Understanding deep learning techniques for image segmentation
The machine learning community has been overwhelmed by a plethora of deep learning--
based approaches. Many challenging computer vision tasks, such as detection, localization …
based approaches. Many challenging computer vision tasks, such as detection, localization …
A review on dark channel prior based image dehazing algorithms
The presence of haze in the atmosphere degrades the quality of images captured by visible
camera sensors. The removal of haze, called dehazing, is typically performed under the …
camera sensors. The removal of haze, called dehazing, is typically performed under the …
Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing
Subject-driven text-to-image generation models create novel renditions of an input subject
based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties …
based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties …
Non-local spatial propagation network for depth completion
In this paper, we propose a robust and efficient end-to-end non-local spatial propagation
network for depth completion. The proposed network takes RGB and sparse depth images …
network for depth completion. The proposed network takes RGB and sparse depth images …
Real-time high-resolution background matting
We introduce a real-time, high-resolution background replacement technique which
operates at 30fps in 4K resolution, and 60fps for HD on a modern GPU. Our technique is …
operates at 30fps in 4K resolution, and 60fps for HD on a modern GPU. Our technique is …
Physical attack on monocular depth estimation with optimal adversarial patches
Deep learning has substantially boosted the performance of Monocular Depth Estimation
(MDE), a critical component in fully vision-based autonomous driving (AD) systems (eg …
(MDE), a critical component in fully vision-based autonomous driving (AD) systems (eg …
Robust high-resolution video matting with temporal guidance
We introduce a robust, real-time, high-resolution human video matting method that achieves
new state-of-the-art performance. Our method is much lighter than previous approaches and …
new state-of-the-art performance. Our method is much lighter than previous approaches and …
Ccpl: Contrastive coherence preserving loss for versatile style transfer
In this paper, we aim to devise a universally versatile style transfer method capable of
performing artistic, photo-realistic, and video style transfer jointly, without seeing videos …
performing artistic, photo-realistic, and video style transfer jointly, without seeing videos …
Unsupervised learning of image segmentation based on differentiable feature clustering
The usage of convolutional neural networks (CNNs) for unsupervised image segmentation
was investigated in this study. Similar to supervised image segmentation, the proposed CNN …
was investigated in this study. Similar to supervised image segmentation, the proposed CNN …