Silhouette Guided Point Cloud Reconstruction beyond Occlusion

2020 IEEE Winter Conference on Applications of Computer Vision (WACV)(2020)

引用 11|浏览216
暂无评分
摘要
One major challenge in 3D reconstruction is to infer the complete shape geometry from partial foreground occlusions. In this paper, we propose a method to reconstruct the complete 3D shape of an object from a single RGB image, with robustness to occlusion. Given the image and a silhouette of the visible region, our approach completes the silhouette of the occluded region and then generates a point cloud. We show improvements for reconstruction of non-occluded and partially occluded objects by providing the predicted complete silhouette as guidance. We also improve state-of-the-art for 3D shape prediction with a 2D reprojection loss from multiple synthetic views and a surface-based smoothing and refinement step. Experiments demonstrate the efficacy of our approach both quantitatively and qualitatively on synthetic and real scene datasets.
更多
查看译文
关键词
3D shape prediction,silhouette guided point cloud reconstruction,shape geometry,partial foreground occlusions,RGB image
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要