Deep Marching Cubes: Learning Explicit Surface Representations

Liao, Yiyi; Donné, Simon; Geiger, Andreas

doi:10.1109/cvpr.2018.00308

Cited by 242 publications

(182 citation statements)

References 30 publications

Supporting

Mentioning

162

Contrasting

Order By: Relevance

“…There have been a variety of 3D shape representations for deep learning of shapes, such as voxel grids [10,15,30,48,49], octrees [19,38,43,46,47], multi-view images [4,31,42], point clouds [1,13,14,35,36,50,51], geometry images [40,41], deformable mesh/patches [17,41,45,50], and part-based structural graphs [29,52]. To the best of our knowledge, our work is the first to introduce a deep network for learning implicit fields for generative shape modeling 1 .…”

Section: Related Workmentioning

confidence: 99%

Learning Implicit Fields for Generative Shape Modeling

Feng

Zhang

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

1,358

1,019

View full text Add to dashboard Cite

We advocate the use of implicit fields for learning generative models of shapes and introduce an implicit field decoder, called IM-NET, for shape generation, aimed at improving the visual quality of the generated shapes. An implicit field assigns a value to each point in 3D space, so that a shape can be extracted as an iso-surface. IM-NET is trained to perform this assignment by means of a binary classifier. Specifically, it takes a point coordinate, along with a feature vector encoding a shape, and outputs a value which indicates whether the point is outside the shape or not. By replacing conventional decoders by our implicit decoder for representation learning (via IM-AE) and shape generation (via IM-GAN), we demonstrate superior results for tasks such as generative shape modeling, interpolation, and single-view 3D reconstruction, particularly in terms of visual quality. Code and supplementary material are available at https://github.com/czq142857/implicit-decoder.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning Implicit Fields for Generative Shape Modeling

Feng

Zhang

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

1,358

1,019

View full text Add to dashboard Cite

show abstract

“…A natural limitation of these approaches is the lack of surface connectivity in the representation. To address this limitation, [12,21,29,40] proposed to directly learn 3D meshes.…”

Section: D Reconstructionmentioning

confidence: 99%

“…In the last decade, major breakthroughs in shape extraction were due to deep neural networks coupled with the abundance of visual data. Recent works focus on learning 3D reconstruction using 2.5D [14,16,24,43], volumetric [7,11,13,18,30,42], mesh [12,21] and point cloud [10,27] representations. However, none of the above are sufficiently parsimonious or interpretable to allow for higher-level 3D scene understanding as required by intelligent systems.…”

Section: Introductionmentioning

confidence: 99%

Superquadrics Revisited: Learning 3D Shape Parsing Beyond Cuboids

Paschalidou

Ulusoy

Geiger

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

164

255

View full text Add to dashboard Cite

Abstracting complex 3D shapes with parsimonious partbased representations has been a long standing goal in computer vision. This paper presents a learning-based solution to this problem which goes beyond the traditional 3D cuboid representation by exploiting superquadrics as atomic elements. We demonstrate that superquadrics lead to more expressive 3D scene parses while being easier to learn than 3D cuboid representations. Moreover, we provide an analytical solution to the Chamfer loss which avoids the need for computational expensive reinforcement learning or iterative prediction. Our model learns to parse 3D objects into consistent superquadric representations without supervision. Results on various ShapeNet categories as well as the SURREAL human body dataset demonstrate the flexibility of our model in capturing fine details and complex poses that could not have been modelled using cuboids.

show abstract

“…As such, the whole pipeline cannot be trained end-to-end. To overcome this limitation, Liao et al [46] introduced the Deep Marching Cubes, an end-to-end trainable network, which predicts explicit surface representations of arbitrary topology. They use a modified differentiable representation, which separates the mesh topology from the geometry.…”

Section: Deep Marching Cubesmentioning

confidence: 99%

Image-Based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era

Han

Laga

Bennamoun

2021

IEEE Trans. Pattern Anal. Mach. Intell.

304

150

View full text Add to dashboard Cite

3D reconstruction is a longstanding ill-posed problem, which has been explored for decades by the computer vision, computer graphics, and machine learning communities. Since 2015, image-based 3D reconstruction using convolutional neural networks (CNN) has attracted increasing interest and demonstrated an impressive performance. Given this new era of rapid evolution, this article provides a comprehensive survey of the recent developments in this field. We focus on the works which use deep learning techniques to estimate the 3D shape of generic objects either from a single or multiple RGB images. We organize the literature based on the shape representations, the network architectures, and the training mechanisms they use. While this survey is intended for methods which reconstruct generic objects, we also review some of the recent works which focus on specific object classes such as human body shapes and faces. We provide an analysis and comparison of the performance of some key papers, summarize some of the open problems in this field, and discuss promising directions for future research.

show abstract

Deep Marching Cubes: Learning Explicit Surface Representations

Cited by 242 publications

References 30 publications

Learning Implicit Fields for Generative Shape Modeling

Learning Implicit Fields for Generative Shape Modeling

Superquadrics Revisited: Learning 3D Shape Parsing Beyond Cuboids

Image-Based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era

Contact Info

Product

Resources

About