Mesh Neural Networks Based on Dual Graph Pyramids.

Deep neural networks (DNNs) have been widely used for mesh processing in recent years. However, current DNNs can not process arbitrary meshes efficiently. On the one hand, most DNNs expect 2-manifold, watertight meshes, but many meshes, whether manually designed or automatically generated, may have gaps, non-manifold geometry, or other defects. On the other hand, the irregular structure of meshes also brings challenges to building hierarchical structures and aggregating local geometric information, which is critical to conduct DNNs. In this paper, we present DGNet, an efficient, effective and generic deep neural mesh processing network based on dual graph pyramids; it can handle arbitrary meshes. Firstly, we construct dual graph pyramids for meshes to guide feature propagation between hierarchical levels for both downsampling and upsampling. Secondly, we propose a novel convolution to aggregate local features on the proposed hierarchical graphs. By utilizing both geodesic neighbors and Euclidean neighbors, the network enables feature aggregation both within local surface patches and between isolated mesh components. Experimental results demonstrate that DGNet can be applied to both shape analysis and large-scale scene understanding. Furthermore, it achieves superior performance on various benchmarks, including ShapeNetCore, HumanBody, ScanNet and Matterport3D. Code and models will be available at https://github.com/li-xl/DGNet.

Beyond Self-Attention: External Attention Using Two Linear Layers for Visual Tasks.

Attention mechanisms, especially self-attention, have played an increasingly important role in deep feature representation for visual tasks. Self-attention updates the feature at each position by computing a weighted sum of features using pair-wise affinities across all positions to capture the long-range dependency within a single sample. However, self-attention has quadratic complexity and ignores potential correlation between different samples. This article proposes a novel attention mechanism which we call external attention, based on two external, small, learnable, shared memories, which can be implemented easily by simply using two cascaded linear layers and two normalization layers; it conveniently replaces self-attention in existing popular architectures. External attention has linear complexity and implicitly considers the correlations between all data samples. We further incorporate the multi-head mechanism into external attention to provide an all-MLP architecture, external attention MLP (EAMLP), for image classification. Extensive experiments on image classification, object detection, semantic segmentation, instance segmentation, image generation, and point cloud analysis reveal that our method provides results comparable or superior to the self-attention mechanism and some of its variants, with much lower computational and memory costs.

High-Quality Textured 3D Shape Reconstruction with Cascaded Fully Convolutional Networks.

We present a learning-based approach to reconstructing high-resolution three-dimensional (3D) shapes with detailed geometry and high-fidelity textures. Albeit extensively studied, algorithms for 3D reconstruction from multi-view depth-and-color (RGB-D) scans are still prone to measurement noise and occlusions; limited scanning or capturing angles also often lead to incomplete reconstructions. Propelled by recent advances in 3D deep learning techniques, in this paper, we introduce a novel computation- and memory-efficient cascaded 3D convolutional network architecture, which learns to reconstruct implicit surface representations as well as the corresponding color information from noisy and imperfect RGB-D maps. The proposed 3D neural network performs reconstruction in a progressive and coarse-to-fine manner, achieving unprecedented output resolution and fidelity. Meanwhile, an algorithm for end-to-end training of the proposed cascaded structure is developed. We further introduce Human10, a newly created dataset containing both detailed and textured full-body reconstructions as well as corresponding raw RGB-D scans of 10 subjects. Qualitative and quantitative experimental results on both synthetic and real-world datasets demonstrate that the presented approach outperforms existing state-of-the-art work regarding visual quality and accuracy of reconstructed models.

Study on fusion characteristics of biomass ash.

The ash fusion characteristics (AFC) of Capsicum stalks ashes, cotton stalks ashes and wheat stalks ashes that all prepared by ashing at 400 degrees C, 600 degrees C and 815 degrees C are consistent after 860 degrees C, 990 degrees C and 840 degrees C, respectively in the ash fusion temperature test and TG. Initial deformation temperature (IDT) increases with decreased K(2)O and went up with increased MgO, CaO, Fe(2)O(3) and Al(2)O(3). Softening temperature (ST), hemispherical temperature (HT) and fluid temperature (FT) do not affected by the concentrations of each element and the ashing temperature obviously. Therefore, the IDT may be as an evaluation index of biomass AFC rather than the ST used as an evaluation index of coal AFC. XRD shows that no matter what the ashing temperature is, the biomass ashes contain same high-temperature molten material. Therefore, evaluation of the biomass AFC should not be simply on the proportion of elements except IDT, but the high-temperature molten material in biomass ash.