6 accepted papers
Personalized speech enhancement (PSE) methods typically rely on pre-trained speaker verification models or self-designed speaker encoders to extract target speaker clues, guiding the PSE model in isolating the desired speech. However, these approaches suffer from significant model complexity and oft…
Referring image segmentation is a task that aims to predict pixel-wise masks corresponding to objects in an image described by natural language expressions. Previous methods for referring image segmentation employ a cascade framework to break down complex problems into multiple stages. However, its…
Social relation extraction (SRE for short), which aims to infer the social relation between two people in daily life, has been demonstrated to be of great value in reality. Existing methods for SRE consider extracting social relation only from unimodal information such as text or image, ignoring the…
In this paper, we present a Haze-Aware Representation Distillation Generative Adversarial Network named HardGAN for single-image dehazing. Unlike previous studies that intend to model the transmission map and global atmospheric light jointly to restore a clear image, we solve this regression problem…
In this paper, we propose a method of reconstructing the depth map of a set of multiview images from the epipolar plane images (EPIs) of multiview Images. Our method involves two steps: finding support points and estimating depth. First, we propose to include a consistency term and a smoothness term…
Semi-Global Matching (SGM) is a robust method in traditional stereo matching. It maintains precise boundary with low computational cost. However, directly applying SGM to light field stereo matching degrades the results greatly due to the sparsity of support points. In this letter, we proposes a nov…