Automatic portrait video matting is an under-constrained problem. Most state-of-the-art methods only exploit the semantic information and process each frame individually. Their performance is compromised due to the lack of temporal information between the frames. To solve this problem, we propose the context motion network to leverage semantic information and motion information. To capture the motion information, we estimate the optical flow and design a context-motion updating operator to integrate features between frames recurrently. Our experiments show that our network outperforms state-of-the-art matting methods significantly on the Video240K SD dataset.
National Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；North China University of Technology（北方工业大学）
Image matting plays an important role in image and video editing. However, the formulation of image matting is inherently ill-posed. Traditional methods usually employ interaction to deal with the image matting problem with trimaps and strokes, and cannot run on the mobile phone in real-time. In this paper, we propose a real-time automatic deep matting approach for mobile devices. By leveraging the densely connected blocks and the dilated convolution, a light full convolutional network is designed to predict a coarse binary mask for portrait images. And a feathering block, which is edge-preser…
City University of Hong Kong（香港城市大学）；Dalian University of Technology（大连理工大学）
To address the challenging portrait video matting problem more precisely, existing works typically apply some matting priors that require additional user efforts to obtain, such as annotated trimaps or background images. In this work, we observe that instead of asking the user to explicitly provide a background image, we may recover it from the input video itself. To this end, we first propose a novel background restoration module (BRM) to recover the background image dynamically from the input video. BRM is extremely lightweight and can be easily integrated into existing matting models. By co…
Multimedia Laboratory, The Chinese University of Hong Kong（香港中文大学多媒体实验室）；Adobe NextCam；Shanghai AI Laboratory（上海人工智能实验室）；CPII under InnoHK（创新香港研发平台下的CPII）
City University of Hong Kong（香港城市大学）；SenseTime Research（商汤科技研究院）
Existing portrait matting methods either require auxiliary inputs that are costly to obtain or involve multiple stages that are computationally expensive, making them less suitable for real-time applications. In this work, we present a light-weight matting objective decomposition network (MODNet) for portrait matting in real-time with a single input image. The key idea behind our efficient design is by optimizing a series of sub-objectives simultaneously via explicit constraints. In addition, MODNet includes two novel techniques for improving model efficiency and robustness. First, an Efficien…
Efficient Portrait Matte Creation With Layer Diffusion and Connectivity Priors
School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）；School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院）
We resolve the ill-posed alpha matting problem from a completely different perspective. Given an input portrait image, instead of estimating the corresponding alpha matte, we focus on the other end, to subtly enhance this input so that the alpha matte can be easily estimated by any existing matting models. This is accomplished by exploring the latent space of GAN models. It is demonstrated that interpretable directions can be found in the latent space and they correspond to semantic image transformations. We further explore this property in alpha matting. Particularly, we invert an input portr…
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Istanbul Technical University（伊斯坦布尔理工大学）；Carnegie Mellon University（卡内基梅隆大学）
In the portrait matting, the goal is to predict an alpha matte that identifies the effect of each pixel on the foreground subject. Traditional approaches and most of the existing works utilized an additional input, e.g., trimap, background image, to predict alpha matte. However, (1) providing additional input is not always practical, and (2) models are too sensitive to these additional inputs. To address these points, in this paper, we introduce an additional input-free approach to perform portrait matting. We divide the task into two subtasks, segmentation and alpha matte prediction. We first…
We proposed a novel trimap free video matting method based on the attention mechanism. By the nature of the problem, most existing approaches use either multiple computational expansive modules or complex algorithms to exploit temporal information fully. We designed a temporal aggregation module to compute the temporal coherence between the current frame and its two previous frames.
The University of Sydney（悉尼大学）；JD Explore Academy（京东探索研究院）
Recently, there has been an increasing concern about the privacy issue raised by using personally identifiable information in machine learning. However, previous portrait matting methods were all based on identifiable portrait images. To fill the gap, we present P3M-10k in this paper, which is the first large-scale anonymized benchmark for Privacy-Preserving Portrait Matting. P3M-10k consists of 10,000 high-resolution face-blurred portrait images along with high-quality alpha mattes. We systematically evaluate both trimap-free and trimap-based matting methods on P3M-10k and find that existing …
We tackle the problem of automatic portrait matting on mobile devices. The proposed model is aimed at attaining real-time inference on mobile devices with minimal degradation of model performance. Our model MMNet, based on multi-branch dilated convolution with linear bottleneck blocks, outperforms the state-of-the-art model and is orders of magnitude faster. The model can be accelerated four times to attain 30 FPS on Xiaomi Mi 5 device with moderate increase in the gradient error. Under the same conditions, our model has an order of magnitude less number of parameters and is faster than Mobile…
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Istanbul Technical University（伊斯坦布尔理工大学）；Carnegie Mellon University（卡内基梅隆大学）
Exposure errors in an image cause a degradation in the contrast and low visibility in the content. In this paper, we address this problem and propose an end-to-end exposure correction model in order to handle both under- and overexposure errors with a single model. Our model contains an image encoder, consecutive residual blocks, and image decoder to synthesize the corrected image. We utilize perceptual loss, feature matching loss, and multi-scale discriminator to increase the quality of the generated image as well as to make the training more stable. The experimental results indicate the effe…
Indian Institute of Technology, Gandhinagar（甘地讷格尔印度理工学院）
Image matting is a longstanding problem in computational photography. Although, it has been studied for more than two decades, yet there is a challenge of developing an automatic matting algorithm which does not require any human efforts. Most of the state-of-the-art matting algorithms require human intervention in the form of trimap or scribbles to generate the alpha matte form the input image. In this paper, we present a simple and efficient approach to automatically generate the trimap from the input image and make the whole matting process free from human-in-the-loop. We use learning based…
McGill University（麦吉尔大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳人工智能与机器人学会）
Natural image matting aims to precisely separate foreground objects from background using alpha matte. Fully automatic natural image matting without external annotation is challenging. Well-performed matting methods usually require accurate labor-intensive handcrafted trimap as extra input, while the performance of automatic trimap generation method of dilating foreground segmentation fluctuates with segmentation quality. Therefore, we argue that how to handle trade-off of additional information input is a major issue in automatic matting. This paper presents a semantic-guided automatic natura…
Huazhong University of Science and Technology（华中科技大学）
We introduce in-context matting, a novel task setting of image matting. Given a reference image of a certain foreground and guided priors such as points, scribbles, and masks, in-context matting enables automatic alpha estimation on a batch of target images of the same foreground category, without additional auxiliary input. This setting marries good performance in auxiliary input-based matting and ease of use in automatic matting, which finds a good trade-off between customization and automation. To overcome the key challenge of accurate foreground matching, we introduce IconMatting, an in-co…
We design a real-time portrait matting pipeline for everyday use, particularly for "virtual backgrounds" in video conferences. Existing segmentation and matting methods prioritize accuracy and quality over throughput and efficiency, and our pipeline enables trading off a controllable amount of accuracy for better throughput by leveraging online distillation on the input video stream. We construct our own dataset of simulated video calls in various scenarios, and show that our approach delivers a 5x speedup over a saliency detection based pipeline in a non-GPU accelerated setting while deliveri…
Image compositing is a key step in film making and image editing that aims to segment a foreground object and combine it with a new background. Automatic image compositing can be done easily in a studio using chroma-keying when the background is pure blue or green. However, image compositing in natural scenes with complex backgrounds remains a tedious task, requiring experienced artists to hand-segment. In order to achieve automatic compositing in natural scenes, we propose a fully automated method that integrates instance segmentation and image matting processes to generate high-quality seman…
Tencent Online Video（腾讯在线视频）；Tencent PCG（腾讯平台与内容事业群）；International Digital Economy Academy (IDEA)（国际数字经济研究院）
Automatic human matting is highly desired for many real applications. We investigate recent human matting methods and show that common bad cases happen when semantic human segmentation fails. This indicates that semantic understanding is crucial for robust human matting. From this, we develop a fast yet accurate human matting framework, named Semantic Guided Human Matting (SGHM). It builds on a semantic human segmentation network and introduces a light-weight matting module with only marginal computational cost. Unlike previous works, our framework is data efficient, which requires a small amo…
In this paper, we propose an image matting framework called Salient Image Matting to estimate the per-pixel opacity value of the most salient foreground in an image. To deal with a large amount of semantic diversity in images, a trimap is conventionally required as it provides important guidance about object semantics to the matting process. However, creating a good trimap is often expensive and timeconsuming. The SIM framework simultaneously deals with the challenge of learning a wide range of semantics and salient object types in a fully automatic and an end to end manner. Specifically, our …
The University of Sydney（悉尼大学）；JD Explore Academy, JD.com（京东探索研究院）
Automatic image matting (AIM) refers to estimating the soft foreground from an arbitrary natural image without any auxiliary input like trimap, which is useful for image editing. Prior methods try to learn semantic features to aid the matting process while being limited to images with salient opaque foregrounds such as humans and animals. In this paper, we investigate the difficulties when extending them to natural images with salient transparent/meticulous foregrounds or non-salient foregrounds. To address the problem, a novel end-to-end matting network is proposed, which can predict a genera…
Natural image matting separates the foreground from background in fractional occupancy which can be caused by highly transparent objects, complex foreground (e.g., net or tree), and/or objects containing very fine details (e.g., hairs). Although conventional matting formulation can be applied to all of the above cases, no previous work has attempted to reason the underlying causes of matting due to various foreground semantics. We show how to obtain better alpha mattes by incorporating into our framework semantic classification of matting regions. Specifically, we consider and learn 20 classes…
Image matting refers to the estimation of the opacity of foreground objects. It requires correct contours and fine details of foreground objects for the matting results. To better accomplish human image matting tasks, we propose the Cascade Image Matting Network with Deformable Graph Refinement, which can automatically predict precise alpha mattes from single human images without any additional inputs. We adopt a network cascade architecture to perform matting from low-to-high resolution, which corresponds to coarse-to-fine optimization. We also introduce the Deformable Graph Refinement (DGR) …
In this paper, we propose an end to end solution for image matting i.e high-precision extraction of foreground objects from natural images. Image matting and background detection can be achieved easily through chroma keying in a studio setting when the background is either pure green or blue. Nonetheless, image matting in natural scenes with complex and uneven depth backgrounds remains a tedious task that requires human intervention. To achieve complete automatic foreground extraction in natural scenes, we propose a method that assimilates semantic segmentation and deep image matting processes…
We in this paper solve the problem of high-quality automatic real-time background cut for 720p portrait videos. We first handle the background ambiguity issue in semantic segmentation by proposing a global background attenuation model. A spatial-temporal refinement network is developed to further refine the segmentation errors in each frame and ensure temporal coherence in the segmentation map. We form an end-to-end network for training and testing. Each module is designed considering efficiency and accuracy. We build a portrait dataset, which includes 8,000 images with high-quality labeled ma…
We propose a method for creating a matte -- the per-pixel foreground color and alpha -- of a person by taking photos or videos in an everyday setting with a handheld camera. Most existing matting methods require a green screen background or a manually created trimap to produce a good matte. Automatic, trimap-free methods are appearing, but are not of comparable quality. In our trimap free approach, we ask the user to take an additional photo of the background without the subject at the time of capture. This step requires a small amount of foresight but is far less time-consuming than creating …
Extracting accurate foreground objects from a scene is an essential step for many video applications. Traditional background subtraction algorithms can generate coarse estimates, but generating high quality masks requires professional softwares with significant human interventions, e.g., providing trimaps or labeling key frames. We propose an automatic foreground extraction method in applications where a static but imperfect background is available. Examples include filming and surveillance where the background can be captured before the objects enter the scene or after they leave the scene. O…
In actual industrial production, the assessment of the steel plate welding effect is an important task, and the segmentation of the weld section is the basis of the assessment. This paper proposes an industrial weld segmentation network based on a deep learning semantic segmentation algorithm fused with heatmap detail guidance and Image Matting to solve the automatic segmentation problem of weld regions. In the existing semantic segmentation networks, the boundary information can be preserved by fusing the features of both high-level and low-level layers. However, this method can lead to insuf…
Most automatic matting methods try to separate the salient foreground from the background. However, the insufficient quantity and subjective bias of the current existing matting datasets make it difficult to fully explore the semantic association between object-to-object and object-to-environment in a given image. In this paper, we propose a Situational Perception Guided Image Matting (SPG-IM) method that mitigates subjective bias of matting annotations and captures sufficient situational perception information for better global saliency distilled from the visual-to-textual task. SPG-IM can be…
Human matting, high quality extraction of humans from natural images, is crucial for a wide variety of applications. Since the matting problem is severely under-constrained, most previous methods require user interactions to take user designated trimaps or scribbles as constraints. This user-in-the-loop nature makes them difficult to be applied to large scale data or time-sensitive scenarios. In this paper, instead of using explicit user input constraints, we employ implicit semantic constraints learned from data and propose an automatic human matting algorithm (SHM). SHM is the first algorith…
Data61/CSIRO（联邦科学与工业研究组织Data61）；Australian National University（澳大利亚国立大学）
Given an artistic portrait, recovering the latent photorealistic face that preserves the subject's identity is challenging because the facial details are often distorted or fully lost in artistic portraits. We develop an Identity-preserving Face Recovery from Portraits (IFRP) method that utilizes a Style Removal network (SRN) and a Discriminative Network (DN). Our SRN, composed of an autoencoder with residual block-embedded skip connections, is designed to transfer feature maps of stylized images to the feature maps of the corresponding photorealistic faces. Owing to the Spatial Transformer Ne…
Australian National University（澳大利亚国立大学）；Data61/CSIRO（数据61/联邦科学与工业研究组织）
Recovering the latent photorealistic faces from their artistic portraits aids human perception and facial analysis. However, a recovery process that can preserve identity is challenging because the fine details of real faces can be distorted or lost in stylized images. In this paper, we present a new Identity-preserving Face Recovery from Portraits (IFRP) to recover latent photorealistic faces from unaligned stylized portraits. Our IFRP method consists of two components: Style Removal Network (SRN) and Discriminative Network (DN). The SRN is designed to transfer feature maps of stylized images…
Department of Computer Science, Rutgers University（罗格斯大学计算机科学系）
This paper presents Generative Adversarial Talking Head (GATH), a novel deep generative neural network that enables fully automatic facial expression synthesis of an arbitrary portrait with continuous action unit (AU) coefficients. Specifically, our model directly manipulates image pixels to make the unseen subject in the still photo express various emotions controlled by values of facial AU coefficients, while maintaining her personal characteristics, such as facial geometry, skin color and hair style, as well as the original surrounding background. In contrast to prior work, GATH is purely d…
The University of Adelaide（阿德莱德大学）；Zhejiang University（浙江大学）；MeiTuan（美团）；Baidu（百度）
Most existing real-time deep models trained with each frame independently may produce inconsistent results across the temporal axis when tested on a video sequence. A few methods take the correlations in the video sequence into account,e.g., by propagating the results to the neighboring frames using optical flow or extracting frame representations using multi-frame information, which may lead to inaccurate results or unbalanced latency. In this work, we focus on improving the temporal consistency without introducing computation overhead in inference. To this end, we perform inference at each f…
Face portrait line drawing is a unique style of art which is highly abstract and expressive. However, due to its high semantic constraints, many existing methods learn to generate portrait drawings using paired training data, which is costly and time-consuming to obtain. In this paper, we propose a novel method to automatically transform face photos to portrait drawings using unpaired training data with two new features; i.e., our method can (1) learn to generate high quality portrait drawings in multiple styles using a single network and (2) generate portrait drawings in a "new style" unseen …
Technical University of Munich（慕尼黑工业大学）；Stanford University（斯坦福大学）；Max-Planck-Institute for Informatics（马克斯·普朗克信息学研究所）；University of Erlangen-Nuremberg（埃尔朗根-纽伦堡大学）
We propose HeadOn, the first real-time source-to-target reenactment approach for complete human portrait videos that enables transfer of torso and head motion, face expression, and eye gaze. Given a short RGB-D video of the target actor, we automatically construct a personalized geometry proxy that embeds a parametric head, eye, and kinematic torso model. A novel real-time reenactment algorithm employs this proxy to photo-realistically map the captured motion from the source actor to the target actor. On top of the coarse geometric proxy, we propose a video-based rendering technique that compo…
This paper proposes a vision-based method for video sky replacement and harmonization, which can automatically generate realistic and dramatic sky backgrounds in videos with controllable styles. Different from previous sky editing methods that either focus on static photos or require inertial measurement units integrated in smartphones on shooting videos, our method is purely vision-based, without any requirements on the capturing devices, and can be well applied to either online or offline processing scenarios. Our method runs in real-time and is free of user interactions. We decompose this a…
We propose an end-to-end lecture video generation system that can generate realistic and complete lecture videos directly from annotated slides, instructor's reference voice and instructor's reference portrait video. Our system is primarily composed of a speech synthesis module with few-shot speaker adaptation and an adversarial learning-based talking-head generation module. It is capable of not only reducing instructors' workload but also changing the language and accent which can help the students follow the lecture more easily and enable a wider dissemination of lecture contents. Our experi…
Adobe Systems Romania（Adobe系统罗马尼亚公司）；LAPI, University Politehnica of Bucharest（布加勒斯特理工大学LAPI）
Rectifying the orientation of images represents a daily task for every photographer. This task may be complicated even for the human eye, especially when the horizon or other horizontal and vertical lines in the image are missing. In this paper we address this problem and propose a new deep learning network specially adapted for image rotation correction: we introduce the rectangle-shaped depthwise convolutions which are specialized in detecting long lines from the image and a new adapted loss function that addresses the problem of orientation errors. Compared to other methods that are able to…
Versatile Multimodal Controls for Expressive Talking Human Animation
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi'an Jiaotong University, Ant Group（人机混合增强智能国家级实验室，西安交通大学，蚂蚁集团）；National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi'an Jiaotong University（人机混合增强智能国家级实验室，西安交通大学）；University at Buffalo（布法罗大学）
Weak to Strong: VLM-Based Pseudo-Labeling as a Weakly Supervised Training Strategy in Multimodal Video-based Hidden Emotion Understanding Tasks
The University of New South Wales, Sydney, New South Wales, Australia（新南威尔士大学）；The University of Sydney, Sydney, New South Wales, Australia（悉尼大学）；School of Software and Microelectronics, Peking University, Zibo, Shandong, China（北京大学软件与微电子学院）；Shandong University of Technology, Beijing, China（山东理工大学）
Tsinghua University（清华大学）；National Engineering Laboratory for Neuromodulation（神经调控国家工程实验室）
Data sharing for medical research has been difficult as open-sourcing clinical data may violate patient privacy. Traditional methods for face de-identification wipe out facial information entirely, making it impossible to analyze facial behavior. Recent advancements on whole-body keypoints detection also rely on facial input to estimate body keypoints. Both facial and body keypoints are critical in some medical diagnoses, and keypoints invariability after de-identification is of great importance. Here, we propose a solution using deepfake technology, the face swapping technique. While this swa…
