Taiga Yoshida
YOU?
Author Swipe
View article: Objective, Absolute and Hue-aware Metrics for Intrinsic Image Decomposition on Real-World Scenes: A Proof of Concept
Objective, Absolute and Hue-aware Metrics for Intrinsic Image Decomposition on Real-World Scenes: A Proof of Concept Open
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 unavailability of ground truth. The existing method provide…
View article: Leveraging 2D-VLM for Label-Free 3D Segmentation in Large-Scale Outdoor Scene Understanding
Leveraging 2D-VLM for Label-Free 3D Segmentation in Large-Scale Outdoor Scene Understanding Open
View article: Real-Time LiDAR Point Cloud Densification for Low-Latency Spatial Data Transmission
Real-Time LiDAR Point Cloud Densification for Low-Latency Spatial Data Transmission Open
View article: Memory-Efficient Point Cloud Registration via Overlapping Region Sampling
Memory-Efficient Point Cloud Registration via Overlapping Region Sampling Open
Recent advances in deep learning have improved 3D point cloud registration but increased graphics processing unit (GPU) memory usage, often requiring preliminary sampling that reduces accuracy. We propose an overlapping region sampling met…
View article: Unsupervised Intrinsic Image Decomposition with LiDAR Intensity Enhanced Training
Unsupervised Intrinsic Image Decomposition with LiDAR Intensity Enhanced Training Open
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 detection and ranging (LiDAR) intensity demonstrated impressive…
View article: Shadow Detection Based on Luminance-LiDAR Intensity Uncorrelation
Shadow Detection Based on Luminance-LiDAR Intensity Uncorrelation Open
In recent years, there has been a growing demand for urban digitization using cameras and light detection and ranging (LiDAR). Shadows are a condition that affects measurement the most. Therefore, shadow detection technology is essential. …
View article: Unsupervised Intrinsic Image Decomposition with LiDAR Intensity
Unsupervised Intrinsic Image Decomposition with LiDAR Intensity Open
Intrinsic image decomposition (IID) is the task that decomposes a natural image into albedo and shade. While IID is typically solved through supervised learning methods, it is not ideal due to the difficulty in observing ground truth albed…
View article: [Invited Paper] Spatial Verification via Pairwise Geometric Constraints and 3D View-Directional Voting
[Invited Paper] Spatial Verification via Pairwise Geometric Constraints and 3D View-Directional Voting Open
Existing instance search methods based on spatial verification still suffer from limited efficiency and large 3D viewpoint changes. To address these issues, we newly incorporate two spatial verification methods in local feature-based insta…
View article: View-Directional Consistency Constraints for Robust 3D Object Recognition (Special Issue on Computer Vision and Applications)
View-Directional Consistency Constraints for Robust 3D Object Recognition (Special Issue on Computer Vision and Applications) Open