GIFS: Neural Implicit Function for General Shape Representation

Ye, Jianglong; Chen, Yuntao; Wang, Naiyan; Wang, Xiaolong

doi:10.48550/arxiv.2204.07126

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been many 3D scene representations, such as multiview images [60,77], textured meshes [38,85], point clouds [1,61], and voxels [42,75]. Recently, some methods [11,41,44,51,76,96,103] propose implicit neural representations to represent scenes, which uses MLP networks to predict scene properties for any point in 3D space, such as occupancy [44,67], signed distance [41,51], and semantics [23,103]. This enables them to describe continuous and high-resolution 3D scenes.…”

Section: Related Workmentioning

confidence: 99%

Learning Neural Volumetric Representations of Dynamic Humans in Minutes

Chen¹,

Peng²,

Zhao³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Learning Neural Volumetric Representations of Dynamic Humans in Minutes

Chen¹,

Peng²,

Zhao³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…However, SDFs are constrained to modeling watertight shapes limiting their use in open surfaces (e.g., garments). Unsigned distance fields [10] (with Ball-Pivoting [5]) and GIFS [58] are alternatives that support open surfaces and mesh generation. To model high-quality shape, recent methods employ vector quantization together with transformers [53,37].…”

Section: Related Workmentioning

confidence: 99%

NeuralODF: Learning Omnidirectional Distance Fields for 3D Shape Representation

Houchens¹,

Lu²,

Duggal³

et al. 2022

Preprint

View full text Add to dashboard Cite

In visual computing, 3D geometry is represented in many different forms including meshes, point clouds, voxel grids, level sets, and depth images. Each representation is suited for different tasks thus making the transformation of one representation into another (forward map) an important and common problem. We propose Omnidirectional Distance Fields (ODFs), a new 3D shape representation that encodes geometry by storing the depth to the object's surface from any 3D position in any viewing direction. Since rays are the fundamental unit of an ODF, it can be used to easily transform to and from common 3D representations like meshes or point clouds. Different from level set methods that are limited to representing closed surfaces, ODFs are unsigned and can thus model open surfaces (e.g., garments). We demonstrate that ODFs can be effectively learned with a neural network (Neu-ralODF) despite the inherent discontinuities at occlusion boundaries. We also introduce efficient forward mapping algorithms for transforming ODFs to and from common 3D representations. Specifically, we introduce an efficient Jumping Cubes algorithm for generating meshes from ODFs. Experiments demonstrate that NeuralODF can learn to capture high-quality shape by overfitting to a single object, and also learn to generalize on common shape categories.

show abstract

GIFS: Neural Implicit Function for General Shape Representation

Cited by 2 publications

References 0 publications

Learning Neural Volumetric Representations of Dynamic Humans in Minutes

Learning Neural Volumetric Representations of Dynamic Humans in Minutes

NeuralODF: Learning Omnidirectional Distance Fields for 3D Shape Representation

Contact Info

Product

Resources

About