10 accepted papers
Reliable place recognition is essential to SLAM, as it enables loop closure detection, re-localization, and map merging in long-term operation and multi-robot deployments. While semantic information enables a more human-like understanding of environments, only a few studies have integrated semantic
This paper addresses the Pitch Variation Problem in Two-Wheeled Self-Balancing (TWSB) robots that use 2D LiDAR for Simultaneous Localization And Mapping (SLAM). The issue arises from sudden accelerations or decelerations, leading to abrupt pitch variations that cause the 2D LiDAR to capture data fro…
The development of camera-based real-time 3D perception network for edge devices is essential for embodied systems such as autonomous vehicles and robots. However, existing methods often demand substantial computational resources and tend to overlook performance on resource-constrained devices. In t…
This paper addresses the Pitch Variation Problem in Two-Wheeled Self-Balancing (TWSB) robots that use 2D LiDAR for Simultaneous Localization And Mapping (SLAM). The issue arises from sudden accelerations or decelerations, leading to abrupt pitch variations that cause the 2D LiDAR to capture data fro
Recent studies show strong generative performance in domain translation especially by using transfer learning techniques on the unconditional generator. However, the control between different domain features using a single model is still challenging. Existing methods often require additional models,…
"While recent advances in generative models benefit the society, the generated images can be abused for malicious purposes, like fraud, defamation, and false news. To prevent such cases, vigorous research is conducted on distinguishing the generated images from the real ones, but challenges still re…
Various deepfake detectors have been proposed, but challenges still exist to detect images of unknown categories or GAN models outside of the training settings. Such issues arise from the overfitting issue, which we discover from our own analysis and the previous studies to originate from the frequ…
Modern neural speech enhancement models usually include various forms of phase information in their training loss terms, either explicitly or implicitly. However, these loss terms are typically designed to reduce the distortion of phase spectrum values at specific frequencies, which ensures they do…
With the development of 3D scanning technologies, 3D vision tasks have become a popular research area. Owing to the large amount of data acquired by sensors, unsupervised learning is essential for understanding and utilizing point clouds without an expensive annotation process. In this paper, we pro…
Generating a novel image by manipulating two input images is an interesting research problem in the study of generative adversarial networks (GANs). We propose a new GAN-based network that generates a fusion image with the identity of input image x and the shape of input image y. Our network can sim…