12 papers
LagrangeGS: Non-Conservative Lagrangian System on Dynamic 3D Gaussian Splatting
Shogo Sato, Takuhiro Kaneko, Shoichiro Takeda +4
Dynamic 3D Gaussian Splatting (3DGS) achieves photorealistic reconstruction of time-varying scenes, and recent physics-aware extensions improve extrapolation by explicitly predicti…
Probing Association Instability with Track-State Perturbations for Clip-Level Active Learning in Query-Propagation Multi-Object Tracking
Riku Inoue, Shogo Sato, Kazuhiko Murasaki +3
Training query-propagation end-to-end multi-object tracking (MOT) models requires dense bounding-box and identity annotations across video sequences, making dataset construction ex…
Clip-level Uncertainty and Temporal-aware Active Learning for End-to-End Multi-Object Tracking
Riku Inoue, Shogo Sato, Kazuhiko Murasaki +3
Multi-Object Tracking (MOT) in dynamic environments relies on robust temporal reasoning to maintain consistent object identities over time. Transformer-based end-to-end MOT models…
ComptonUNet: A Deep Learning Model for GRB Localization with Compton Cameras under Noisy and Low-Statistic Conditions
Shogo Sato, Kazuo Tanaka, Shojun Ogasawara +4
Gamma-ray bursts (GRBs) are among the most energetic transient phenomena in the universe and serve as powerful probes for high-energy astrophysical processes. In particular, faint…
Real-Time LiDAR Point Cloud Densification for Low-Latency Spatial Data Transmission
Kazuhiko Murasaki, Shunsuke Konagai, Masakatsu Aoki +2
To realize low-latency spatial transmission system for immersive telepresence, there are two major problems: capturing dynamic 3D scene densely and processing them in real time. Li…
Leveraging 2D-VLM for Label-Free 3D Segmentation in Large-Scale Outdoor Scene Understanding
Toshihiko Nishimura, Hirofumi Abe, Kazuhiko Murasaki +2
This paper presents a novel 3D semantic segmentation method for large-scale point cloud data that does not require annotated 3D training data or paired RGB images. The proposed app…
IPCD: Intrinsic Point-Cloud Decomposition
Shogo Sato, Takuhiro Kaneko, Shoichiro Takeda +5
Point clouds are widely used in various fields, including augmented reality (AR) and robotics, where relighting and texture editing are crucial for realistic visualization. Achievi…
Objective, Absolute and Hue-aware Metrics for Intrinsic Image Decomposition on Real-World Scenes: A Proof of Concept
Shogo Sato, Masaru Tsuchida, Mariko Yamaguchi +4
Intrinsic image decomposition (IID) is the task of separating an image into albedo and shade. In real-world scenes, it is difficult to quantitatively assess IID quality due to the…
LiM-Loc: Visual Localization with Dense and Accurate 3D Reference Maps Directly Corresponding 2D Keypoints to 3D LiDAR Point Clouds
Masahiko Tsuji, Hitoshi Niigaki, Ryuichi Tanida
Visual localization is to estimate the 6-DOF camera pose of a query image in a 3D reference map. We extract keypoints from the reference image and generate a 3D reference map with…
MultiBARF: Integrating Imagery of Different Wavelength Regions by Using Neural Radiance Fields
Kana Kurata, Hitoshi Niigaki, Xiaojun Wu +1
Optical sensor applications have become popular through digital transformation. Linking observed data to real-world locations and combining different image sensors is essential to…
Memory-Efficient Point Cloud Registration via Overlapping Region Sampling
Tomoyasu Shimada, Kazuhiko Murasaki, Shogo Sato +3
Recent advances in deep learning have improved 3D point cloud registration but increased graphics processing unit (GPU) memory usage, often requiring preliminary sampling that redu…
Unsupervised Intrinsic Image Decomposition with LiDAR Intensity Enhanced Training
Shogo Sato, Takuhiro Kaneko, Kazuhiko Murasaki +3
Unsupervised intrinsic image decomposition (IID) is the process of separating a natural image into albedo and shade without these ground truths. A recent model employing light dete…