paper-with-me

Papers

Cutting-Edge Techniques for Depth Map Super-Resolution

2023-06-27 · Ryan Peterson, Josiah Smith

To overcome hardware limitations in commercially available depth sensors which result in low-resolution depth maps, depth map super-resolution (DMSR) is a practical and valuable computer vision task. DMSR requires upscaling a low-resolution (LR) depth map into a high-resolution (HR) space. Joint image filtering for DMSR has been applied using spatially-invariant and spatially-variant convolutional neural network (CNN) approaches. In this project, we propose a novel joint image filtering DMSR algorithm using a Swin transformer architecture. Furthermore, we introduce a Nonlinear Activation Free (NAF) network based on a conventional CNN model used in cutting-edge image restoration applications and compare the performance of the techniques. The proposed algorithms are validated through numerical studies and visual examples demonstrating improvements to state-of-the-art performance while maintaining competitive computation time for noisy depth map super-resolution.

📄 PDF Abstract BibTeX arXiv:2306.15244

Code (0)

등록된 구현이 없습니다.

Tasks

Depth Map Super-ResolutionImage RestorationSuper-Resolution

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Stochastic Depth Stochastic Depth aims to shrink the depth of a network during training, while keeping it unchanged during testing. This is achieved by randomly dropping entire…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

An Empirical Study of Super-resolution on Low-resolution Micro-expression Recognition

2023-10-16 · Ling Zhou, Mingpei Wang, Xiaohua Huang, Wenming Zheng 외

Micro-expression recognition (MER) in low-resolution (LR) scenarios presents an important and complex challenge, particularly for practical applications such as group MER in crowded environments. Despite considerable adv…

BenchmarkingMicro Expression RecognitionMicro-Expression RecognitionSuper-Resolution

Semantic-Aware Depth Super-Resolution in Outdoor Scenes

2016-05-31 · Miaomiao Liu, Mathieu Salzmann, Xuming He

While depth sensors are becoming increasingly popular, their spatial resolution often remains limited. Depth super-resolution therefore emerged as a solution to this problem. Despite much progress, state-of-the-art techn…

Super-Resolution

License Plate Super-Resolution Using Diffusion Models

2023-09-21 · Sawsan AlHalawani, Bilel Benjdira, Adel Ammar, Anis Koubaa 외

In surveillance, accurately recognizing license plates is hindered by their often low quality and small dimensions, compromising recognition precision. Despite advancements in AI-based image super-resolution, methods lik…

Image RestorationImage Super-ResolutionSSIMSuper-Resolution

A Review of Deep Learning Based Image Super-resolution Techniques

2022-01-22 · Fangyuan Zhu

Image super-resolution technology is the process of obtaining high-resolution images from one or more low-resolution images. With the development of deep learning, image super-resolution technology based on deep learning…

Deep LearningImage Super-ResolutionSuper-Resolution

Variational Depth Superresolution Using Example-Based Edge Representations

2015-12-01 · ICCV 2015 12 · David Ferstl, Matthias Ruther, Horst Bischof

In this paper we propose a novel method for depth image superresolution which combines recent advances in example based upsampling with variational superresolution based on a known blur kernel. Most traditional depth sup…