Zobrazeno 1 - 10
of 285
pro vyhledávání: '"Kim, Euntai"'
Learning efficient representations of local features is a key challenge in feature volume-based 3D neural mapping, especially in large-scale environments. In this paper, we introduce Decomposition-based Neural Mapping (DNMap), a storage-efficient lar
Externí odkaz:
http://arxiv.org/abs/2407.15554
Neural Radiance Fields (NeRF) presented a novel way to represent scenes, allowing for high-quality 3D reconstruction from 2D images. Following its remarkable achievements, global localization within NeRF maps is an essential task for enabling a wide
Externí odkaz:
http://arxiv.org/abs/2406.12202
We present a novel, training-free approach to scene change detection. Our method leverages tracking models, which inherently perform change detection between consecutive frames of video by identifying common objects and detecting new or missing objec
Externí odkaz:
http://arxiv.org/abs/2406.11210
Targetless IMU-LiDAR extrinsic calibration methods are gaining significant attention as the importance of the IMU-LiDAR fusion system increases. Notably, existing calibration methods derive calibration parameters under the assumption that the methods
Externí odkaz:
http://arxiv.org/abs/2312.14035
We propose a novel solution for unpaired image-to-image (I2I) translation. To translate complex images with a wide range of objects to a different domain, recent approaches often use the object annotations to perform per-class source-to-target style
Externí odkaz:
http://arxiv.org/abs/2301.04685
The network trained for domain adaptation is prone to bias toward the easy-to-transfer classes. Since the ground truth label on the target domain is unavailable during training, the bias problem leads to skewed predictions, forgetting to predict hard
Externí odkaz:
http://arxiv.org/abs/2211.02307
Recent studies made great progress in video matting by extending the success of trimap-based image matting to the video domain. In this paper, we push this task toward a more practical setting and propose One-Trimap Video Matting network (OTVM) that
Externí odkaz:
http://arxiv.org/abs/2207.13353
Geometric verification is considered a de facto solution for the re-ranking task in image retrieval. In this study, we propose a novel image retrieval re-ranking network named Correlation Verification Networks (CVNet). Our proposed network, comprisin
Externí odkaz:
http://arxiv.org/abs/2204.01458
We present a new domain generalized semantic segmentation network named WildNet, which learns domain-generalized features by leveraging a variety of contents and styles from the wild. In domain generalization, the low generalization ability for unsee
Externí odkaz:
http://arxiv.org/abs/2204.01446
Unsupervised video object segmentation (UVOS) is a per-pixel binary labeling problem which aims at separating the foreground object from the background in the video without using the ground truth (GT) mask of the foreground object. Most of the previo
Externí odkaz:
http://arxiv.org/abs/2112.12402