5 papers
High-fidelity Multi-view Normal Integration with Scale-encoded Neural Surface Representation
Tongyu Yang, Heng Guo, Yasuyuki Matsushita +3
Previous multi-view normal integration methods typically sample a single ray per pixel, without considering the spatial area covered by each pixel, which varies with camera intrins…
Near-light Photometric Stereo with Symmetric Lights
Lilika Makabe, Heng Guo, Hiroaki Santo +2
This paper describes a linear solution method for near-light photometric stereo by exploiting symmetric light source arrangements. Unlike conventional non-convex optimization appro…
NeuraLeaf: Neural Parametric Leaf Models with Shape and Deformation Disentanglement
Yang Yang, Dongni Mao, Hiroaki Santo +2
We develop a neural parametric model for 3D leaves for plant modeling and reconstruction that are essential for agriculture and computer graphics. While neural parametric models ar…
Spectral Sensitivity Estimation with an Uncalibrated Diffraction Grating
Lilika Makabe, Hiroaki Santo, Fumio Okura +2
This paper introduces a practical and accurate calibration method for camera spectral sensitivity using a diffraction grating. Accurate calibration of camera spectral sensitivity i…
HoGS: Unified Near and Far Object Reconstruction via Homogeneous Gaussian Splatting
Xinpeng Liu, Zeyi Huang, Fumio Okura +1
Novel view synthesis has demonstrated impressive progress recently, with 3D Gaussian splatting (3DGS) offering efficient training time and photorealistic real-time rendering. Howev…