In geometry processing,symmetry research benefits from global geo-metric features of complete shapes,but the shape of an object captured in real-world applications is often incomplete due to the limited sensor resoluti...In geometry processing,symmetry research benefits from global geo-metric features of complete shapes,but the shape of an object captured in real-world applications is often incomplete due to the limited sensor resolution,single viewpoint,and occlusion.Different from the existing works predicting symmetry from the complete shape,we propose a learning approach for symmetry predic-tion based on a single RGB-D image.Instead of directly predicting the symmetry from incomplete shapes,our method consists of two modules,i.e.,the multi-mod-al feature fusion module and the detection-by-reconstruction module.Firstly,we build a channel-transformer network(CTN)to extract cross-fusion features from the RGB-D as the multi-modal feature fusion module,which helps us aggregate features from the color and the depth separately.Then,our self-reconstruction net-work based on a 3D variational auto-encoder(3D-VAE)takes the global geo-metric features as input,followed by a prediction symmetry network to detect the symmetry.Our experiments are conducted on three public datasets:ShapeNet,YCB,and ScanNet,we demonstrate that our method can produce reliable and accurate results.展开更多
The thermal shape-memory effect at room temperature for Co-32%Ni(mass fraction) magnetic shape memory alloy of single crystal was presented. When compressing the sample along the direction at room temperature, strain ...The thermal shape-memory effect at room temperature for Co-32%Ni(mass fraction) magnetic shape memory alloy of single crystal was presented. When compressing the sample along the direction at room temperature, strain can be recovered to some extent during later heating and the recovery rate varies with the pre-strain. But no obvious recoverable strain can be obtained along other crystal directions. For the thermal-mechanical training of the sample along , the recovery strain decreases obviously during the second round of compress and nearly no recovery happens after the third round of compress. A possible mechanism based on reversible motions of Shockley partial dislocations was proposed.展开更多
文摘In geometry processing,symmetry research benefits from global geo-metric features of complete shapes,but the shape of an object captured in real-world applications is often incomplete due to the limited sensor resolution,single viewpoint,and occlusion.Different from the existing works predicting symmetry from the complete shape,we propose a learning approach for symmetry predic-tion based on a single RGB-D image.Instead of directly predicting the symmetry from incomplete shapes,our method consists of two modules,i.e.,the multi-mod-al feature fusion module and the detection-by-reconstruction module.Firstly,we build a channel-transformer network(CTN)to extract cross-fusion features from the RGB-D as the multi-modal feature fusion module,which helps us aggregate features from the color and the depth separately.Then,our self-reconstruction net-work based on a 3D variational auto-encoder(3D-VAE)takes the global geo-metric features as input,followed by a prediction symmetry network to detect the symmetry.Our experiments are conducted on three public datasets:ShapeNet,YCB,and ScanNet,we demonstrate that our method can produce reliable and accurate results.
文摘The thermal shape-memory effect at room temperature for Co-32%Ni(mass fraction) magnetic shape memory alloy of single crystal was presented. When compressing the sample along the direction at room temperature, strain can be recovered to some extent during later heating and the recovery rate varies with the pre-strain. But no obvious recoverable strain can be obtained along other crystal directions. For the thermal-mechanical training of the sample along , the recovery strain decreases obviously during the second round of compress and nearly no recovery happens after the third round of compress. A possible mechanism based on reversible motions of Shockley partial dislocations was proposed.
