Search

3D dense captioning aims to semantically describe each object detected in a 3D scene, which plays a significant role in 3D scene understanding. Previous works lack a complete definition of 3D spatial relationships and the directly integrate visual and language modalities, thus ignoring the discrepancies between the two modalities. To address these issues, we propose a novel complete 3D relationship extraction modality alignment network, which consists of three steps: 3D object detection, complete 3D relationships extraction, and modality alignment caption. To comprehensively capture the 3D spatial relationship features, we define a complete set of 3D spatial relationships, including the local spatial relationship between objects and the global spatial relationship between each object and the entire scene. To this end, we propose a complete 3D relationships extraction module based on message passing and self-attention to mine multi-scale spatial relationship features and inspect the transformation to obtain features in different views. In addition, we propose the modality alignment caption module to fuse multi-scale relationship features and generate descriptions to bridge the semantic gap from the visual space to the language space with the prior information in the word embedding, and help generate improved descriptions for the 3D scene. Extensive experiments demonstrate that the proposed model outperforms the state-of-the-art methods on the ScanRefer and Nr3D datasets.

Ulvan is a complex sulfated polysaccharide extracted from Ulva, and ulvan lyases can degrade ulvan through a β-elimination mechanism to obtain oligosaccharides. In this study, a new ulvan lyase, EPL15085, which belongs to the polysaccharide lyase (PL) 28 family from Tamlana fucoidanivoransCW2-9, was characterized in detail. The optimal pH and salinity are 9.0 and 0.4 M NaCl, respectively. The Kmand Vmaxof recombinant EPL15085 toward ulvan are 0.80 mg·mL–1and 11.22 μmol·min –1mg–1·mL–1, respectively. Unexpectedly, it is very resistant to high temperatures. After treatment at 100 °C, EPL15085 maintained its ability to degrade ulvan. Molecular dynamics simulation analysis and site-directed mutagenesis analysis indicated that the strong rigidity of the disulfide bond between Cys74–Cys102 in the N-terminus is related to its thermostability. In addition, oligosaccharides with disaccharides and tetrasaccharides were the end products of EPL15085. Based on molecular docking and site-directed mutagenesis analysis, Tyr177 and Leu134 are considered to be the crucial residues for enzyme activity. In conclusion, our study identified a new PL28 family of ulvan lyases, EPL15085, with excellent heat resistance that can expand the database of ulvan lyases and provide the possibility to make full use of ulvan.

Simulating liquid-textile interaction has received great attention in computer graphics recently. Most existing methods take textiles as particles or parameterized meshes. Although these methods can generate visually pleasing results, they cannot simulate water content at a microscopic level due to the lack of geometrically modeling of textile's anisotropic structure. In this paper, we develop a method for yarn-level simulation of hygroscopicity of textiles and evaluate it using various quantitative metrics. We model textiles in a fiber-yarn-fabric multi-scale manner and consider the dynamic coupled physical mechanisms of liquid spreading, including wetting, wicking, moisture sorption/desorption, and transient moisture-heat transfer in textiles. Our method can accurately simulate liquid spreading on textiles with different fiber materials and geometrical structures with consideration of air temperatures and humidity conditions. It visualizes the hygroscopicity of textiles to demonstrate their moisture management ability. We conduct qualitative and quantitative experiments to validate our method and explore various factors to analyze their influence on liquid spreading and hygroscopicity of textiles.

Point cloud upsampling aims to generate dense point clouds from given sparse ones, which is a challenging task due to the irregular and unordered nature of point sets. To address this issue, we present a novel deep learning-based model, called PU-Flow, which incorporates normalizing flows and weight prediction techniques to produce dense points uniformly distributed on the underlying surface. Specifically, we exploit the invertible characteristics of normalizing flows to transform points between euclidean and latent spaces and formulate the upsampling process as ensemble of neighbouring points in a latent space, where the ensemble weights are adaptively learned from local geometric context. Extensive experiments show that our method is competitive and, in most test cases, it outperforms state-of-the-art methods in terms of reconstruction quality, proximity-to-surface accuracy, and computation efficiency. The source code will be publicly available at https://github.com/unknownue/puflow.