paper-with-me

Papers

PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations

2020-08-04 · ECCV 2020 8 · Edgar Tretschk, Ayush Tewari, Vladislav Golyanik, Michael Zollhöfer, Carsten Stoll, Christian Theobalt

Implicit surface representations, such as signed-distance functions, combined with deep learning have led to impressive models which can represent detailed shapes of objects with arbitrary topology. Since a continuous function is learned, the reconstructions can also be extracted at any arbitrary resolution. However, large datasets such as ShapeNet are required to train such models. In this paper, we present a new mid-level patch-based surface representation. At the level of patches, objects across different categories share similarities, which leads to more generalizable models. We then introduce a novel method to learn this patch-based representation in a canonical space, such that it is as object-agnostic as possible. We show that our representation trained on one category of objects from ShapeNet can also well represent detailed shapes from any other category. In addition, it can be trained using much fewer shapes, compared to existing approaches. We show several applications of our new representation, including shape interpolation and partial point cloud completion. Due to explicit control over positions, orientations and scales of patches, our representation is also more controllable compared to object-level representations, which enables us to deform encoded shapes non-rigidly.

📄 PDF Abstract BibTeX arXiv:2008.01639

Code (0)

등록된 구현이 없습니다.

Tasks

Point Cloud Completion

Similar Papers 제목 키워드 기반

Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition

2016-09-01 · Zhe Wang, Li-Min Wang, Yali Wang, Bo-Wen Zhang 외

Traditional feature encoding scheme (e.g., Fisher vector) with local descriptors (e.g., SIFT) and recent convolutional neural networks (CNNs) are two classes of successful methods for image recognition. In this paper, we…

Scene Recognition

SwIPE: Efficient and Robust Medical Image Segmentation with Implicit Patch Embeddings

2023-07-23 · Yejia Zhang, Pengfei Gu, Nishchal Sapkota, Danny Z. Chen

Modern medical image segmentation methods primarily use discrete representations in the form of rasterized masks to learn features and generate predictions. Although effective, this paradigm is spatially inflexible, scal…

3D Shape ReconstructionImage SegmentationMedical Image SegmentationOrgan Segmentation+2

Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Clouds

2020-12-14 · CVPR 2021 1 · Wenbin Zhao, Jiabao Lei, Yuxin Wen, JianGuo Zhang 외

Shape modeling and reconstruction from raw point clouds of objects stand as a fundamental challenge in vision and graphics research. Classical methods consider analytic shape priors; however, their performance degraded w…

Surface Reconstruction

Local Implicit Grid Representations for 3D Scenes

2020-03-19 · Chiyu Max Jiang, Avneesh Sud, Ameesh Makadia, Jingwei Huang 외

Shape priors learned from data are commonly used to reconstruct 3D objects from partial or noisy data. Yet no such shape priors are available for indoor scenes, since typical 3D autoencoders cannot handle their scale, co…

3D Shape RepresentationDecoderDiversitySurface Reconstruction

Local Implicit Grid Representations for 3D Scenes

2020-06-01 · CVPR 2020 6 · Chiyu "Max" Jiang, Avneesh Sud, Ameesh Makadia, Jingwei Huang 외

Shape priors learned from data are commonly used to reconstruct 3D objects from partial or noisy data. Yet no such shape priors are available for indoor scenes, since typical 3D autoencoders cannot handle their scale, co…

3D Shape RepresentationDecoderDiversitySurface Reconstruction