6 papers
G-MASt3R-SfM: Graph-based View Pruning and Multi-stage Optimization for Robust SfM
Toshiki Watanabe, Shintaro Ito, Natsuki Takama +2
Structure from Motion (SfM) is essential for multi-view 3D reconstruction, however, its accuracy heavily relies on the accuracy of image matching. While the recent correspondence m…
ErpGS: Equirectangular Image Rendering enhanced with 3D Gaussian Regularization
Shintaro Ito, Natsuki Takama, Koichi Ito +2
The use of multi-view images acquired by a 360-degree camera can reconstruct a 3D space with a wide area. There are 3D reconstruction methods from equirectangular images based on N…
Stereo Radargrammetry Using Deep Learning from Airborne SAR Images
Tatsuya Sasayama, Shintaro Ito, Koichi Ito +1
In this paper, we propose a stereo radargrammetry method using deep learning from airborne Synthetic Aperture Radar (SAR) images. Deep learning-based methods are considered to suff…
Sparse2DGS: Sparse-View Surface Reconstruction using 2D Gaussian Splatting with Dense Point Cloud
Natsuki Takama, Shintaro Ito, Koichi Ito +2
Gaussian Splatting (GS) has gained attention as a fast and effective method for novel view synthesis. It has also been applied to 3D reconstruction using multi-view images and can…
Zero-Shot Pseudo Labels Generation Using SAM and CLIP for Semi-Supervised Semantic Segmentation
Nagito Saito, Shintaro Ito, Koichi Ito +1
Semantic segmentation is a fundamental task in medical image analysis and autonomous driving and has a problem with the high cost of annotating the labels required in training. To…
OB3D: A New Dataset for Benchmarking Omnidirectional 3D Reconstruction Using Blender
Shintaro Ito, Natsuki Takama, Toshiki Watanabe +3
Recent advancements in radiance field rendering, exemplified by Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), have significantly progressed 3D modeling and recons…