Proceedings ArticleDOI
Content-aware compression using saliency-driven image retargeting
Fabio Zünd,Yael Pritch,Alexander Sorkine-Hornung,Stefan Mangold,Thomas R. Gross +4 more
- pp 1845-1849
TLDR
A novel method to compress video content based on image retargeting that introduces a non-uniform antialiasing technique that significantly improves the image resampling quality and achieves a significant improvement of the visual quality of salient image regions.Abstract:
In this paper we propose a novel method to compress video content based on image retargeting. First, a saliency map is extracted from the video frames either automatically or according to user input. Next, nonlinear image scaling is performed which assigns a higher pixel count to salient image regions and fewer pixels to non-salient regions. The non-linearly downscaled images can then be compressed using existing compression techniques and decoded and upscaled at the receiver. To this end we introduce a non-uniform antialiasing technique that significantly improves the image resampling quality. The overall process is complementary to existing compression methods and can be seamlessly incorporated into existing pipelines. We compare our method to JPEG 2000 and H.264/AVC-10 and show that, at the cost of visual quality in non-salient image regions, our method achieves a significant improvement of the visual quality of salient image regions in terms of Structural Similarity (SSIM) and Peak Signal-to-Noise-Ratio (PSNR) quality measures, in particular for scenarios with high compression ratios.read more
Citations
More filters
Proceedings ArticleDOI
Multi-Source Weak Supervision for Saliency Detection
TL;DR: Li et al. as mentioned in this paper proposed a unified framework to train saliency detection models with diverse weak supervision sources, such as category labels, captions, and unlabeled data.
Proceedings ArticleDOI
Learning to Promote Saliency Detectors
TL;DR: This work forms a zero-shot learning problem to promote existing saliency detectors and significantly improves accuracy of existing methods and compares favorably against state-of-the-art approaches.
Proceedings ArticleDOI
Semantic Perceptual Image Compression Using Deep Convolution Networks
TL;DR: A new cnn architecture directed specifically to image compression is presented, which generates a map that highlights semantically-salient regions so that they can be encoded at a better quality compared to background regions.
Posted Content
DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection
TL;DR: The proposed saliency detector, a modified U-Net architecture with DNA, performs favorably against state-of-the-art methods on various datasets and evaluation metrics without bells and whistles and can successfully break through the bottleneck of the current linear approaches.
Posted Content
Semantic Perceptual Image Compression using Deep Convolution Networks
TL;DR: In this paper, a CNN architecture is proposed to generate a map that highlights semantically-salient regions so that they can be encoded at higher quality as compared to background regions by adding a complete set of features for every class and then taking a threshold over the sum of all feature activations.
References
More filters
Journal ArticleDOI
Image quality assessment: from error visibility to structural similarity
TL;DR: In this article, a structural similarity index is proposed for image quality assessment based on the degradation of structural information, which can be applied to both subjective ratings and objective methods on a database of images compressed with JPEG and JPEG2000.
Journal ArticleDOI
The Laplacian Pyramid as a Compact Image Code
Peter J. Burt,Edward H. Adelson +1 more
TL;DR: A technique for image encoding in which local operators of many scales but identical shape serve as the basis functions, which tends to enhance salient image features and is well suited for many image analysis tasks as well as for image compression.
Proceedings ArticleDOI
Saliency filters: Contrast based filtering for salient region detection
TL;DR: A conceptually clear and intuitive algorithm for contrast-based saliency estimation that outperforms all state-of-the-art approaches and can be formulated in a unified way using high-dimensional Gaussian filters.
Journal ArticleDOI
The JPEG2000 still image coding system: an overview
TL;DR: It is interesting to note that JPEG2000 is being designed to address the requirements of a diversity of applications, e.g. Internet, color facsimile, printing, scanning, digital photography, remote sensing, mobile applications, medical imagery, digital library and E-commerce.
Journal ArticleDOI
Automatic foveation for video compression using a neurobiological model of visual attention
TL;DR: A general-purpose usefulness of the algorithm is suggested in improving compression ratios of unconstrained video, based on a nonlinear integration of low-level visual cues, mimicking processing in primate occipital, and posterior parietal cortex.