Takafumi Iwaguchi
YOU?
Author Swipe
View article: Geometry-aware deblurring of blur caused by a diffuser using 3D Gaussian splatting
Geometry-aware deblurring of blur caused by a diffuser using 3D Gaussian splatting Open
Objects behind a diffuser are observed with varying blur depending on their location and the viewpoint, making the recovery of the clear scene challenging. Unlike defocus or motion blur, the blurring caused by a diffuser is a phenomenon th…
View article: ActiveNeuS: Neural Signed Distance Fields for Active Stereo
ActiveNeuS: Neural Signed Distance Fields for Active Stereo Open
3D-shape reconstruction in extreme environments, such as low illumination or scattering condition, has been an open problem and intensively researched. Active stereo is one of potential solution for such environments for its robustness and…
View article: Neural Active Structure-from-Motion in Dark and Textureless Environment
Neural Active Structure-from-Motion in Dark and Textureless Environment Open
Active 3D measurement, especially structured light (SL) has been widely used in various fields for its robustness against textureless or equivalent surfaces by low light illumination. In addition, reconstruction of large scenes by moving t…
View article: Underwater Image Enhancement by Transformer-based Diffusion Model with Non-uniform Sampling for Skip Strategy
Underwater Image Enhancement by Transformer-based Diffusion Model with Non-uniform Sampling for Skip Strategy Open
In this paper, we present an approach to image enhancement with diffusion model in underwater scenes. Our method adapts conditional denoising diffusion probabilistic models to generate the corresponding enhanced images by using the underwa…
View article: Virtual myocardial PET generated from deep learning of SPECT and PET datasets: potential for attenuation correction in CT-less SPECT
Virtual myocardial PET generated from deep learning of SPECT and PET datasets: potential for attenuation correction in CT-less SPECT Open
Objective Deep-learning approaches have attracted attention for improving the scoring accuracy in computed tomography-less single photon emission computerized tomography (SPECT). This study evaluated the improvement in visual ischemia scor…
View article: High-frequency shape recovery from shading by CNN and domain adaptation
High-frequency shape recovery from shading by CNN and domain adaptation Open
Importance of structured-light based one-shot scanning technique is increasing because of its simple system configuration and ability of capturing moving objects. One severe limitation of the technique is that it can capture only sparse sh…
View article: Programmable Non-Epipolar Indirect Light Transport: Capture and Analysis
Programmable Non-Epipolar Indirect Light Transport: Capture and Analysis Open
The decomposition of light transport into direct and global components, diffuse and specular interreflections, and subsurface scattering allows for new visualizations of light in everyday scenes. In particular, indirect light contains a my…
View article: Optical tomography based on shortest-path model for diffuse surface object
Optical tomography based on shortest-path model for diffuse surface object Open
We tackle an optical measurement of the internal structure of a diffuse surface object—we define as an object that has a diffuse surface and its interior is transparent, like grapes or hollow plastic bottles. Our approach is based on optic…
View article: Light path alignment for computed tomography of scattering material
Light path alignment for computed tomography of scattering material Open
We aim to estimate internal slice of the scattering material by Computed Tomography (CT). In the scattering material, the light path is disturbed and is spread. Conventional CT cannot measure the scattering material because they rely on th…