Single image super-resolution (SISR) aims to reconstruct a high-resolution image from its low-resolution observation. Recent deep learning-based SISR models show high performance at the expense of increased computational costs, limiting their use in resource-constrained environments. As a promising solution for computationally efficient network design, network quantization has been extensively studied. However, existing quantization methods developed for SISR have yet to effectively exploit image self-similarity, which is a new direction for exploration in this study. We introduce a novel method called reference-based quantization for image super-resolution (RefQSR) that applies high-bit quantization to several representative patches and uses them as references for low-bit quantization of the rest of the patches in an image. To this end, we design dedicated patch clustering and reference-based quantization modules and integrate them into existing SISR network quantization methods. The experimental results demonstrate the effectiveness of RefQSR on various SISR networks and quantization methods.

Urban scene modeling is a challenging but essential task for various applications, such as 3D map generation, city digitization, and AR/VR/metaverse applications. To model man-made structures, such as roads and buildings, which are the major components in general urban scenes, we present a clustering-based plane segmentation neural network using 3D point clouds, called hybrid K-means plane segmentation (HKPS). The proposed method segments unorganized 3D point clouds into planes by training the neural network to estimate the appropriate number of planes in the point cloud based on hybrid K-means clustering. We consider both the Euclidean distance and cosine distance to cluster nearby points in the same direction for better plane segmentation results. Our network does not require any labeled information for training. We evaluated the proposed method using the Virtual KITTI dataset and showed that our method outperforms conventional methods in plane segmentation. Our code is publicly available.

Due to the scale ambiguity problem, the performance of monocular depth estimation (MDE) is inherently restricted. Multi-camera systems, especially those equipped with active depth cameras, have addressed this problem at the expense of increased hardware costs and space. In this Letter, we adopt a similar but cost-effective solution using only single-pixel depth guidance with a single-photon avalanche diode. To this end, we design a single-pixel guidance module (SPGM) that combines the global information from the single-pixel depth guidance with the spatial information from the image at the feature level. By integrating SPGMs into an MDE network, we introduce PhoMoNet, the first, to the best of our knowledge, end-to-end MDE network with single-pixel depth guidance. Experimental results show the effectiveness and superiority of PhoMoNet over state-of-the-art MDE networks on synthetic and real-world datasets.