Zobrazeno 1 - 10
of 55
pro vyhledávání: '"Lee, Seokju"'
Recent advances in large pre-trained vision-language models have demonstrated remarkable performance on zero-shot downstream tasks. Building upon this, recent studies, such as CoOp and CoCoOp, have proposed the use of prompt learning, where context w
Externí odkaz:
http://arxiv.org/abs/2404.16804
Text-guided non-rigid editing involves complex edits for input images, such as changing motion or compositions within their surroundings. Since it requires manipulating the input structure, existing methods often struggle with preserving object ident
Externí odkaz:
http://arxiv.org/abs/2402.08601
Autor:
Kim, Dunam, Lee, Seokju
Recent studies on generalizing CLIP for monocular depth estimation reveal that CLIP pre-trained on web-crawled data is inefficient for deriving proper similarities between image patches and depth-related prompts. In this paper, we adapt CLIP for mean
Externí odkaz:
http://arxiv.org/abs/2402.03251
Unsupervised domain adaptation (UDA) has been a potent technique to handle the lack of annotations in the target domain, particularly in semantic segmentation task. This study introduces a different UDA scenarios where the target domain contains unla
Externí odkaz:
http://arxiv.org/abs/2309.11711
Open compound domain adaptation (OCDA) considers the target domain as the compound of multiple unknown homogeneous subdomains. The goal of OCDA is to minimize the domain gap between the labeled source domain and the unlabeled compound target domain,
Externí odkaz:
http://arxiv.org/abs/2207.09045
Estimating the motion of the camera together with the 3D structure of the scene from a monocular vision system is a complex task that often relies on the so-called scene rigidity assumption. When observing a dynamic environment, this assumption is vi
Externí odkaz:
http://arxiv.org/abs/2110.06853
Autor:
Bangunharcana, Antyanta, Cho, Jae Won, Lee, Seokju, Kweon, In So, Kim, Kyung-Soo, Kim, Soohyun
Volumetric deep learning approach towards stereo matching aggregates a cost volume computed from input left and right images using 3D convolutions. Recent works showed that utilization of extracted image features and a spatially varying cost volume a
Externí odkaz:
http://arxiv.org/abs/2108.05773
Publikováno v:
IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 1103-1110, April 2022
A thermal camera can robustly capture thermal radiation images under harsh light conditions such as night scenes, tunnels, and disaster scenarios. However, despite this advantage, neither depth nor ego-motion estimation research for the thermal camer
Externí odkaz:
http://arxiv.org/abs/2103.00760
We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we highlight t
Externí odkaz:
http://arxiv.org/abs/2102.02629
Autor:
Zhang, Chaoning, Benz, Philipp, Argaw, Dawit Mureja, Lee, Seokju, Kim, Junsik, Rameau, Francois, Bazin, Jean-Charles, Kweon, In So
ResNet or DenseNet? Nowadays, most deep learning based approaches are implemented with seminal backbone networks, among them the two arguably most famous ones are ResNet and DenseNet. Despite their competitive performance and overwhelming popularity,
Externí odkaz:
http://arxiv.org/abs/2010.12496