページ]
	DeepRemaster: Temporal Source-Reference Attention Networks for Comprehensive Video Enhancement —深層学習による動画のデジタルリマスター— Satoshi Iizuka, Edgar Simo-Serra SIGGRAPH Asia 2019 [プロジェクトページ] [BibTex]
	Virtual Thin Slice: 3D Conditional GAN-based Super-resolution for CT Slice Interval —3次元敵対的ネットワークによるCT画像の超解像— Akira Kudo, Yoshiro Kitamura, Yuanzhong Li, Satoshi Iizuka, Edgar Simo-Serra MICCAI Workshop 2019 [論文]
	MLSNet: Resource-efficient Adaptive Inference with Multi-level Segmentation Networks —セマンティックセグメンテーションにおけるリソース制約を考慮した適応的推定— Shuhei Yokoo, Satoshi Iizuka, Kazuhiro Fukui IEEE International Conference on Image Processing (ICIP) 2019
	Optimization-Based Data Generation for Photo Enhancement —画像補正の学習のための最適化を用いたデータ生成— Mayu Omiya, Yusuke Horiuchi, Edgar Simo-Serra, Satoshi Iizuka, Hiroshi Ishikawa IEEE Conference in Computer Vision and Pattern Recognition Workshops (CVPRW) 2019
	Temporal Distance Matrices for Squat Classification —時系列距離行列を用いたスクワット分類— Ryoji Ogata, Edgar Simo-Serra, Satoshi Iizuka, Hiroshi Ishikawa IEEE Conference in Computer Vision and Pattern Recognition Workshops (CVPRW) 2019
	Re-staining Pathology Images by FCNN —CNNによる病理画像の染色変換— Masayuki Fujitani, Yoshihiko Mochizuki, Satoshi Iizuka, Edgar Simo-Serra, Hirokazu Kobayashi, Chika Iwamoto, Kenoki Ohuchida, Makoto Hashizume, Hidekata Hontani, Hiroshi Ishikawa International Conference on Machine Vision Applications (MVA) 2019
	Spectral Normalization and Relativistic Adversarial Training for Conditional Pose Generation with Self-Attention —姿勢で条件付けた人物全身画像の生成におけるSelf-Attentionの活用と学習— Yusuke Horiuchi, Edgar Simo-Serra, Satoshi Iizuka, Hiroshi Ishikawa International Conference on Machine Vision Applications (MVA) 2019
	Learning Photo Enhancement by Black-Box Model Optimization Data Generation —深層学習による写真の自動補正— Mayu Omiya, Edgar Simo-Serra, Satoshi Iizuka, Hiroshi Ishikawa SIGGRAPH Asia 2018 Technical Brief
	Real-Time Data-Driven Interactive Rough Sketch Inking —データ駆動型の対話的なペン入れ— Edgar Simo-Serra, Satoshi Iizuka, Hiroshi Ishikawa SIGGRAPH 2018 [プロジェクトページ] [BibTex]
	Learning to Restore Deteriorated Line Drawing —古い線画の自動修復— Kazuma Sasaki, Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Ishikawa Computer Graphics International 2018 [プロジェクトページ] [BibTex]
	Mastering Sketching: Adversarial Augmentation for Structured Prediction —敵対的データ拡張による自動線画化— Edgar Simo-Serra, Satoshi Iizuka, Hiroshi Ishikawa (equal contribution) ACM Transactions on Graphics* [プロジェクトページ] [BibTex]
	Adaptive Energy Selection For Content-Aware Image Resizing —CNNを用いた画像のリサイズ— Kazuma Sasaki, Yuya Nagahama, Zheng Ze, Satoshi Iizuka, Edgar Simo-Serra, Yoshihiko Mochizuki, Hiroshi Ishikawa ACPR 2017
	What Makes a Style: Experimental Analysis of Fashion Prediction —機械学習によるファッションの理解— Moeko Takagi, Edgar Simo-Serra, Satoshi Iizuka, Hiroshi Ishikawa ICCV 2017 Workshop [論文(4.9MB)] [データセット]
	Recurrent Residual Network for Aerial Image Segmentation —航空写真のセグメンテーション— Koki Takahashi, Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Ishikawa
	Deep Mario —ディープマリオ— Ryutaro Kitagawa, Edgar Simo-Serra, Satoshi Iizuka, Yoshihiko Mochizuki, Hiroshi Ishikawa
	Globally and Locally Consistent Image Completion —複雑な画像補完— Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Ishikawa SIGGRAPH 2017 [プロジェクトページ] [BibTex]
	Joint Gap Detection and Inpainting of Line Drawings —線画の自動補完— Kazuma Sasaki, Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Ishikawa CVPR 2017 [プロジェクトページ] [BibTex]
	Detection by Classification of Buildings in Multispectral Satellite Imagery —衛星画像の地物認識— Tomohiro Ishii, Edgar Simo-Serra, Satoshi Iizuka, Yoshihiko Mochizuki, Akihiro Sugimoto, Hiroshi Ishikawa, Ryosuke Nakamura ICPR 2016 (Oral presentation) [プロジェクトページ] [BibTex]
	Room Reconstruction from a Single Spherical Image by Higher-order Energy Minimization —高階エネルギー最適化による球面画像からの部屋の3次元復元— Kosuke Fukano, Yoshihiko Mochizuki, Edgar Simo-Serra, Satoshi Iizuka, Akihiro Sugimoto, Hiroshi Ishikawa ICPR 2016 [BibTex]
	Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification —白黒写真の自動色付け— Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Ishikawa (equal contribution) SIGGRAPH 2016* [プロジェクトページ] [BibTex]
	Learning to Simplify: Fully Convolutional Networks for Rough Sketch Cleanup —ラフスケッチの自動線画化— Edgar Simo-Serra, Satoshi Iizuka, Kazuma Sasaki, Hiroshi Ishikawa (equal contribution) SIGGRAPH 2016* [プロジェクトページ] [BibTex]
	Single Image Weathering via Exemplar Propagation —物体表面のテクスチャ変化を伴う画像の経年変化の再現— Satoshi Iizuka, Yuki Endo, Yoshihiro Kanamori, Jun Mitani Eurographics 2016 [プロジェクトページ] [BibTex]
	DeepProp: Extracting Deep Features from a Single Image for Edit Propagation Yuki Endo, Satoshi Iizuka, Yoshihiro Kanamori, Jun Mitani Eurographics 2016 [プロジェクトページ] [BibTex]
	Efficient Depth Propagation for Constructing a Layered Depth Image from a Single Image —スパースなデプス入力による1枚の画像からの3次元モデルの生成— Satoshi Iizuka, Yuki Endo, Yoshihiro Kanamori, Jun Mitani, Yukio Fukui Pacific Graphics 2014 [プロジェクトページ] [BibTex]
	Object Repositioning Based on the Perspective in a Single Image —シーンの奥行きを考慮した景観画像における対話的なオブジェクト再配置— Satoshi Iizuka, Yuki Endo, Masaki Hirose, Yoshihiro Kanamori, Jun Mitani, Yukio Fukui Computer Graphics Forum (presented at Eurographics 2015) [プロジェクトページ] [BibTex]
	Efficiently Modeling 3D Scenes from a Single Image —1枚の景観画像からの効率的な3Dシーンの生成— Satoshi Iizuka, Yoshihiro Kanamori, Jun Mitani, Yukio Fukui IEEE Computer Graphics & Applications [プロジェクトページ] [BibTex]
	An Interactive Design System for Pop-Up Cards with a Physical Simulation - 物理シミュレーションを用いたポップアップカード設計支援システム - Satoshi Iizuka, Yuki Endo, Jun Mitani, Yoshihiro Kanamori, Yukio Fukui Computer Graphics International 2011 [プロジェクトページ] [BibTex]