← Search

Itaru Kitahara

2 accepted papers

2025

Dual-S3D: Hierarchical Dual-Path Selective SSM-CNN for High-Fidelity Implicit Reconstruction

ICCV 2025poster

Single-view 3D reconstruction aims to recover the complete 3D geometry and appearance of objects from a single RGB image. Due to incomplete image information and ambiguity, this task remains challenging. Existing methods struggle with the trade-off between local detail and global topology, and with…

Cited by 0SourcePDFScholar
2022

Neural Density-Distance Fields

ECCV 2022poster

"The success of neural fields for 3D vision tasks is now indisputable. Following this trend, several methods aiming for visual localization (e.g., SLAM) have been proposed to estimate distance or density fields using neural fields. However, it is difficult to achieve high localization performance by…