Fast and Accurate Light Field Saliency Detection through Deep Encoding
- URL: http://arxiv.org/abs/2010.13073v2
- Date: Mon, 13 Dec 2021 17:12:56 GMT
- Title: Fast and Accurate Light Field Saliency Detection through Deep Encoding
- Authors: Sahan Hemachandra, Ranga Rodrigo, Chamira Edussooriya
- Abstract summary: Light field saliency detection still lacks speed and can improve in accuracy.
Existing approaches consume unnecessarily large amounts of computational resources for training, and have longer execution times for testing.
We solve this by aggressively reducing the large light field images to a much smaller three-channel feature map.
- Score: 0.8356765961526955
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Light field saliency detection -- important due to utility in many vision
tasks -- still lacks speed and can improve in accuracy. Due to the formulation
of the saliency detection problem in light fields as a segmentation task or a
memorizing task, existing approaches consume unnecessarily large amounts of
computational resources for training, and have longer execution times for
testing. We solve this by aggressively reducing the large light field images to
a much smaller three-channel feature map appropriate for saliency detection
using an RGB image saliency detector with attention mechanisms. We achieve this
by introducing a novel convolutional neural network based features extraction
and encoding module. Our saliency detector takes $0.4$ s to process a light
field of size $9\times9\times512\times375$ in a CPU and is significantly faster
than state-of-the-art light field saliency detectors, with better or comparable
accuracy. Furthermore, model size of our architecture is significantly lower
compared to state-of-the-art light field saliency detectors. Our work shows
that extracting features from light fields through aggressive size reduction
and the attention mechanism results in a faster and accurate light field
saliency detector leading to near real-time light field processing.
Related papers
- Characterization of point-source transient events with a rolling-shutter compressed sensing system [0.0]
Point-source transient events (PSTEs) pose several challenges to an imaging system.
Traditional imaging systems that meet these requirements are costly in terms of price, size, weight, power consumption, and data bandwidth.
We develop a novel compressed sensing algorithm adapted to the rolling shutter readout of an imaging system.
arXiv Detail & Related papers (2024-08-29T19:22:37Z) - SegNet: A Segmented Deep Learning based Convolutional Neural Network Approach for Drones Wildfire Detection [2.07180164747172]
This research addresses the pressing challenge of enhancing processing times and detection capabilities in Unmanned Aerial Vehicle (UAV)/drone imagery for global wildfire detection.
We focus on reducing feature maps to boost both time resolution and accuracy significantly advancing processing speeds and accuracy in real-time wildfire detection.
arXiv Detail & Related papers (2024-02-29T15:23:12Z) - Learning based Deep Disentangling Light Field Reconstruction and
Disparity Estimation Application [1.5603081929496316]
We propose a Deep Disentangling Mechanism, which inherits the principle of the light field disentangling mechanism and adds advanced network structure.
We design a light-field reconstruction network (i.e., DDASR) on the basis of the Deep Disentangling Mechanism, and achieve SOTA performance in the experiments.
arXiv Detail & Related papers (2023-11-14T12:48:17Z) - Global Context Aggregation Network for Lightweight Saliency Detection of
Surface Defects [70.48554424894728]
We develop a Global Context Aggregation Network (GCANet) for lightweight saliency detection of surface defects on the encoder-decoder structure.
First, we introduce a novel transformer encoder on the top layer of the lightweight backbone, which captures global context information through a novel Depth-wise Self-Attention (DSA) module.
The experimental results on three public defect datasets demonstrate that the proposed network achieves a better trade-off between accuracy and running efficiency compared with other 17 state-of-the-art methods.
arXiv Detail & Related papers (2023-09-22T06:19:11Z) - Low-Light Image Enhancement with Illumination-Aware Gamma Correction and
Complete Image Modelling Network [69.96295927854042]
Low-light environments usually lead to less informative large-scale dark areas.
We propose to integrate the effectiveness of gamma correction with the strong modelling capacities of deep networks.
Because exponential operation introduces high computational complexity, we propose to use Taylor Series to approximate gamma correction.
arXiv Detail & Related papers (2023-08-16T08:46:51Z) - Factorized Inverse Path Tracing for Efficient and Accurate
Material-Lighting Estimation [97.0195314255101]
Inverse path tracing is expensive to compute, and ambiguities exist between reflection and emission.
Our Factorized Inverse Path Tracing (FIPT) addresses these challenges by using a factored light transport formulation.
Our algorithm enables accurate material and lighting optimization faster than previous work, and is more effective at resolving ambiguities.
arXiv Detail & Related papers (2023-04-12T07:46:05Z) - Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and
Transformer-Based Method [51.30748775681917]
We consider the task of low-light image enhancement (LLIE) and introduce a large-scale database consisting of images at 4K and 8K resolution.
We conduct systematic benchmarking studies and provide a comparison of current LLIE algorithms.
As a second contribution, we introduce LLFormer, a transformer-based low-light enhancement method.
arXiv Detail & Related papers (2022-12-22T09:05:07Z) - SALISA: Saliency-based Input Sampling for Efficient Video Object
Detection [58.22508131162269]
We propose SALISA, a novel non-uniform SALiency-based Input SAmpling technique for video object detection.
We show that SALISA significantly improves the detection of small objects.
arXiv Detail & Related papers (2022-04-05T17:59:51Z) - Infrared Small-Dim Target Detection with Transformer under Complex
Backgrounds [155.388487263872]
We propose a new infrared small-dim target detection method with the transformer.
We adopt the self-attention mechanism of the transformer to learn the interaction information of image features in a larger range.
We also design a feature enhancement module to learn more features of small-dim targets.
arXiv Detail & Related papers (2021-09-29T12:23:41Z) - Lightweight Convolutional Neural Network with Gaussian-based Grasping
Representation for Robotic Grasping Detection [4.683939045230724]
Current object detectors are difficult to strike a balance between high accuracy and fast inference speed.
We present an efficient and robust fully convolutional neural network model to perform robotic grasping pose estimation.
The network is an order of magnitude smaller than other excellent algorithms.
arXiv Detail & Related papers (2021-01-25T16:36:53Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.