Search

Panoptic 3D reconstruction from a monocular video is a fundamental perceptual task in robotic scene understanding. However, existing efforts suffer from inefficiency in terms of inference speed and accuracy, limiting their practical applicability. We present EPRecon, an efficient real-time panoptic 3D reconstruction framework. Current volumetric-based reconstruction methods usually utilize multi-view depth map fusion to obtain scene depth priors, which is time-consuming and poses challenges to real-time scene reconstruction. To address this issue, we propose a lightweight module to directly estimate scene depth priors in a 3D volume for reconstruction quality improvement by generating occupancy probabilities of all voxels. In addition, compared with existing panoptic segmentation methods, EPRecon extracts panoptic features from both voxel features and corresponding image features, obtaining more detailed and comprehensive instance-level semantic information and achieving more accurate segmentation results. Experimental results on the ScanNetV2 dataset demonstrate the superiority of EPRecon over current state-of-the-art methods in terms of both panoptic 3D reconstruction quality and real-time inference. Code is available at https://github.com/zhen6618/EPRecon.

Glass largely blurs the boundary between the real world and the reflection. The special transmittance and reflectance quality have confused the semantic tasks related to machine vision. Therefore, how to clear the boundary built by glass, and avoid over-capturing features as false positive information in deep structure, matters for constraining the segmentation of reflection surface and penetrating glass. We proposed the Fourier Boundary Features Network with Wider Catchers (FBWC), which might be the first attempt to utilize sufficiently wide horizontal shallow branches without vertical deepening for guiding the fine granularity segmentation boundary through primary glass semantic information. Specifically, we designed the Wider Coarse-Catchers (WCC) for anchoring large area segmentation and reducing excessive extraction from a structural perspective. We embed fine-grained features by Cross Transpose Attention (CTA), which is introduced to avoid the incomplete area within the boundary caused by reflection noise. For excavating glass features and balancing high-low layers context, a learnable Fourier Convolution Controller (FCC) is proposed to regulate information integration robustly. The proposed method has been validated on three different public glass segmentation datasets. Experimental results reveal that the proposed method yields better segmentation performance compared with the state-of-the-art (SOTA) methods in glass image segmentation.

The social reform and opening-up in Chinese society in the last three decades have resulted in overall changes in almost every aspect of social life of its people. As an important indicator in these changes, English has become an important tool in education for students to move ahead to a higher level of schooling, and better jobs in the employment. A new challenge, thus, emerges as English learning is controversially related to sociocultural and economic factors of the family. This study then aims to answer whether the family background in terms of social, cultural and financial status would affect the outcomes of English learning at the compulsory stage of education in Shanghai, and to what extent this influence works on the school education. The study, based on the surveys of 2034 students and 1640 of their families, together with interviews with students and teachers, has found that English language learning has become a highly commercialized subject in Shanghai and the students and their families were widely involved as the major part of the customer-base due to the defective quality of instruction in the school classrooms. The study has found that in general there are correlations between the family background and the learning outcomes. However, such correlations are not intrinsic in the process and mechanism of language learning. They affect the teaching and learning of English as foreign language within certain constraints. (Contains 14 footnotes and 5 figures.)