News

Research

当研究室では、コンピュータ・グラフィクスとコンピュータ・ビジョンの分野を中心に、実世界を二次元的・三次元的にスキャンして得られる写真・動画・形状のデータを処理して、より目的に合った形で高品質化したり、可視化したりする技術について研究しています。以下では、最近行った研究をご紹介しております。

全てのプロジェクトは、メニューの[RESEARCH]からご覧ください。

当研究室への配属を希望で、卒業研究や修士課程・博士課程での研究について知りたい方はメニューの[JOIN US]をご覧ください。

Event-Based Camera Simulation Using Monte Carlo Path Tracing with Adaptive Denoising

graphics

rendering

出典: Yuta Tsuji, Tatsuya Yatagawa, Hiroyuki Kubo, Shigeo Morishima, "Event-Based Camera Simulation Using Monte Carlo Path Tracing with Adaptive Denoising," IEEE International Conference on Image Processing 2023.

End-to-End Deep Learning for Reconstructing Segmented 3D CT Image from Multi-Energy X-ray Projections

applications

NDT

出典: Siqi Wang, Tatsuya Yatagawa, Yutaka Ohtake, Toru Aoki, Jun Hotta, "End-to-End Deep Learning for Reconstructing Segmented 3D CT Image from Multi-Energy X-ray Projections," IEEE/CVF Conference on Computer Vision Workshop 2023.

Sparse-View Cone-Beam CT Reconstruction by Bar-by-Bar Neural FDK Algorithm

applications

NDT

出典: Siqi Wang, Tatsuya Yatagawa, Yutaka Ohtake, Hiromasa Suzuki, "Sparse-View Cone-Beam CT Reconstruction by Bar-by-Bar Neural FDK Algorithm," Nondestructive Testing and Evaluation (2023).

Bin-scanning: Segmentation of X-ray CT volume of binned parts using Morse skeleton graph of distance transform

graphics

geometry

applications

出典: Yuta Yamauchi, Tatsuya Yatagawa, Yutaka Ohtake, Hiromasa Suzuki, "Bin-scanning: Segmentation of X-ray CT volume of binned parts using Morse skeleton graph of distance transform," Computational Visual Media (2023).

Learning Self-prior for Mesh Denoising using Dual Graph Convolutional Networks

graphics

geometry

deep learning

出典: Shota Hattori, Tatsuya Yatagawa, Yutaka Ohtake, Hiromasa Suzuki, "Learning Self-prior for Mesh Denoising using Dual Graph Convolutional Networks," European Conference on Computer Vision 2022.

Access