此文为07-ECCV-Accurate RGB-D Salient Object Detection via Collaborative Learning中所注明的RGB-D首例研究,故在此全文翻译。 摘要:RGBD显著性检测设计了各种低水平的显著性线索,如颜色和深度对比度特征以及背景和颜色紧致度先验。然而,这些低水平的显著性线索如何相互作用,以及如何有效地结合它们来生成主显著性图仍...
本文设计了一种新的卷积神经网络(CNN),将不同的低水平显著性线索融合为层次特征(如颜色或深度对比特征、背景和颜色紧实度先验),用于自动检测RGBD图像中的显著性目标。 与现有的直接将原始图像像素输入CNN的方法不同,该方法利用了传统显著性检测中的知识,采用各种有意义的、设计良好的显著性特征向量作为输入。这可以减...
342017ISCSIVPAn integration of bottom-up and top-down salient cueson rgb-d data: saliency from objectness versus non-objectnessPaper/Project 332017MCLPIEEE TCYBAn iterative co-saliency framework for RGBD imagesPaper/Project 322017DFIEEE TIPRGBD Salient Object Detection via Deep FusionPaper/Project ...
Wang, Z., et al.: A deep-learning based feature hybrid framework for spatiotemporal saliency detection inside videos. Neurocomputing 287, 68–83 (2018) Article Google Scholar Han, J., et al.: Background prior-based salient object detection via deep reconstruction residual. IEEE Trans. Circui...
andyzeng / tsdf-fusion-python Star 1.3k Code Issues Pull requests Python code to fuse multiple RGB-D images into a TSDF voxel volume. cuda artificial-intelligence vision rgbd 3d 3d-reconstruction depth-camera volumetric-data 3d-deep-learning tsdf kinect-fusion Updated Feb 18, 2023 Python ...