Hiroshi Kawasaki 研究室

主宰者：Hiroshi Kawasaki

九州大学

AI 要約（直近 5 年の研究成果）

川崎研究室では、困難な環境での高精度な3次元計測と画像復元を実現する方法の開発に取り組んでいます。対象とする環境は多岐にわたり、水中撮影、医療用内視鏡、霜がかったガラス越し、低照度環境など、通常のカメラでは正確な測定が難しい状況が含まれます。研究では、パターン光投影による構造化照明や能動的ステレオなど、光の性質を制御・利用した計測手法を基盤としています。実装面では、深層学習やニューラル表現（神経符号距離場やガウシアンスプラッティングなど）、逆レンダリングといった最新の計算手法を組み合わせることで、少ない観測データからの正確な3次元復元を可能にしています。特に医療応用では、微小なパターン投影器を内視鏡に組み込むシステムを開発し、術中のリアルタイム3次元計測と拡張現実表示に活用できる段階に進んでいます。さらに、水中環境での画像改善やテクスチャレス物体の復元、複数フレームを統合した姿勢最適化など、個々の課題に対して専門化したアルゴリズムを提案しており、基礎研究から実用的な応用まで幅広い段階で研究を展開しています。

※ AI（Claude）が、公開されている論文要旨から研究の問い・手法・主要な発見を事実情報として抽出・再構成して自動生成しています。誤りを含む可能性があるため、正確性は研究室公式情報でご確認ください。

外部リンク

研究成果（42 件）

[2026] Depth Estimation in Scattering Media due to Synchronization Delay in Projector Camera Systems
DOI: https://doi.org/10.5220/0014404900004084
[2026] Learning Underwater Image Enhancement Iteratively Without Reference Images
DOI: https://doi.org/10.1609/aaai.v40i11.37906
[2025] Geometry-aware deblurring of blur caused by a diffuser using 3D Gaussian splatting
DOI: https://doi.org/10.1364/oe.571109
[2025] ShadowSG: Spherical Gaussian Illumination from Shadows
DOI: https://doi.org/10.1109/3dv66043.2025.00106
[2025] Neural SDF for Shadow-Aware Unsupervised Structured Light
DOI: https://doi.org/10.1109/wacv61041.2025.00038
[2025] Acquiring Aligned Endoscopic and Depth Image Pairs Using Structured‐Light Projection, Neural Surfaces and an Electromagnetic Positional Sensor
DOI: https://doi.org/10.1049/htl2.70039
[2024] View Synthesis of Endoscope Images by Monocular Depth Prediction and Gaussian Splatting
DOI: https://doi.org/10.1109/embc53108.2024.10782148
[2024] Calibration‐free structured‐light‐based 3D scanning system in laparoscope for robotic surgery
DOI: https://doi.org/10.1049/htl2.12083
[2024] ActiveNeuS: Neural Signed Distance Fields for Active Stereo
DOI: https://doi.org/10.1109/3dv62453.2024.00014
[2024] Specular Object Reconstruction Behind Frosted Glass by Differentiable Rendering
DOI: https://doi.org/10.1109/wacv57701.2024.00400

続きを表示（残り 32 件）

[2024] Braking Detection and Prediction with Inter-vehicle Distance Estimated from Driving Videos
DOI: https://doi.org/10.1007/s13177-024-00449-6
[2024] Two-stage pose optimization algorithm using color information for underwater SLAM with light-sectioning-based 3D scanning method
DOI: https://doi.org/10.1109/iros58592.2024.10801859
[2024] Gated SPECT-Derived Myocardial Strain Estimated From Deep-Learning Image Translation Validated From N-13 Ammonia PET
DOI: https://doi.org/10.1016/j.acra.2024.06.047
[2024] NeRF-based multi-frame 3D integration for 3D endoscopy using active stereo
DOI: https://doi.org/10.1109/embc53108.2024.10782699
[2023] Deep learning approach using SPECT-to-PET translation for attenuation correction in CT-less myocardial perfusion SPECT imaging
DOI: https://doi.org/10.1007/s12149-023-01889-y
[2023] Scale‐preserving shape reconstruction from monocular endoscope image sequences by supervised depth learning
DOI: https://doi.org/10.1049/htl2.12064
[2023] Underwater Image Enhancement by Transformer-based Diffusion Model with Non-uniform Sampling for Skip Strategy
DOI: https://doi.org/10.1145/3581783.3612378
[2023] Online Adaptive Disparity Estimation for Dynamic Scenes in Structured Light Systems
DOI: https://doi.org/10.1109/iros55552.2023.10342000
[2023] ACT2G
DOI: https://doi.org/10.1145/3606940
[2023] Single and multi-frame auto-calibration for 3D endoscopy with differential rendering
DOI: https://doi.org/10.1109/embc40787.2023.10340381
[2023] Generalization of pixel-wise phase estimation by CNN and improvement of phase-unwrapping by MRF optimization for one-shot 3D scan
DOI: https://doi.org/10.23919/mva57639.2023.10215780
[2023] Surface normal estimation from optimized and distributed light sources using DNN-based photometric stereo
DOI: https://doi.org/10.1109/wacv56688.2023.00039
[2022] Acquisition and Visualization of Micro-Vibration of a Sound Wave in 3D Space
DOI: https://doi.org/10.20965/jrm.2022.p1024
[2022] Single-shot dense active stereo with pixel-wise phase estimation based on grid-structure using CNN and correspondence estimation using GCN
DOI: https://doi.org/10.1109/wacv51458.2022.00032
[2022] Robust Calibration-Marker and Laser-Line Detection For Underwater 3d Shape Reconstruction By Deep Neural Network
DOI: https://doi.org/10.1109/icip46576.2022.9897733
[2022] Auto-augmentation with Differentiable Renderer for High-frequency Shape Recovery
DOI: https://doi.org/10.1109/icpr56361.2022.9956528
[2022] 3D endoscope system with AR display superimposing dense and wide-angle-of-view 3D points obtained by using micro pattern projector
DOI: https://doi.org/10.1109/embc48229.2022.9871060
[2022] TIDE: Temporally Incremental Disparity Estimation via Pattern Flow in Structured Light System
DOI: https://doi.org/10.1109/lra.2022.3150029
[2022] Integration of Gesture Generation System Using Gesture Library with DIY Robot Design Kit
DOI: https://doi.org/10.1109/sii52469.2022.9708837
[2022] Refining OpenPose with a new sports dataset for robust 2D pose estimation
DOI: https://doi.org/10.1109/wacvw54805.2022.00074
[2022] Multi-frame optimisation for active stereo with inverse renderingto obtain consistent shape and projector-camera posesfor 3D endoscopic system
DOI: https://doi.org/10.1080/21681163.2022.2155578
[2021] Challenges on Active 3D Scan for Ultra-Fast Motion, Micro Scale and Extreme Environment
DOI: https://doi.org/10.2493/jjspe.87.656
[2021] Unsupervised 3D Human Pose Estimation in Multi-view-multi-pose Video
DOI: https://doi.org/10.1109/icpr48806.2021.9412270
[2021] Information Hiding Using a Coded Aperture as a Key
DOI: https://doi.org/10.23919/mva51890.2021.9511375
[2021] High-Resolution Image Data Collection Scheme for Road Sensing Using Wide-Angle Cameras on General-Use Vehicle Criteria to Include/Exclude Collected Images for Super Resolution
DOI: https://doi.org/10.1007/s13177-020-00243-0
[2021] Simultaneous estimation of projector and camera poses for multiple oneshot scan using pixel-wise correspondences estimated by U-Nets and GCN
DOI: https://doi.org/10.1080/21681163.2021.2009376
[2021] Active Stereo Method for 3D Endoscopes using Deep-layer GCN and Graph Representation with Proximity Information
DOI: https://doi.org/10.1109/embc46164.2021.9629696
[2021] Efficient light transport acquisition by coded illumination and robust photometric stereo by dual photography using deep neural network
DOI: https://doi.org/10.1109/iccvw54120.2021.00136
[2021] PoseRN: A 2D Pose Refinement Network For Bias-Free Multi-View 3D Human Pose Estimation
DOI: https://doi.org/10.1109/icip42928.2021.9506022
[2021] Self-calibrated dense 3D sensor using multiple cross line-lasers based on light sectioning method and visual odometry
DOI: https://doi.org/10.1109/iros51168.2021.9636505
[2021] High-Frequency Shape Recovery from Shading by CNN and Domain Adaptation
DOI: https://doi.org/10.1109/icip42928.2021.9506450
[2021] A Method for Adding Motion-Blur on Arbitrary Objects by Using Auto-Segmentation and Color Compensation Techniques
DOI: https://doi.org/10.1109/icip42928.2021.9506443

科研費（0 件）

まだデータがありません（KAKEN 取り込み後に表示）。

所属学会・役職（0 件）

まだデータがありません（学会データ連携後に表示）。

AI 要約（直近 5 年の研究成果）

外部リンク

関連研究室(8 件)

研究成果（42 件）

科研費（0 件）

所属学会・役職（0 件）