scholarly journals Normalizing the Normal Map

2020 ◽  
Author(s):  
Charles Preppernau
Keyword(s):  
Normal Map

A measure-driven method for normal mapping and normal map design of 3D models

2018 ◽  
Vol 77 (24) ◽  
pp. 31969-31989 ◽  
Author(s):  
Kun Qian ◽  
Yinghua Li ◽  
Kehua Su ◽  
Jialing Zhang
Keyword(s):  
3D Models ◽  
Normal Map ◽  
Map Design ◽  
Normal Mapping

scholarly journals Pay Attention to Devils: A Photometric Stereo Network for Better Details

2020 ◽  
Author(s):  
Yakun Ju ◽  
Kin-Man Lam ◽  
Yang Chen ◽  
Lin Qi ◽  
Junyu Dong
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Photometric Stereo ◽  
Normal Map ◽  
Surface Normal ◽  
3D Surface ◽  
Surface Reconstructions ◽  
Higher Weights

We present an attention-weighted loss in a photometric stereo neural network to improve 3D surface recovery accuracy in complex-structured areas, such as edges and crinkles, where existing learning-based methods often failed. Instead of using a uniform penalty for all pixels, our method employs the attention-weighted loss learned in a self-supervise manner for each pixel, avoiding blurry reconstruction result in such difficult regions. The network first estimates a surface normal map and an adaptive attention map, and then the latter is used to calculate a pixel-wise attention-weighted loss that focuses on complex regions. In these regions, the attention-weighted loss applies higher weights of the detail-preserving gradient loss to produce clear surface reconstructions. Experiments on real datasets show that our approach significantly outperforms traditional photometric stereo algorithms and state-of-the-art learning-based methods.

NORMAL-MAP BETWEEN NORMAL-COMPATIBLE MANIFOLDS

2007 ◽  
Vol 17 (05) ◽  
pp. 403-421 ◽  
Author(s):  
FREDERIC CHAZAL ◽  
ANDRE LIEUTIER ◽  
JAREK ROSSIGNAC
Keyword(s):  
Hausdorff Distance ◽  
Arbitrary Dimension ◽  
The Other ◽  
Fréchet Distance ◽  
Feature Size ◽  
Normal Map ◽  
Frechet Distance ◽  
Minimum Feature Size

Consider two (n−1)-dimensional manifolds, S and S′ in ℝn. We say that they are normal-compatible when the closest projection of each one onto the other is a homeomorphism. We give a tight condition under which S and S′ are normal-compatible. It involves the minimum feature size of S and of S′ and the Hausdorff distance between them. Furthermore, when S and S′ are normal-compatible, their Frechet distance is equal to their Hausdorff distance. Our results hold for arbitrary dimension n.

Monocular depth estimation with guidance of surface normal map

2018 ◽  
Vol 280 ◽  
pp. 86-100 ◽  
Author(s):  
Han Yan ◽  
Shunli Zhang ◽  
Yu Zhang ◽  
Li Zhang
Keyword(s):  
Depth Estimation ◽  
Normal Map ◽  
Surface Normal ◽  
Monocular Depth

scholarly journals Deep Representation of a Normal Map for Screen-Space Fluid Rendering

2021 ◽  
Vol 11 (19) ◽  
pp. 9065
Author(s):  
Myungjin Choi ◽  
Jee-Hyeok Park ◽  
Qimeng Zhang ◽  
Byeung-Sun Hong ◽  
Chang-Hun Kim
Keyword(s):  
Surface Reconstruction ◽  
Computation Time ◽  
Fluid Simulation ◽  
Image Resolution ◽  
Reconstruction Method ◽  
Generative Adversarial Network ◽  
Normal Map ◽  
Adversarial Network ◽  
Reconstruction Methods ◽  
Screen Space

We propose a novel method for addressing the problem of efficiently generating a highly refined normal map for screen-space fluid rendering. Because the process of filtering the normal map is crucially important to ensure the quality of the final screen-space fluid rendering, we employ a conditional generative adversarial network (cGAN) as a filter that learns a deep normal map representation, thereby refining the low-quality normal map. In particular, we have designed a novel loss function dedicated to refining the normal map information, and we use a specific set of auxiliary features to train the cGAN generator to learn features that are more robust with respect to edge details. Additionally, we constructed a dataset of six different typical scenes to enable effective demonstrations of multitype fluid simulation. Experiments indicated that our generator was able to infer clearer and more detailed features for this dataset than a basic screen-space fluid rendering method. Moreover, in some cases, the results generated by our method were even smoother than those generated by the conventional surface reconstruction method. Our method improves the fluid rendering results via the high-quality normal map while preserving the advantages of the screen-space fluid rendering methods and the traditional surface reconstruction methods, including that of the computation time being independent of the number of simulation particles and the spatial resolution being related only to image resolution.

Frequency domain normal map filtering

2007 ◽  
Vol 26 (3) ◽  
pp. 28 ◽  
Author(s):  
Charles Han ◽  
Bo Sun ◽  
Ravi Ramamoorthi ◽  
Eitan Grinspun
Keyword(s):  
Frequency Domain ◽  
Normal Map
Sign in / Sign up

Export Citation Format

Share Document