• Corpus ID: 3179251

Saliency Detection with a Deeper Investigation of Light Field

@inproceedings{Zhang2015SaliencyDW,
  title={Saliency Detection with a Deeper Investigation of Light Field},
  author={Jun Zhang and Meng Wang and Jun Gao and Yi Wang and Xudong Zhang and Xindong Wu},
  booktitle={IJCAI},
  year={2015}
}
Although the light field has been recently recognized helpful in saliency detection, it is not comprehensively explored yet. In this work, we propose a new saliency detection model with light field data. The idea behind the proposed model originates from the following observations. (1) People can distinguish regions at different depth levels via adjusting the focus of eyes. Similarly, a light field image can generate a set of focal slices focusing at different depth levels, which suggests that… 

Figures and Tables from this paper

Saliency Detection on Light Field

Experimental results show that this approach can achieve 0.6--6.7% relative improvements over state-of-the-art methods in terms of the F-measure and Precision metrics, which demonstrates the effectiveness of the proposed approach.

Light Field Saliency Detection With Deep Convolutional Networks

This work presents a new Lytro Illum dataset, which contains 640 light fields and their corresponding ground-truth saliency maps and proposes a novel end-to-end CNN-based framework for light field saliency detection, and proposes three novel MAC blocks to process light field micro-lens images.

Fast and Accurate Light Field Saliency Detection through Deep Encoding

This 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.

Deep Learning for Light Field Saliency Detection

This work introduces a new dataset to assist the subsequent research in 4D light field saliency detection and introduces adversarial examples by adding noise intentionally into images to help train the deep network, which can improve the robustness of the proposed network.

Deep Light-field-driven Saliency Detection from a Single View

This paper proposes a high-quality light field synthesis network to produce reliable 4D light field information and proposes a novel light-fielddriven saliency detection network with two purposes, that is, richer saliency features can be produced and geometric information can be considered for integration of multi-view saliency maps in a view-wise attention fashion.

Region-based depth feature descriptor for saliency detection on light field

A novel region-based depth feature descriptor (RDFD) defined over the focal stack is proposed that outperforms state-of-the-art techniques on the challenging light field saliency detection benchmark LFSD.

LFNet: Light Field Fusion Network for Salient Object Detection

A novel light field fusion network-LFNet, a CNNs-based light field saliency model using 4D light field data containing abundant spatial and contextual information is proposed, which can reliably locate and identify salient objects even in a complex scene.

Learning from Pixel-Level Noisy Label : A New Perspective for Light Field Saliency Detection

This paper proposes to learn light field saliency from pixel-level noisy labels obtained from unsupervised hand crafted featured-based saliency methods by formulating the learning as a joint optimization of intra light field features fusion stream and inter scenes correlation stream to generate the predictions.

Fast and Accurate Light Field Saliency Detection through Feature Extraction

This work shows that extracting features from light fields through aggressive size reduction and the attention results in a faster and accurate light-field saliency detector, significantly faster than existing systems, with better or comparable accuracy.

Light Field Salient Object Detection: A Review and Benchmark

This paper provides the first comprehensive review and a benchmark for light field SOD, which has long been lacking in the saliency community and benchmarking results are publicly available at https://github.com/kerenfu/LFSOD-Survey.

References

SHOWING 1-10 OF 71 REFERENCES

Saliency Detection on Light Field

Experiments show that the saliency detection scheme can robustly handle challenging scenarios such as similar foreground and background, cluttered background, complex occlusions, etc., and achieve high accuracy and robustness.

RGBD Salient Object Detection: A Benchmark and Algorithms

A simple fusion framework that combines existing RGB-produced saliency with new depth-induced saliency and a specialized multi-stage RGBD model is proposed which takes account of both depth and appearance cues derived from low-level feature contrast, mid-level region grouping and high-level priors enhancement.

Geodesic Saliency Using Background Priors

Evaluation on two databases validates that geodesic saliency achieves superior results and outperforms previous approaches by a large margin, in both accuracy and speed (2 ms per image), illustrating that appropriate prior exploitation is helpful for the ill-posed saliency detection problem.

Saliency Optimization from Robust Background Detection

This work proposes a robust background measure, called boundary connectivity, which characterizes the spatial layout of image regions with respect to image boundaries and is much more robust and presents unique benefits that are absent in previous saliency measures.

Depth saliency based on anisotropic center-surround difference

A novel saliency method that works on depth images based on anisotropic center-surround difference is proposed, which measures the saliency of a point by how much it outstands from surroundings, which takes the global depth structure into consideration.

Depth Matters: Influence of Depth Cues on Visual Saliency

This work collects a large human eye fixation database compiled from a pool of 600 2D-vs-3D image pairs viewed by 80 subjects, where the depth information is directly provided by the Kinect camera and the eye tracking data are captured in both 2D and 3D free-viewing experiments.

Salient Region Detection by UFO: Uniqueness, Focusness and Objectness

A novel salient region detection algorithm by integrating three important visual cues namely uniqueness, focus ness and objectness (UFO), which shows that, even with a simple pixel level combination of the three components, the proposed approach yields significant improvement compared with previously reported methods.

Context-aware saliency detection

A new type of saliency is proposed – context-aware saliency – which aims at detecting the image regions that represent the scene and a detection algorithm is presented which is based on four principles observed in the psychological literature.

Saliency Detection via Graph-Based Manifold Ranking

This work considers both foreground and background cues in a different way and ranks the similarity of the image elements with foreground cues or background cues via graph-based manifold ranking, defined based on their relevances to the given seeds or queries.

Saliency Detection via Dense and Sparse Reconstruction

A visual saliency detection algorithm from the perspective of reconstruction errors that applies the Bayes formula to integrate saliency measures based on dense and sparse reconstruction errors and refined by an object-biased Gaussian model is proposed.
...