# Silhouette Guided Point Cloud Reconstruction beyond Occlusion

arXiv: https://arxiv.org/abs/1907.12253 · HTML: https://mlsanity.com/paper/1907.12253/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2019.

## Built on by (most cited first, 3 of 3)

- [Amodal Ground Truth and Completion in the Wild](https://mlsanity.com/paper/2312.17247/) (2023)
- [3D objects and scenes classification, recognition, segmentation, and reconstruction using 3D point cloud data: A review](https://mlsanity.com/paper/2306.05978/) (2023)
- [SE-MD: A Single-encoder multiple-decoder deep network for point cloud generation from 2D images](https://mlsanity.com/paper/2106.15325/) (2021)

## Abstract (arXiv)

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.