Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Shim, Dongseok"'
Object removal refers to the process of erasing designated objects from an image while preserving the overall appearance, and it is one area where image inpainting is widely used in real-world applications. The performance of an object remover is qua
Externí odkaz:
http://arxiv.org/abs/2404.11104
The objective of the image inpainting task is to fill missing regions of an image in a visually plausible way. Recently, deep-learning-based image inpainting networks have generated outstanding results, and some utilize their models as object remover
Externí odkaz:
http://arxiv.org/abs/2305.07857
As previous representations for reinforcement learning cannot effectively incorporate a human-intuitive understanding of the 3D environment, they usually suffer from sub-optimal performances. In this paper, we present Semantic-aware Neural Radiance F
Externí odkaz:
http://arxiv.org/abs/2301.11520
Autor:
Shim, Dongseok, Kim, H. Jin
Monocular depth estimation plays a critical role in various computer vision and robotics applications such as localization, mapping, and 3D object detection. Recently, learning-based algorithms achieve huge success in depth estimation by training mod
Externí odkaz:
http://arxiv.org/abs/2301.06715
Thanks to the development of 2D keypoint detectors, monocular 3D human pose estimation (HPE) via 2D-to-3D uplifting approaches have achieved remarkable improvements. Still, monocular 3D HPE is a challenging problem due to the inherent depth ambiguiti
Externí odkaz:
http://arxiv.org/abs/2212.02796
Offline reinforcement learning (Offline RL) suffers from the innate distributional shift as it cannot interact with the physical environment during training. To alleviate such limitation, state-based offline RL leverages a learned dynamics model from
Externí odkaz:
http://arxiv.org/abs/2209.15256
Super-resolution suffers from an innate ill-posed problem that a single low-resolution (LR) image can be from multiple high-resolution (HR) images. Recent studies on the flow-based algorithm solve this ill-posedness by learning the super-resolution s
Externí odkaz:
http://arxiv.org/abs/2204.09679
Autor:
Shim, Dongseok, Kim, H. Jin
Deep neural networks have been widely studied in autonomous driving applications such as semantic segmentation or depth estimation. However, training a neural network in a supervised manner requires a large amount of annotated labels which are expens
Externí odkaz:
http://arxiv.org/abs/2103.05902
Autor:
Shim, Dongseok, Kim, H. Jin
Previous studies on image classification have mainly focused on the performance of the networks, not on real-time operation or model compression. We propose a Gaussian Deep Recurrent visual Attention Model (GDRAM)- a reinforcement learning based ligh
Externí odkaz:
http://arxiv.org/abs/2011.06190
Autor:
Shim, Dongseok, Kim, H. Jin
Estimating a depth map from a single RGB image has been investigated widely for localization, mapping, and 3-dimensional object detection. Recent studies on a single-view depth estimation are mostly based on deep Convolutional neural Networks (ConvNe
Externí odkaz:
http://arxiv.org/abs/2011.03207