computer-vision-9

Video Style Transfer

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in video-style-transfer-9

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find video-style-transfer-9 models and implementations

Datasets

StyleGallery

Subtasks

No subtasks available.

Most implemented papers

A Style-Aware Content Loss for Real-time HD Style Transfer

B. Ommer, Artsiom Sanakoyeu, Dmytro Kotovenko, Sabine Lang•Wed Jul 25 2018

A style-aware content loss is proposed, which is trained jointly with a deep encoder-decoder network for real-time, high-resolution stylization of images and videos and results show that this approach better captures the subtle nature in which a style affects content.

224

Content

0

Paper Graph

ReCoNet: Real-time Coherent Video Style Transfer Network

Yizhou Yu, Chang Gao, Derun Gu, Fangjun Zhang•Mon Jul 02 2018

A novel real-time video style transfer model, ReCoNet, is proposed, which can generate temporally coherent style transfer videos while maintaining favorable perceptual styles and exhibits outstanding performance both qualitatively and quantitatively.

65 0

Paper Graph

AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer

Errui Ding, Xin Li, Tianwei Lin, Dongliang He, Songhua Liu, Fu Li, Meiling Wang, Zhengxing Sun, Qian Li•Sat Aug 07 2021

A novel attention and normalization module, named Adaptive Attention Normalization (AdaAttN), to adaptively perform attentive normalization on per-point basis is proposed, which achieves state-of-the-art arbitrary image/video style transfer.

405 0

Paper Graph

Layered neural atlases for consistent video editing

Oliver Wang, Tali Dekel, Yoni Kasten, Dolev Ofri-Amar•Wed Sep 22 2021

A method that decomposes, and "unwraps", an input video into a set of layered 2D atlases, each providing a unified representation of the appearance of an object (or background) over the video, which does not require any prior 3D knowledge about scene geometry or camera poses.

184 0

Paper Graph

Creative Flow+ Dataset

S. Fidler, Maria Shugrina, Z. Liang, Amlan Kar, Jiaman Li, Angad Singh, Karan Singh•Fri May 31 2019

We present the Creative Flow+ Dataset, the first diverse multi-style artistic video dataset richly labeled with per-pixel optical flow, occlusions, correspondences, segmentation labels, normals, and depth. Our dataset includes 3000 animated sequences rendered using styles randomly selected from 40 textured line styles and 38 shading styles, spanning the range between flat cartoon fill and wildly sketchy shading. Our dataset includes 124K+ train set frames and 10K test set frames rendered at 1500x1500 resolution, far surpassing the largest available optical flow datasets in size. While modern techniques for tasks such as optical flow estimation achieve impressive performance on realistic images and video, today there is no way to gauge their performance on non-photorealistic images. Creative Flow+ poses a new challenge to generalize real-world Computer Vision to messy stylized content. We show that learning-based optical flow methods fail to generalize to this data and struggle to compete with classical approaches, and invite new research in this area. Our dataset and a new optical flow benchmark will be publicly available at: www.cs.toronto.edu/creativeflow/. We further release the complete dataset creation pipeline, allowing the community to generate and stylize their own data on demand.

23 0

Paper Graph

Consistent Video Style Transfer via Relaxation and Regularization

Jiaying Liu, Wenjing Wang, Jizheng Xu, Shuai Yang•Tue Sep 22 2020

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. Our project is publicly available at: https://daooshee.github.io/ReReVST/.

81 0

Paper Graph

CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer

Xiang Bai, Zijie Wu, Zhen Zhu, Junping Du•Sun Jul 10 2022

This paper makes a mild and reasonable assumption that global inconsistency is dominated by local inconsistencies and devise a generic Contrastive Coherence Preserving Loss (CCPL) applied to local patches that can preserve the coherence of the content source during style transfer without degrading stylization.

125 0

Paper Graph

FateZero: Fusing Attentions for Zero-shot Text-based Video Editing

Xintao Wang, Qifeng Chen, Ying Shan, Xiaodong Cun, Chenyang Lei, Chenyang Qi, Yong Zhang•Thu Mar 16 2023

F FateZero, a zero-shot text-based editing method on real-world videos without per-prompt training or use-specific mask, is proposed, which is the first one to show the ability of zero-shot text-driven video style and local attribute editing from the trained text-to-image model.

473 0

Paper Graph

CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer

C. Zou, Chengying Gao, Linfeng Wen•Thu Mar 30 2023

A new framework named CAP-VSTNet, which consists of a new reversible residual network and an unbiased linear transform module, for versatile style transfer is proposed, which can not only preserve content affinity but not introduce redundant information as traditional reversible networks, and hence facilitate better stylization.

63 0

Paper Graph

Adding a benchmark result helps the community track progress.