Silhouette Guided Point Cloud Reconstruction beyond Occlusion
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.
Code (1)
Tasks
3D ReconstructionPoint cloud reconstructionSimilar Papers 제목 키워드 기반
GaitPoint+: A Gait Recognition Network Incorporating Point Cloud Analysis and Recycling
Gait is a behavioral biometric modality that can be used to recognize individuals by the way they walk from a far distance. Most existing gait recognition approaches rely on either silhouettes or skeletons, while their j…
Gait RecognitionPose EstimationDRWR: A Differentiable Renderer without Rendering for Unsupervised 3D Structure Learning from Silhouette Images
Differentiable renderers have been used successfully for unsupervised 3D structure learning from 2D images because they can bridge the gap between 3D and 2D. To optimize 3D shape parameters, current renderers rely on pix…
From Image Collections to Point Clouds with Self-supervised Shape and Pose Networks
Reconstructing 3D models from 2D images is one of the fundamental problems in computer vision. In this work, we propose a deep learning technique for 3D object reconstruction from a single image. Contrary to recent works…
3D Object Reconstruction3D Object Reconstruction From A Single Image3D Point Cloud ReconstructionObject Reconstruction+2Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matching
Learning to generate 3D point clouds without 3D supervision is an important but challenging problem. Current solutions leverage various differentiable renderers to project the generated 3D point clouds onto a 2D image pl…
Point Cloud GenerationUnsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projections Matching
Learning to generate 3D point clouds without 3D supervision is an important but challenging problem. Current solutions leverage various differentiable renderers to project the generated 3D point clouds onto a 2D imag…
Point Cloud Generation