Neural light field 3D printing

Zheng, Quan; Babaei, Vahid; Wetzstein, Gordon; Seidel, Hans‐Peter; Zwicker, Matthias; Singh, Gurprit

doi:10.1145/3414685.3417879

Cited by 9 publications

(6 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the works surveyed so far have been concerned with modeling the imaging process of consumer cameras, which measure the visible electromagnetic radiation via optical lenses, using sensors that digitize irradiance into intensity over a 2D raster grid. Nonetheless, neural fields can also model alternative signal modalities such as non‐line‐of‐sight imaging [SWL*21], non‐visible x‐rays for computed tomography (CT) [SPX21, ZIL*21, SLX*21], magnetic resonance imaging (MRI) [SPX21], pressure waves for audio [RBBJ], chemiluminescence [PXZ*21], time‐of‐flight imaging [ALG*21], as well as volumetric light displays [ZBW*20].…”

Section: Beyond Visual Computingmentioning

confidence: 99%

Neural Fields in Visual Computing and Beyond

Xie

Takikawa

Saito

et al. 2022

Computer Graphics Forum

311

View full text Add to dashboard Cite

Manipulation 2D and 3D Reconstruction Generative Models Digital Humans Compression 903.63 KB Robotics …and Beyond! Figure 1: Contribution of this report. Following a survey of over 250 papers, we provide a review of (Part I) techniques in neural fields such as prior learning and conditioning, representations, forward maps, architectures, and manipulation, and of (Part II) applications in visual computing including 2D image processing, 3D scene reconstruction, generative modeling, digital humans, compression, robotics, and beyond. This report is complemented by a community-driven website with search, filtering, bibliographic, and visualization features.

show abstract

Section: Beyond Visual Computingmentioning

confidence: 99%

Neural Fields in Visual Computing and Beyond

Xie

Takikawa

Saito

et al. 2022

Computer Graphics Forum

311

View full text Add to dashboard Cite

show abstract

“…Several works propose multi-scale DNN by projecting data into a high dimensional space with a set of sinusoids in efficiently representing complex 3D objects and scenes. (Tancik et al, 2020;Bi et al, 2020;Pumarola et al, 2021;Hennigh et al, 2021;Wang et al, 2021b;Häni et al, 2020;Zheng et al, 2020;Peng et al, 2021;Guo et al, 2020). Tancik et al (2021) use meta-learning to obtain a good initialization for fast and effective image restoration.…”

Section: Inspiring the Design Of Algorithmmentioning

confidence: 99%

Overview frequency principle/spectral bias in deep learning

Xu¹,

Zhang²,

Luo³

2022

Preprint

View full text Add to dashboard Cite

Understanding deep learning is increasingly emergent as it penetrates more and more into industry and science. In recent years, a research line from Fourier analysis sheds lights into this magical "black box" by showing a Frequency Principle (F-Principle or spectral bias) of the training behavior of deep neural networks (DNNs) -DNNs often fit functions from low to high frequency during the training. The F-Principle is first demonstrated by one-dimensional synthetic data followed by the verification in high-dimensional real datasets. A series of works subsequently enhance the validity of the F-Principle. This low-frequency implicit bias reveals the strength of neural network in learning low-frequency functions as well as its deficiency in learning high-frequency functions. Such understanding inspires the design of DNN-based algorithms in practical problems, explains experimental phenomena emerging in various scenarios, and further advances the study of deep learning from the frequency perspective. Although incomplete, we provide an overview of F-Principle and propose some open problems for future research.

show abstract

“…Work was also done in controlling the surface reflectance of 3Dprintouts, either by directly printing microgeometry [Luongo et al 2020;Rouiller et al 2013], or based on a controlled application of varnishes [Piovarči et al 2020]. Recently, Zheng et al [2020] used neural networks and end-to-end optimization to create static 4D light fields that can then be fabricated with inkjet 3D printers.…”

Section: Full-color Fabricationmentioning

confidence: 99%

“…Future work can build on this and integrate spatially-varying constraints, or perceptive metrics that include translucency, to replicate artist-friendly control akin to Brunton et al [2018] or directionallydependent goals as discussed by Zheng et al [2020].…”

Section: Applicationsmentioning

confidence: 99%

A gradient-based framework for 3D print appearance optimization

et al. 2021

View full text Add to dashboard Cite

In full-color inkjet 3D printing, a key problem is determining the material configuration for the millions of voxels that a printed object is made of. The goal is a configuration that minimises the difference between desired target appearance and the result of the printing process. So far, the techniques used to find such a configuration have relied on domain-specific methods or heuristic optimization, which allowed only a limited level of control over the resulting appearance. We propose to use differentiable volume rendering in a continuous material-mixture space, which leads to a framework that can be used as a general tool for optimising inkjet 3D printouts. We demonstrate the technical feasibility of this approach, and use it to attain fine control over the fabricated appearance, and high levels of faithfulness to the specified target.

show abstract

Neural light field 3D printing

Cited by 9 publications

References 42 publications

Neural Fields in Visual Computing and Beyond

Neural Fields in Visual Computing and Beyond

Overview frequency principle/spectral bias in deep learning

A gradient-based framework for 3D print appearance optimization

Contact Info

Product

Resources

About