Style transfer is to render given image contents in given styles, and it has an important role in both computer vision fundamental research and industrial applications. Following the success of deep learning based approaches, this problem has been re-launched recently, but still remains a difficult task because of trade-off between preserving contents and faithful rendering of styles. Indeed, how well-balanced content and style are is crucial in evaluating the quality of stylized images. In this paper, we propose an end-to-end two-stream Fully Convolutional Networks (FCNs) aiming at balancing the contributions of the content and the style in rendered images. Our proposed network consists of the encoder and decoder parts. The encoder part utilizes a FCN for content and a FCN for style where the two FCNs have feature injections and are independently trained to preserve the semantic content and to learn the faithful style representation in each. The semantic content feature and the style representation feature are then concatenated adaptively and fed into the decoder to generate style-transferred (stylized) images. In order to train our proposed network, we employ a loss network, the pre-trained VGG-16, to compute content loss and style loss, both of which are efficiently used for the feature injection as well as the feature concatenation. Our intensive experiments show that our proposed model generates more balanced stylized images in content and style than state-of-the-art methods. Moreover, our proposed network achieves efficiency in speed.
AIOZ；University of Liverpool（利物浦大学）；VinAI Research（VinAI研究院）
Audio-driven talking head animation is a challenging research topic with many real-world applications. Recent works have focused on creating photo-realistic 2D animation, while learning different talking or singing styles remains an open problem. In this paper, we present a new method to generate talking head animation with learnable style references. Given a set of style reference frames, our framework can reconstruct 2D talking head animation based on a single input image and an audio stream. Our method first produces facial landmarks motion from the audio stream and constructs the intermedi…
SplitFlux: Learning to Decouple Content and Style from a Single Image
School of Computing and Artificial Intelligence（计算与人工智能学院）；University College London, University of London（伦敦大学大学学院）；College of Computer Science and Technology（计算机科学与技术学院）
Center for Research on Intelligent Perception and Computing, NLPR, CASIA（中国科学院自动化研究所模式识别国家重点实验室智能感知与计算研究中心）；School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)（中国科学院大学人工智能学院）
Existing text-to-image synthesis methods generally are only applicable to words in the training dataset. However, human faces are so variable to be described with limited words. So this paper proposes the first free-style text-to-face method namely AnyFace enabling much wider open world applications such as metaverse, social media, cosmetics, forensics, etc. AnyFace has a novel two-stream framework for face image synthesis and manipulation given arbitrary descriptions of the human face. Specifically, one stream performs text-to-face generation and the other conducts face image reconstruction. …
FreeStyle: Free Lunch for Text-guided Style Transfer using Diffusion Models
School of Cyberspace Security at Sun Yat-sen University（中山大学网络空间安全学院）；Institute of Software,Chinese Academy of Sciences（中国科学院软件研究所）；Information Technology Service Center of People’s Court（人民法院信息技术服务中心）；School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）
University of British Columbia（不列颠哥伦比亚大学）；University of California, Davis（加州大学戴维斯分校）
Motion style transfer is a common method for enriching character animation. Motion style transfer algorithms are often designed for offline settings where motions are processed in segments. However, for online animation applications, such as realtime avatar animation from motion capture, motions need to be processed as a stream with minimal latency. In this work, we realize a flexible, high-quality motion style transfer method for this setting. We propose a novel style transfer model, Style-ERD, to stylize motions in an online manner with an Encoder-Recurrent-Decoder structure, along with a no…
SMCD: High Realism Motion Style Transfer via Mamba-based Diffusion
Academy for Engineering and Technology, Fudan University（工程与技术学院，复旦大学）；School of Computer Science and Technology, East China Normal University（计算机科学与技术学院，华东师范大学）
We introduce a two-stream model for dynamic texture synthesis. Our model is based on pre-trained convolutional networks (ConvNets) that target two independent tasks: (i) object recognition, and (ii) optical flow prediction. Given an input dynamic texture, statistics of filter responses from the object recognition ConvNet encapsulate the per-frame appearance of the input texture, while statistics of filter responses from the optical flow ConvNet model its dynamics. To generate a novel texture, a randomly initialized input sequence is optimized to match the feature statistics from each stream of…
LocalStyleFool: Regional Video Style Transfer Attack Using Segment Anything Model
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Shandong University（山东大学）；CSIRO’s Data61（联邦科学与工业研究组织数据61部）；Ping An Technology（平安科技）；Shenzhen Institute of Information Technology（深圳信息职业技术学院）
提出 LocalStyleFool，利用 SAM 进行区域分割与跟踪，将基于风格迁移的扰动叠加到选定区域，提升了对抗攻击的自然性与高分辨率下的可扩展性，同时保持欺骗率和查询效率。
UniVST: A Unified Framework for Training-free Localized Video Style Transfer
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, China（中国教育部多媒体可信感知与高效计算重点实验室，厦门大学，中国）；Rakuten Asia Pte. Ltd.；School of Computing, National University of Singapore（新加坡国立大学计算机学院）；Institute of Artificial Intelligence, Xiamen University（厦门大学人工智能研究院）
University of Barcelona（巴塞罗那大学）；Computer Vision Center, Universitat Autónoma de Barcelona（巴塞罗那自治大学计算机视觉中心）；Microsoft Research（微软研究院）
This paper proposes a system for automatic social pattern characterization using a wearable photo-camera. The proposed pipeline consists of three major steps. First, detection of people with whom the camera wearer interacts and, second, categorization of the detected social interactions into formal and informal. These two steps act at event-level where each potential social event is modeled as a multi-dimensional time-series, whose dimensions correspond to a set of relevant features for each task, and a LSTM network is employed for time-series classification. In the last step, recurrences of t…
Czech Technical University in Prague（捷克布拉格技术大学）；Snap Inc.（Snap公司）
In this paper, we present a learning-based method to the keyframe-based video stylization that allows an artist to propagate the style from a few selected keyframes to the rest of the sequence. Its key advantage is that the resulting stylization is semantically meaningful, i.e., specific parts of moving objects are stylized according to the artist's intention. In contrast to previous style transfer techniques, our approach does not require any lengthy pre-training process nor a large training dataset. We demonstrate how to train an appearance translation network from scratch using only a few s…
Style-Aware Blending and Prototype-Based Cross-Contrast Consistency for Semi-Supervised Medical Image Segmentation
School of Information Science and Engineering（信息科学与工程学院）；Yunnan University（云南大学）；Yunnan Key Laboratory of Intelligent Systems and Computing（智能系统与计算云南省重点实验室）
Nanyang Technological University（南洋理工大学）；University of California, Berkeley（加利福尼亚大学伯克利分校）；SenseTime Research（商汤科技研究院）
We introduce a simple and versatile framework for image-to-image translation. We unearth the importance of normalization layers, and provide a carefully designed two-stream generative model with newly proposed feature transformations in a coarse-to-fine fashion. This allows multi-scale semantic structure information and style representation to be effectively captured and fused by the network, permitting our method to scale to various tasks in both unsupervised and supervised settings. No additional constraints (e.g., cycle consistency) are needed, contributing to a very clean and simple method…
Recently, FCNs have attracted widespread attention in the CD field. In pursuit of better CD performance, it has become a tendency to design deeper and more complicated FCNs, which inevitably brings about huge numbers of parameters and an unbearable computational burden. With the goal of designing a quite deep architecture to obtain more precise CD results while simultaneously decreasing parameter numbers to improve efficiency, in this work, we present a very deep and efficient CD network, entitled EffCDNet. In EffCDNet, to reduce the numerous parameters associated with deep architecture, an ef…
We introduce an approach that leverages surface normal predictions, along with appearance cues, to retrieve 3D models for objects depicted in 2D still images from a large CAD object library. Critical to the success of our approach is the ability to recover accurate surface normals for objects in the depicted scene. We introduce a skip-network model built on the pre-trained Oxford VGG convolutional neural network (CNN) for surface normal prediction. Our model achieves state-of-the-art accuracy on the NYUv2 RGB-D dataset for surface normal prediction, and recovers fine object detail compared to …
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
For the two-stream style methods in action recognition, fusing the two streams' predictions is always by the weighted averaging scheme. This fusion method with fixed weights lacks of pertinence to different action videos and always needs trial and error on the validation set. In order to enhance the adaptability of two-stream ConvNets and improve its performance, an end-to-end trainable gated fusion method, namely gating ConvNet, for the two-stream ConvNets is proposed in this paper based on the MoE (Mixture of Experts) theory. The gating ConvNet takes the combination of feature maps from the …
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）；Healthcare Technology Innovation Centre（医疗技术创新中心）；Indian Institute of Information Technology Design & Manufacturing Kancheepuram（金奈设计与制造印度理工学院）；Zasti（Zasti公司）
Recently, state-of-the-art results have been achieved in semantic segmentation using fully convolutional networks (FCNs). Most of these networks employ encoder-decoder style architecture similar to U-Net and are trained with images and the corresponding segmentation maps as a pixel-wise classification task. Such frameworks only exploit class information by using the ground truth segmentation maps. In this paper, we propose a multi-task learning framework with the main aim of exploiting structural and spatial information along with the class information. We modify the decoder part of the FCN to…
The Zero-Shot Sketch-based Image Retrieval (ZS-SBIR) is a challenging task because of the large domain gap between sketches and natural images as well as the semantic inconsistency between seen and unseen categories. Previous literature bridges seen and unseen categories by semantic embedding, which requires prior knowledge of the exact class names and additional extraction efforts. And most works reduce domain gap by mapping sketches and natural images into a common high-level space using constructed sketch-image pairs, which ignore the unpaired information between images and sketches. To add…
Utilizing the trained model under different conditions without data annotation is attractive for robot applications. Towards this goal, one class of methods is to translate the image style from another environment to the one on which models are trained. In this paper, we propose a weakly-paired setting for the style translation, where the content in the two images is aligned with errors in poses. These images could be acquired by different sensors in different conditions that share an overlapping region, e.g. with LiDAR or stereo cameras, from sunny days or foggy nights. We consider this setti…
Kunming University of Science and Technology（昆明理工大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）
Since human-labeled samples are free for the target set, unsupervised person re-identification (Re-ID) has attracted much attention in recent years, by additionally exploiting the source set. However, due to the differences on camera styles, illumination and backgrounds, there exists a large gap between source domain and target domain, introducing a great challenge on cross-domain matching. To tackle this problem, in this paper we propose a novel method named Dual-stream Reciprocal Disentanglement Learning (DRDL), which is quite efficient in learning domain-invariant features. In DRDL, two enc…
We present a framework for interactive design of new image stylizations using a wide range of predefined filter blocks. Both novel and off-the-shelf image filtering and rendering techniques are extended and combined to allow the user to unleash their creativity to intuitively invent, modify, and tune new styles from a given set of filters. In parallel to this manual design, we propose a novel procedural approach that automatically assembles sequences of filters, leading to unique and novel styles. An important aim of our framework is to allow for interactive exploration and design, as well as …
Georgia Institute of Technology（佐治亚理工学院）；Georgia Tech Research Institution（佐治亚理工研究所）
Recent two-stream deep Convolutional Neural Networks (ConvNets) have made significant progress in recognizing human actions in videos. Despite their success, methods extending the basic two-stream ConvNet have not systematically explored possible network architectures to further exploit spatiotemporal dynamics within video sequences. Further, such networks often use different baseline two-stream networks. Therefore, the differences and the distinguishing factors between various methods using Recurrent Neural Networks (RNN) or convolutional networks on temporally-constructed feature vectors (Te…
