Understanding deep learning techniques for image segmentation

S Ghosh, N Das, I Das, U Maulik - ACM computing surveys (CSUR), 2019 - dl.acm.org
The machine learning community has been overwhelmed by a plethora of deep learning--
based approaches. Many challenging computer vision tasks, such as detection, localization …

A review on dark channel prior based image dehazing algorithms

S Lee, S Yun, JH Nam, CS Won, SW Jung - EURASIP Journal on Image …, 2016 - Springer
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 …

Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing

D Li, J Li, S Hoi - Advances in Neural Information …, 2024 - proceedings.neurips.cc
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 …

Matting by generation

Z Wang, B Li, J Wang, YL Liu, J Gu… - ACM SIGGRAPH 2024 …, 2024 - dl.acm.org
This paper introduces an innovative approach for image matting that redefines the traditional
regression-based task as a generative modeling challenge. Our method harnesses the …

Non-local spatial propagation network for depth completion

J Park, K Joo, Z Hu, CK Liu, I So Kweon - Computer Vision–ECCV 2020 …, 2020 - Springer
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 …

Real-time high-resolution background matting

S Lin, A Ryabtsev, S Sengupta… - Proceedings of the …, 2021 - openaccess.thecvf.com
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 …

Physical attack on monocular depth estimation with optimal adversarial patches

Z Cheng, J Liang, H Choi, G Tao, Z Cao, D Liu… - European conference on …, 2022 - Springer
Deep learning has substantially boosted the performance of Monocular Depth Estimation
(MDE), a critical component in fully vision-based autonomous driving (AD) systems (eg …

Robust high-resolution video matting with temporal guidance

S Lin, L Yang, I Saleemi… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
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 …

Ccpl: Contrastive coherence preserving loss for versatile style transfer

Z Wu, Z Zhu, J Du, X Bai - European Conference on Computer Vision, 2022 - Springer
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 …

Unsupervised learning of image segmentation based on differentiable feature clustering

W Kim, A Kanezaki, M Tanaka - IEEE Transactions on Image …, 2020 - ieeexplore.ieee.org
The usage of convolutional neural networks (CNNs) for unsupervised image segmentation
was investigated in this study. Similar to supervised image segmentation, the proposed CNN …