Figure - uploaded by Xinshuo Weng
Content may be subject to copyright.
Quantitative evaluation for the proposed SPCSF task on the KITTI and nuScenes datasets. Ours+Point and Ours+RM denote that we use the point-based and range map-based encoder-decoder for our method respectively.
Source publication
Predicting the future is a crucial first step to effective control, since systems that can predict the future can select plans that lead to desired outcomes. In this work, we study the problem of future prediction at the level of 3D scenes, represented by point clouds captured by a LiDAR sensor, i.e., directly learning to forecast the evolution of...
Contexts in source publication
Context 1
... We summarize the performance for the proposed SPCSF task on the KITTI and NuScenes datasets in Table 1, where +RM and +Point denote the range map-based and point-based encoder-decoder for our method. The proposed SPCSFNet consistently outperforms all competitive baselines in both EMD and CD metrics. ...Context 2
... We summarize the performance for the proposed SPCSF task on the KITTI and NuScenes datasets in Table 1, where +RM and +Point denote the range map-based and point-based encoder-decoder for our method. The proposed SPCSFNet consistently outperforms all competitive baselines in both EMD and CD metrics. ...Similar publications
Communicating environmental changes and scenarios to stakeholders and decision-makers can be challenging. Immersive environments offer a novel tool to transfer knowledge and allow the interactive discussion of scenarios. With the increase of space- and airborne remote sensing and coherent classification of ecosystems, many large-scale geospatial da...
The documentation of built heritage has seen a significant development these past few decades due to advancements in new 3D sensors and 3D recording techniques. 3D data serve as reliable and tangible archive for historical sites and monuments. Since 3D data have such importance in the field of heritage documentation, quality control is paramount an...
A novel approach to generating watertight, manifold boundary representations from noisy binary image masks of MRI or CT scans is presented. The method samples an input segmented image and locally approximates the material boundary. Geometric error metrics between the voxelated boundary and an approximating template surface are minimized, and bounda...
