6 papers
Do We Still Need Rotation-Invariant Architectures? A Statistical Robustness Benchmark for Point Cloud Classification
Abdulla Nasir Chowdhury, Gulpi Qorik Oktagalu Pratamasunu, Kazuhiro Fukui
A substantial line of work builds rotation invariance directly into point cloud architectures. We benchmark 10 architectures (PointNet, PointNet++, DGCNN, RIConv, RIConv++, RISurCo…
Two-point residual step size gradient methods for linear systems
Xin Xu
Kaczmarz-type methods often converge slowly when the coefficient matrix is ill-conditioned. In particular, when the smallest singular value is small, every row of the coefficient m…
InstructionCrafter: Generating Consistent and High-Fidelity Visual Instructions
Shun Okamoto, Satoshi Iizuka, Kazuhiro Fukui
Given textual task instructions, generating step-by-step visual instructions as an image sequence requires the simultaneous satisfaction of multiple properties, specifically step f…
Improving Image-to-Image Translation via a Rectified Flow Reformulation
Satoshi Iizuka, Shun Okamoto, Kazuhiro Fukui
In this work, we propose Image-to-Image Rectified Flow Reformulation (I2I-RFR), a practical plug-in reformulation that recasts standard I2I regression networks as continuous-time t…
Separability Membrane: 3D Active Contour for Point Cloud Surface Reconstruction
Gulpi Qorik Oktagalu Pratamasunu, Guoqing Hao, Kazuhiro Fukui
This paper proposes Separability Membrane, a robust 3D active contour for extracting a surface from 3D point cloud object. Our approach defines the surface of a 3D object as the bo…
Point Cloud Novelty Detection Based on Latent Representations of a General Feature Extractor
Shizuka Akahori, Satoshi Iizuka, Ken Mawatari +1
We propose an effective unsupervised 3D point cloud novelty detection approach, leveraging a general point cloud feature extractor and a one-class classifier. The general feature e…