Learning and Meshing From Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching

Lei, Jiabao; Jia, Kui; Ma, Yi

doi:10.1109/tpami.2021.3135007

Cited by 8 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Aiming for exact extraction, initial efforts focused on identifying linear regions (Serra et al, 2018) and employing Analytical Marching (Lei & Jia, 2020) to exactly reconstruct the zero-level isosurface. Contemporary approaches involve region subdivision, wherein the regions of the complex are progressively subdivided from neuron to neuron and layer to layer, allowing for the efficient calculation of the exponentially increasing linear regions (Raghu et al, 2017;Hanin & Rolnick, 2019;Humayun et al, 2023;Berzins, 2023).…”

Section: Related Workmentioning

confidence: 99%

“…Recent advancements in visualizing deep neural networks (Zhang et al, 2020;Lei & Jia, 2020;Lei et al, 2021;Berzins, 2023) contribute significantly to understanding the intricate structures that define these networks. This progress not only provides valuable insights into their expressivity, robustness, training methodologies, and distinctive geometry, but it also, by leveraging the inherent piecewise linearity in Continuous Piecewise Affine (CPWA) functions, e.g., ReLU neural networks, represents each region as a convex polyhedral, and the assembly of these polyhedral sets constructs a polyhedral complex that delineates the decision boundaries of neural networks (Grigsby & Lindsey, 2022).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of Explainable Artificial Intelligence (XAI) in Urban Growth Modeling: A Case Study of Seoul Metropolitan Area, Korea

Kim

Kim²,

Jin

et al. 2023

Land

View full text Add to dashboard Cite

Unplanned and rapid urban growth requires the reckless expansion of infrastructure including water, sewage, energy, and transportation facilities, and thus causes environmental problems such as deterioration of old towns, reduction of open spaces, and air pollution. To alleviate and prevent such problems induced by urban growth, the accurate prediction and management of urban expansion is crucial. In this context, this study aims at modeling and predicting urban expansion in Seoul metropolitan area (SMA), Korea, using GIS and XAI techniques. To this end, we examined the effects of land-cover, socio-economic, and environmental features in 2007 and 2019, within the optimal radius from a certain raster cell. Then, this study combined the extreme gradient boosting (XGBoost) model and Shapley additive explanations (SHAP) in analyzing urban expansion. The findings of this study suggest urban growth is dominantly affected by land-cover characteristics, followed by topographic attributes. In addition, the existence of water body and high ECVAM grades tend to significantly reduce the possibility of urban expansion. The findings of this study are expected to provide several policy implications in urban and environmental planning fields, particularly for effective and sustainable management of lands.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Application of Explainable Artificial Intelligence (XAI) in Urban Growth Modeling: A Case Study of Seoul Metropolitan Area, Korea

Kim

Kim²,

Jin

et al. 2023

Land

View full text Add to dashboard Cite

show abstract

“…Marching" [81] that can extract the exact polygonal mesh from neural implicit representations, the gap between neural implicit and explicit meshes may diminish in the future.…”

Section: Representationsmentioning

confidence: 99%

A Review of Deep Learning-Powered Mesh Reconstruction Methods

Feng¹

2023

Preprint

View full text Add to dashboard Cite

With the recent advances in hardware and rendering techniques, 3D models have emerged everywhere in our life. Yet creating 3D shapes is arduous and requires significant professional knowledge. Meanwhile, Deep learning has enabled high-quality 3D shape reconstruction from various sources, making it a viable approach to acquiring 3D shapes with minimal effort. Importantly, to be used in common 3D applications, the reconstructed shapes need to be represented as polygonal meshes, which is a challenge for neural networks due to the irregularity of mesh tessellations.In this survey, we provide a comprehensive review of mesh reconstruction methods that are powered by machine learning. We first describe various representations for 3D shapes in the deep learning context. Then we review the development of 3D mesh reconstruction methods from voxels, point clouds, single images, and multi-view images. Finally, we identify several challenges in this field and propose potential future directions.

show abstract

“…SRNs were first introduced for representing 3D opaque meshes, either as occupancy grids [MON*19, MLL*21] or signed distance field [TLY*21, DNJ20, LJM21, CLI*20]. In these methods, the networks were trained in world‐space, that is, from pairs of position to data value.…”

Section: Related Workmentioning

confidence: 99%

Fast Neural Representations for Direct Volume Rendering

Weiß

Hermüller

Westermann

2022

Computer Graphics Forum

View full text Add to dashboard Cite

Despite the potential of neural scene representations to effectively compress 3D scalar fields at high reconstruction quality, the computational complexity of the training and data reconstruction step using scene representation networks limits their use in practical applications. In this paper, we analyse whether scene representation networks can be modified to reduce these limitations and whether such architectures can also be used for temporal reconstruction tasks. We propose a novel design of scene representation networks using GPU tensor cores to integrate the reconstruction seamlessly into on-chip raytracing kernels, and compare the quality and performance of this network to alternative network-and non-network-based compression schemes. The results indicate competitive quality of our design at high compression rates, and significantly faster decoding times and lower memory consumption during data reconstruction. We investigate how density gradients can be computed using the network and show an extension where density, gradient and curvature are predicted jointly. As an alternative to spatial super-resolution approaches for time-varying fields, we propose a solution that builds upon latent-space interpolation to enable random access reconstruction at arbitrary granularity. We summarize our findings in the form of an assessment of the strengths and limitations of scene representation networks for compression domain volume rendering, and outline future research directions. Source code: https:// github.com/ shamanDevel/ fV-SRN

show abstract

Learning and Meshing From Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching

Cited by 8 publications

References 37 publications

Application of Explainable Artificial Intelligence (XAI) in Urban Growth Modeling: A Case Study of Seoul Metropolitan Area, Korea

Application of Explainable Artificial Intelligence (XAI) in Urban Growth Modeling: A Case Study of Seoul Metropolitan Area, Korea

A Review of Deep Learning-Powered Mesh Reconstruction Methods

Fast Neural Representations for Direct Volume Rendering

Contact Info

Product

Resources

About