Depth-aware neural style transfer
Explore this paper's citation graph
Summary
A novel approach for neural style transfer is introduced that integrates depth preservation as additional loss, preserving overall image layout while performing style transfer, and producing an image that preserves its semantic content.
- Type
- article
- Published
- 2017-07-29
- Cited by
- 82
- References
- 54
- Access
- Open access
- OpenAlex
- https://openalex.org/W2740729727
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:13405888
Keywords
Computer science, Artificial intelligence, Convolutional neural network, Focus (optics), Image (mathematics)
References
- Monocular Object Instance Segmentation and Depth Ordering with CNNs
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Torch7: A Matlab-like Environment for Machine Learning
- Non-photorealistic computer graphics: modeling, rendering, and animation
- cuDNN: Efficient Primitives for Deep Learning
- Salient Object Detection: A Benchmark
- Fully convolutional networks for semantic segmentation
- Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture
- Towards unified depth and semantic prediction from a single image
- Understanding deep image representations by inverting them
- The visual perception of 3-D shape from multiple cues: Are observers capable of perceiving metric structure?
- Image quilting for texture synthesis and transfer
- Non-Photorealistic Rendering and the science of art
- Global contrast based salient region detection
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
- Contour Detection and Hierarchical Image Segmentation
- Vision meets robotics: The KITTI dataset
- Texture synthesis by non-parametric sampling
- Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs
- Deep convolutional neural fields for depth estimation from a single image
Cited by
- Richer Convolutional Features for Edge Detection
- Neural style transfer: a paradigm shift for image-based artistic rendering?
- Direction-aware Neural Style Transfer
- Adjustable Real-time Style Transfer
- MaeSTrO: A Mobile App for Style Transfer Orchestration Using Neural Networks
- Image Neural Style Transfer With Preserving the Salient Regions
- Locally controllable neural style transfer on mobile devices
- A comprehensive survey on non-photorealistic rendering and benchmark developments for image abstraction and stylization
- Depth-Preserving Real-Time Arbitrary Style Transfer
- Neural Style Transfer: A Review
- Neural Style Transfer with Content Discrimination
- Structure-Preserving Neural Style Transfer
- Direction-aware neural style transfer with texture enhancement
- Застосування нейронної мережі для стилізованої обробки зображень
- ImagineNet: Restyling Apps Using Neural Style Transfer
- Deep Learning for Anime Style Transfer
- Light-Field Style Transfer
- Style Transfer for Light Field Photography
- Detail-Preserving Arbitrary Style Transfer
- Depth-Aware Arbitrary Style Transfer Using Instance Normalization
Related papers
- An Adaptable Real-Time Object Detection for Traffic Surveillance using R-CNN over CNN with Improved Accuracy
- Morphological focus marking in Gùrùntùm (West Chadic)
- SEGMENTATION OF MEDICAL IMAGES BY CONVOLUTIONAL NEURAL NETWORKS
- Convolutional Neural Network (CNN) Applied to the Risk Analysis of Accidents in Vessels Navigating the Amazon Rivers
- Using Discourse Focus, Temporal Focus, and Spatial Focus to Generate Multisentential Text
- A General Survey of Focused Study
- Age Estimation Method based on Comparative Convolutional Neural Network using Inception Module