PISA: Pixelwise Image Saliency by Aggregating Complementary Appearance Contrast Measures with Edge-Preserving Coherence

TL;DR

PISA is a unified pixelwise saliency detection framework that combines multiple cues and priors to produce detailed, edge-preserving saliency maps, outperforming previous methods and including a new dataset for evaluation.

Contribution

The paper introduces PISA, a novel framework that aggregates diverse bottom-up cues with spatial priors for accurate, fine-grained saliency detection, along with a faster version and a new dataset.

Findings

PISA outperforms state-of-the-art saliency methods on public datasets.

The faster PISA maintains accuracy while significantly reducing runtime.

A new dataset with 800 images is provided for saliency evaluation.

Abstract

Driven by recent vision and graphics applications such as image segmentation and object recognition, computing pixel-accurate saliency values to uniformly highlight foreground objects becomes increasingly important. In this paper, we propose a unified framework called PISA, which stands for Pixelwise Image Saliency Aggregating various bottom-up cues and priors. It generates spatially coherent yet detail-preserving, pixel-accurate and fine-grained saliency, and overcomes the limitations of previous methods which use homogeneous superpixel-based and color only treatment. PISA aggregates multiple saliency cues in a global context such as complementary color and structure contrast measures with their spatial priors in the image domain. The saliency confidence is further jointly modeled with a neighborhood consistence constraint into an energy minimization formulation, in which each pixel will be evaluated with multiple hypothetical saliency levels. Instead of using global discrete optimization methods, we employ the cost-volume filtering technique to solve our formulation, assigning the saliency levels smoothly while preserving the edge-aware structure details. In addition, a faster version of PISA is developed using a gradient-driven image sub-sampling strategy to greatly improve the runtime efficiency while keeping comparable detection accuracy. Extensive experiments on a number of public datasets suggest that PISA convincingly outperforms other state-of-the-art approaches. In addition, with this work we also create a new dataset containing $800$ commodity images for evaluating saliency detection. The dataset and source code of PISA can be downloaded at http://vision.sysu.edu.cn/project/PISA/