Anime Sketch Coloring with Swish-Gated Residual U-Net

Liu, Gang; Chen, Xin; Hu, Yanzhong

doi:10.1007/978-981-13-6473-0_17

Cited by 7 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, we implement the Context Generation Network as a 3D variant of the U-Net architecture which was originally proposed by Ronneberger et al [56]. U-Net has successfully been applied for different computer vision tasks that involve dense localized predictions such as image style transfer [57], image segmentation [58,59], image enhancement [60], image coloring [61,62], and image generation [63,64] Different from the original U-Net architecture, we replace the 2D convolutions with 3D counterparts and utilize residue blocks instead of individual convolution layers for better training properties of the network. The U-Net comprises of a contractive part followed by an expansive part.…”

Section: Context Generation Networkmentioning

confidence: 99%

MESHFREEFLOWNET: A Physics-Constrained Deep Continuous Space-Time Super-Resolution Framework

Jiang

Esmaeilzadeh

Azizzadenesheli

et al. 2020

SC20: International Conference for High Performance Computing, Networking, Storage and Analysis

View full text Add to dashboard Cite

We propose MeshfreeFlowNet, a novel deep learningbased super-resolution framework to generate continuous (grid-free) spatio-temporal solutions from the low-resolution inputs. While being computationally efficient, Mesh-freeFlowNet accurately recovers the fine-scale quantities of interest. MeshfreeFlowNet allows for: (i) the output to be sampled at all spatio-temporal resolutions, (ii) a set of Partial Differential Equation (PDE) constraints to be imposed, and (iii) training on fixed-size inputs on arbitrarily sized spatio-temporal domains owing to its fully convolutional encoder.We empirically study the performance of Mesh-freeFlowNet on the task of super-resolution of turbulent flows in the Rayleigh-Bénard convection problem. Across a diverse set of evaluation metrics, we show that Mesh-freeFlowNet significantly outperforms existing baselines. Furthermore, we provide a large scale implementation of MeshfreeFlowNet and show that it efficiently scales across large clusters, achieving 96.80% scaling efficiency on up to 128 GPUs and a training time of less than 4 minutes.We provide an open-source implementation of our method that supports arbitrary combinations of PDE constraints 1 . * Denotes equal contribution.

show abstract