-
Real-time Universal Style Transfer on High-resolution Images via Zero-channel Pruning
Extracting effective deep features to represent content and style inform...
read it
-
Fast Universal Style Transfer for Artistic and Photorealistic Rendering
Universal style transfer is an image editing task that renders an input ...
read it
-
StyleNAS: An Empirical Study of Neural Architecture Search to Uncover Surprisingly Fast End-to-End Universal Style Transfer Networks
Neural Architecture Search (NAS) has been widely studied for designing d...
read it
-
A Closed-form Solution to Photorealistic Image Stylization
Photorealistic image style transfer algorithms aim at stylizing a conten...
read it
-
StyleBank: An Explicit Representation for Neural Image Style Transfer
We propose StyleBank, which is composed of multiple convolution filter b...
read it
-
Reinforced Rewards Framework for Text Style Transfer
Style transfer deals with the algorithms to transfer the stylistic prope...
read it
-
Photo Stylistic Brush: Robust Style Transfer via Superpixel-Based Bipartite Graph
With the rapid development of social network and multimedia technology, ...
read it
Ultrafast Photorealistic Style Transfer via Neural Architecture Search
The key challenge in photorealistic style transfer is that an algorithm should faithfully transfer the style of a reference photo to a content photo while the generated image should look like one captured by a camera. Although several photorealistic style transfer algorithms have been proposed, they need to rely on post- and/or pre-processing to make the generated images look photorealistic. If we disable the additional processing, these algorithms would fail to produce plausible photorealistic stylization in terms of detail preservation and photorealism. In this work, we propose an effective solution to these issues. Our method consists of a construction step (C-step) to build a photorealistic stylization network and a pruning step (P-step) for acceleration. In the C-step, we propose a dense auto-encoder named PhotoNet based on a carefully designed pre-analysis. PhotoNet integrates a feature aggregation module (BFA) and instance normalized skip links (INSL). To generate faithful stylization, we introduce multiple style transfer modules in the decoder and INSLs. PhotoNet significantly outperforms existing algorithms in terms of both efficiency and effectiveness. In the P-step, we adopt a neural architecture search method to accelerate PhotoNet. We propose an automatic network pruning framework in the manner of teacher-student learning for photorealistic stylization. The network architecture named PhotoNAS resulted from the search achieves significant acceleration over PhotoNet while keeping the stylization effects almost intact. We conduct extensive experiments on both image and video transfer. The results show that our method can produce favorable results while achieving 20-30 times acceleration in comparison with the existing state-of-the-art approaches. It is worth noting that the proposed algorithm accomplishes better performance without any pre- or post-processing.
READ FULL TEXT
Comments
There are no comments yet.