In recent years, neural style transfer has attracted more and more attention, especially for image style transfer. However, temporally consistent style transfer for videos is still a challenging problem. Existing methods, either relying on a significant amount of video data with optical flows or using single-frame regularizers, fail to handle strong motions or complex variations, therefore have limited performance on real videos. In this article, we address the problem by jointly considering the intrinsic properties of stylization and temporal consistency. We first identify the cause of the conflict between style transfer and temporal consistency, and propose to reconcile this contradiction by relaxing the objective function, so as to make the stylization loss term more robust to motions. Through relaxation, style transfer is more robust to inter-frame variation without degrading the subjective effect. Then, we provide a novel formulation and understanding of temporal consistency. Based on the formulation, we analyze the drawbacks of existing training strategies and derive a new regularization. We show by experiments that the proposed regularization can better balance the spatial and temporal performance. Based on relaxation and regularization, we design a zero-shot video style transfer framework. Moreover, for better feature migration, we introduce a new module to dynamically adjust inter-channel distributions. Quantitative and qualitative results demonstrate the superiority of our method over state-of-the-art style transfer methods.
We present a novel algorithm for transferring artistic styles of semantically meaningful local regions of an image onto local regions of a target video while preserving its photorealism. Local regions may be selected either fully automatically from an image, through using video segmentation algorithms, or from casual user guidance such as scribbles. Our method, based on a deep neural network architecture inspired by recent work in photorealistic style transfer, is real-time and works on arbitrary inputs without runtime optimization once trained on a diverse dataset of artistic styles. By augmenting our video dataset with noisy semantic labels and jointly optimizing over style, content, mask, and temporal losses, our method can cope with a variety of imperfections in the input and produce temporally coherent videos without visual artifacts. We demonstrate our method on a variety of style images and target videos, including the ability to transfer different styles onto multiple objects simultaneously, and smoothly transition between styles in time.
Video style transfer is getting more attention in AI community for its numerous applications such as augmented reality and animation productions. Compared with traditional image style transfer, performing this task on video presents new challenges: how to effectively generate satisfactory stylized results for any specified style, and maintain temporal coherence across frames at the same time. Towards this end, we propose Multi-Channel Correction network (MCCNet), which can be trained to fuse the exemplar style features and input content features for efficient style transfer while naturally maintaining the coherence of input videos. Specifically, MCCNet works directly on the feature space of style and content domain where it learns to rearrange and fuse style features based on their similarity with content features. The outputs generated by MCC are features containing the desired style patterns which can further be decoded into images with vivid style textures. Moreover, MCCNet is also designed to explicitly align the features to input which ensures the output maintains the content structures as well as the temporal continuity. To further improve the performance of MCCNet under complex light conditions, we also introduce the illumination loss during training. Qualitative and quantitative evaluations demonstrate that MCCNet performs well in both arbitrary video and image style transfer tasks.
Video style transfer techniques inspire many exciting applications on mobile devices. However, their efficiency and stability are still far from satisfactory. To boost the transfer stability across frames, optical flow is widely adopted, despite its high computational complexity, e.g. occupying over 97% inference time. This paper proposes to learn a lightweight video style transfer network via knowledge distillation paradigm. We adopt two teacher networks, one of which takes optical flow during inference while the other does not. The output difference between these two teacher networks highlights the improvements made by optical flow, which is then adopted to distill the target student network. Furthermore, a low-rank distillation loss is employed to stabilize the output of student network by mimicking the rank of input videos. Extensive experiments demonstrate that our student network without an optical flow module is still able to generate stable video and runs much faster than the teacher network.
Recent research has made great progress in realizing neural style transfer of images, which denotes transforming an image to a desired style. Many users start to use their mobile phones to record their daily life, and then edit and share the captured images and videos with other users. However, directly applying existing style transfer approaches on videos, i.e., transferring the style of a video frame by frame, requires an extremely large amount of computation resources. It is still technically unaffordable to perform style transfer of videos on mobile phones. To address this challenge, we propose MVStylizer, an efficient edge-assisted photorealistic video style transfer system for mobile phones. Instead of performing stylization frame by frame, only key frames in the original video are processed by a pre-trained deep neural network (DNN) on edge servers, while the rest of stylized intermediate frames are generated by our designed optical-flow-based frame interpolation algorithm on mobile phones. A meta-smoothing module is also proposed to simultaneously upscale a stylized frame to arbitrary resolution and remove style transfer related distortions in these upscaled frames. In addition, for the sake of continuously enhancing the performance of the DNN model on the edge server, we adopt a federated learning scheme to keep retraining each DNN model on the edge server with collected data from mobile clients and syncing with a global DNN model on the cloud server. Such a scheme effectively leverages the diversity of collected data from various mobile clients and efficiently improves the system performance. Our experiments demonstrate that MVStylizer can generate stylized videos with an even better visual quality compared to the state-of-the-art method while achieving 75.5$\times$ speedup for 1920$\times$1080 videos.
Video-to-video translation is more difficult than image-to-image translation due to the temporal consistency problem that, if unaddressed, leads to distracting flickering effects. Although video models designed from scratch produce temporally consistent results, training them to match the vast visual knowledge captured by image models requires an intractable number of videos. To combine the benefits of image and video models, we propose an image-to-video model transfer method called Hyperconsistency (HyperCon) that transforms any well-trained image model into a temporally consistent video model without fine-tuning. HyperCon works by translating a temporally interpolated video frame-wise and then aggregating over temporally localized windows on the interpolated video. It handles both masked and unmasked inputs, enabling support for even more video-to-video translation tasks than prior image-to-video model transfer techniques. We demonstrate HyperCon on video style transfer and inpainting, where it performs favorably compared to prior state-of-the-art methods without training on a single stylized or incomplete video. Our project website is available at https://ryanszeto.com/projects/hypercon .
Video style transfer is a useful component for applications such as augmented reality, non-photorealistic rendering, and interactive games. Many existing methods use optical flow to preserve the temporal smoothness of the synthesized video. However, the estimation of optical flow is sensitive to occlusions and rapid motions. Thus, in this work, we introduce a novel evolve-sync loss computed by evolvements to replace optical flow. Using this evolve-sync loss, we build an adversarial learning framework, termed as Video Style Transfer Generative Adversarial Network (VST-GAN), which improves upon the MGAN method for image style transfer for more efficient video style transfer. We perform extensive experimental evaluations of our method and show quantitative and qualitative improvements over the state-of-the-art methods.
Recently, style transfer has received a lot of attention. While much of this research has aimed at speeding up processing, the approaches are still lacking from a principled, art historical standpoint: a style is more than just a single image or an artist, but previous work is limited to only a single instance of a style or shows no benefit from more images. Moreover, previous work has relied on a direct comparison of art in the domain of RGB images or on CNNs pre-trained on ImageNet, which requires millions of labeled object bounding boxes and can introduce an extra bias, since it has been assembled without artistic consideration. To circumvent these issues, we propose a style-aware content loss, which is trained jointly with a deep encoder-decoder network for real-time, high-resolution stylization of images and videos. We propose a quantitative measure for evaluating the quality of a stylized image and also have art historians rank patches from our approach against those from previous work. These and our qualitative results ranging from small image patches to megapixel stylistic images and videos show that our approach better captures the subtle nature in which a style affects content.
Image style transfer models based on convolutional neural networks usually suffer from high temporal inconsistency when applied to videos. Some video style transfer models have been proposed to improve temporal consistency, yet they fail to guarantee fast processing speed, nice perceptual style quality and high temporal consistency at the same time. In this paper, we propose a novel real-time video style transfer model, ReCoNet, which can generate temporally coherent style transfer videos while maintaining favorable perceptual styles. A novel luminance warping constraint is added to the temporal loss at the output level to capture luminance changes between consecutive frames and increase stylization stability under illumination effects. We also propose a novel feature-map-level temporal loss to further enhance temporal consistency on traceable objects. Experimental results indicate that our model exhibits outstanding performance both qualitatively and quantitatively.
Training a feed-forward network for fast neural style transfer of images is proven to be successful. However, the naive extension to process video frame by frame is prone to producing flickering results. We propose the first end-to-end network for online video style transfer, which generates temporally coherent stylized video sequences in near real-time. Two key ideas include an efficient network by incorporating short-term coherence, and propagating short-term coherence to long-term, which ensures the consistency over larger period of time. Our network can incorporate different image stylization networks. We show that the proposed method clearly outperforms the per-frame baseline both qualitatively and quantitatively. Moreover, it can achieve visually comparable coherence to optimization-based video style transfer, but is three orders of magnitudes faster in runtime.
Recent progress in style transfer on images has focused on improving the quality of stylized images and speed of methods. However, real-time methods are highly unstable resulting in visible flickering when applied to videos. In this work we characterize the instability of these methods by examining the solution set of the style transfer objective. We show that the trace of the Gram matrix representing style is inversely related to the stability of the method. Then, we present a recurrent convolutional network for real-time video style transfer which incorporates a temporal consistency loss and overcomes the instability of prior methods. Our networks can be applied at any resolution, do not re- quire optical flow at test time, and produce high quality, temporally consistent stylized videos in real-time.