Image-based virtual try-on is an increasingly important task for online shopping. It aims to synthesize images of a specific person wearing a specified garment. Diffusion model-based approaches have recently become popular, as they are excellent at image synthesis tasks. However, these approaches usually employ additional image encoders and rely on the cross-attention mechanism for texture transfer from the garment to the person image, which affects the try-on's efficiency and fidelity. To address these issues, we propose an Texture-Preserving Diffusion (TPD) model for virtual try-on, which enhances the fidelity of the results and introduces no additional image encoders. Accordingly, we make contributions from two aspects. First, we propose to concatenate the masked person and reference garment images along the spatial dimension and utilize the resulting image as the input for the diffusion model's denoising UNet. This enables the original self-attention layers contained in the diffusion model to achieve efficient and accurate texture transfer. Second, we propose a novel diffusion-based method that predicts a precise inpainting mask based on the person and reference garment images, further enhancing the reliability of the try-on results. In addition, we integrate mask prediction and image synthesis into a single compact model. The experimental results show that our approach can be applied to various try-on tasks, e.g., garment-to-person and person-to-person try-ons, and significantly outperforms state-of-the-art methods on popular VITON, VITON-HD databases. Code is available at https://github.com/Ga14way/TPD.

While progress has been made in the field of portrait reenactment, the problem of how to produce high-fidelity and robust videos remains. Recent studies normally find it challenging to handle rarely seen target poses due to the limitation of source data. This paper proposes the Video Portrait via Non-local Quantization Modeling (VPNQ) framework, which produces pose- and disturbance-robust reenactable video portraits. Our key insight is to learn position-invariant quantized local patch representations and build a mapping between simple driving signals and local textures with non-local spatial-temporal modeling. Specifically, instead of learning a universal quantized codebook, we identify that a personalized one can be trained to preserve desired position-invariant local details better. Then, a simple representation of projected landmarks can be used as sufficient driving signals to avoid 3D rendering. Following, we employ a carefully designed Spatio-Temporal Transformer to predict reasonable and temporally consistent quantized tokens from the driving signal. The predicted codes can be decoded back to robust and high-quality videos. Comprehensive experiments have been conducted to validate the effectiveness of our approach.

Occlusion poses a major challenge for person re-identification (ReID). Existing approaches typically rely on outside tools to infer visible body parts, which may be suboptimal in terms of both computational efficiency and ReID accuracy. In particular, they may fail when facing complex occlusions, such as those between pedestrians. Accordingly, in this paper, we propose a novel method named Quality-aware Part Models (QPM) for occlusion-robust ReID. First, we propose to jointly learn part features and predict part quality scores. As no quality annotation is available, we introduce a strategy that automatically assigns low scores to occluded body parts, thereby weakening the impact of occluded body parts on ReID results. Second, based on the predicted part quality scores, we propose a novel identity-aware spatial attention (ISA) module. In this module, a coarse identity-aware feature is utilized to highlight pixels of the target pedestrian, so as to handle the occlusion between pedestrians. Third, we design an adaptive and efficient approach for generating global features from common non-occluded regions with respect to each image pair. This design is crucial, but is often ignored by existing methods. QPM has three key advantages: 1) it does not rely on any outside tools in either the training or inference stages; 2) it handles occlusions caused by both objects and other pedestrians; 3) it is highly computationally efficient. Experimental results on four popular databases for occluded ReID demonstrate that QPM consistently outperforms state-of-the-art methods by significant margins. The code of QPM is available athttps://github.com/Wang-pengfei/QPM.

Advanced face swapping methods have achieved appealing results. However, most of these methods have many parameters and computations, which makes it challenging to apply them in real-time applications or deploy them on edge devices like mobile phones. In this work, we propose a lightweight Identity-aware Dynamic Network (IDN) for subject-agnostic face swapping by dynamically adjusting the model parameters according to the identity information. In particular, we design an efficient Identity Injection Module (IIM) by introducing two dynamic neural network techniques, including the weights prediction and weights modulation. Once the IDN is updated, it can be applied to swap faces given any target image or video. The presented IDN contains only 0.50M parameters and needs 0.33G FLOPs per frame, making it capable for real-time video face swapping on mobile phones. In addition, we introduce a knowledge distillation-based method for stable training, and a loss reweighting module is employed to obtain better synthesized results. Finally, our method achieves comparable results with the teacher models and other state-of-the-art methods.

Generating expressive talking heads is essential for creating virtual humans. However, existing one- or few-shot methods focus on lip-sync and head motion, ignoring the emotional expressions that make talking faces realistic. In this paper, we propose the Granularly Controlled Audio-Visual Talking Heads (GC-AVT), which controls lip movements, head poses, and facial expressions of a talking head in a granular manner. Our insight is to decouple the audio-visual driving sources through prior-based pre-processing designs. Detailedly, we disassemble the driving image into three complementary parts including: 1) a cropped mouth that facilitates lip-sync; 2) a masked head that implicitly learns pose; and 3) the upper face which works corporately and complementarily with a time-shifted mouth to contribute the expression. Interestingly, the encoded features from the three sources are integrally balanced through reconstruction training. Extensive experiments show that our method generates expressive faces with not only synced mouth shapes, controllable poses, but precisely animated emotional expressions as well.

The head swapping task aims at flawlessly placing a source head onto a target body, which is of great importance to various entertainment scenarios. While face swapping has drawn much attention, the task of head swapping has rarely been explored, particularly under the few-shot setting. It is inherently challenging due to its unique needs in head modeling and background blending. In this paper, we present the Head Swapper (HeSer), which achieves few-shot head swapping in the wild through two delicately de-signed modules. Firstly, a Head2Head Aligner is devised to holistically migrate pose and expression information from the target to the source head by examining multi-scale in-formation. Secondly, to tackle the challenges of skin color variations and head-background mismatches in the swapping procedure, a Head2Scene Blender is introduced to si-multaneously modify facial skin color and fill mismatched gaps on the background around the head. Particularly, seamless blending is achieved with the help of a Semantic-Guided Color Reference Creation procedure and a Blending UNet. Extensive experiments demonstrate that the proposed method produces superior head swapping results on a variety of scenes.

Few-shot font generation (FFG), which aims to generate a new font with a few examples, is gaining increasing attention due to the significant reduction in labor cost. A typical FFG pipeline considers characters in a standard font library as content glyphs and transfers them to a new target font by extracting style information from the reference glyphs. Most existing solutions explicitly disentangle content and style of reference glyphs globally or component-wisely. However, the style of glyphs mainly lies in the local details, i.e. the styles of radicals, components, and strokes together depict the style of a glyph. Therefore, even a single character can contain different styles distributed over spatial locations. In this paper, we propose a new font generation approach by learning 1) the fine-grained local styles from references, and 2) the spatial correspondence between the content and reference glyphs. Therefore, each spatial location in the content glyph can be assigned with the right fine-grained style. To this end, we adopt cross-attention over the representation of the content glyphs as the queries and the representations of the reference glyphs as the keys and values. Instead of explicitly disentangling global or component-wise modeling, the cross-attention mechanism can attend to the right local styles in the reference glyphs and aggregate the reference styles into a fine-grained style representation for the given content glyphs. The experiments show that the proposed method outperforms the state-of-the-art methods in FFG. In particular, the user studies also demonstrate the style consistency of our approach significantly outperforms previous methods.

Recent advances in face forgery techniques produce nearly visually untraceable deepfake videos, which could be leveraged with malicious intentions. As a result, researchers have been devoted to deepfake detection. Previous studies have identified the importance of local low-level cues and temporal information in pursuit to generalize well across deepfake methods, however, they still suffer from robustness problem against post-processings. In this work, we propose the Local- & Temporal-aware Transformer-based Deepfake Detection (LTTD) framework, which adopts a local-to-global learning protocol with a particular focus on the valuable temporal information within local sequences. Specifically, we propose a Local Sequence Transformer (LST), which models the temporal consistency on sequences of restricted spatial regions, where low-level information is hierarchically enhanced with shallow layers of learned 3D filters. Based on the local temporal embeddings, we then achieve the final classification in a global contrastive way. Extensive experiments on popular datasets validate that our approach effectively spots local forgery cues and achieves state-of-the-art performance.

Previous studies have explored generating accurately lip-synced talking faces for arbitrary targets given audio conditions. However, most of them deform or generate the whole facial area, leading to non-realistic results. In this work, we delve into the formulation of altering only the mouth shapes of the target person. This requires masking a large percentage of the original image and seamlessly inpainting it with the aid of audio and reference frames. To this end, we propose the Audio-Visual Context-Aware Transformer (AV-CAT) framework, which produces accurate lip-sync with photo-realistic quality by predicting the masked mouth shapes. Our key insight is to exploit desired contextual information provided in audio and visual modalities thoroughly with delicately designed Transformers. Specifically, we propose a convolution-Transformer hybrid backbone and design an attention-based fusion strategy for filling the masked parts. It uniformly attends to the textural information on the unmasked regions and the reference frame. Then the semantic audio information is involved in enhancing the self-attention computation. Additionally, a refinement network with audio injection improves both image and lip-sync quality. Extensive experiments validate that our model can generate high-fidelity lip-synced results for arbitrary subjects.

Face attribute editing aims to generate faces with one or multiple desired face attributes manipulated while other details are preserved. Unlike prior works such as GAN inversion which has an expensive reverse mapping process, we propose a simple feed-forward network to generate high-fidelity manipulated faces. By simply employing some existing and easy-obtainable prior information, our method can control, transfer, and edit diverse attributes of faces in the wild. The proposed method can consequently be applied to various applications such as face swapping, face relighting, and makeup transfer. In our method, we decouple identity, expression, pose, and illumination by using 3D priors; separate texture and colors by using region-wise style codes. All the information is embedded into adversarial learning by our identity-style normalization module. Disentanglement losses are proposed to enhance the generator to extract information independently from each attribute. Comprehensive quantitative and qualitative evaluations have been conducted. In a single framework, our method achieves the best or competitive scores on a variety of face applications.

Fast appearance variations and the distractions of similar objects are two of the most challenging problems in visual object tracking. Unlike many existing trackers that focus on modeling only the target, in this work, we consider the transient variations of the whole scene. The key insight is that the object correspondence and spatial layout of the whole scene are consistent (i.e., global structure consistency) in consecutive frames which helps to disambiguate the target from distractors. Moreover, modeling transient variations enables to localize the target under fast variations. Specifically, we propose an effective and efficient short-term model that learns to exploit the global structure consistency in a short time and thus can handle fast variations and distractors. Since short-term modeling falls short of handling occlusion and out of the views, we adopt the long-short term paradigm and use a long-term model that corrects the short-term model when it drifts away from the target or the target is not present. These two components are carefully combined to achieve the balance of stability and plasticity during tracking. We empirically verify that the proposed tracker can tackle the two challenging scenarios and validate it on large scale benchmarks. Remarkably, our tracker improves state-of-the-art-performance on VOT2018 from 0.440 to 0.460, GOT-10k from 0.611 to 0.640, and NFS from 0.619 to 0.629.

Recent works have made great progress in semantic segmentation by exploiting richer context, most of which are designed from a spatial perspective. In contrast to previous works, we present the concept of class center which extracts the global context from a categorical perspective. This class-level context describes the overall representation of each class in an image. We further propose a novel module, named Attentional Class Feature (ACF) module, to calculate and adaptively combine different class centers according to each pixel. Based on the ACF module, we introduce a coarse-to-fine segmentation network, called Attentional Class Feature Network (ACFNet), which can be composed of an ACF module and any off-the-shell segmentation network (base network). In this paper, we use two types of base networks to evaluate the effectiveness of ACFNet. We achieve new state-of-the-art performance of 81.85% mIoU on Cityscapes dataset with only finely annotated data used for training.

In this paper, we present multinomial latent logistic regression (MLLR), a new learning paradigm that introduces latent variables to logistic regression. By inheriting the advantages of logistic regression, MLLR is efficiently optimized using the second-order derivatives and provides effective probabilistic analysis on output predictions. MLLR is particularly effective in weakly supervised settings where the latent variable has an exponential number of possible values. The effectiveness of MLLR is demonstrated on four different image understanding applications, including a new challenging architectural style classification task. Furthermore, we show that MLLR can be generalized to general structured output prediction, and in doing so, we provide a thorough investigation of the connections and differences between MLLR and existing related algorithms, including latent structural SVMs and hidden conditional random fields.

Variations in the appearance of a tracked object, such as changes in geometry/photometry, camera viewpoint, illumination, or partial occlusion, pose a major challenge to object tracking. Here, we adopt cognitive psychology principles to design a flexible representation that can adapt to changes in object appearance during tracking. Inspired by the well-known Atkinson-Shiffrin Memory Model, we propose MUlti-Store Tracker (MUSTer), a dual-component approach consisting of short- and long-term memory stores to process target appearance memories. A powerful and efficient Integrated Correlation Filter (ICF) is employed in the short-term store for short-term tracking. The integrated long-term component, which is based on keypoint matching-tracking and RANSAC estimation, can interact with the long-term memory and provide additional information for output control. MUSTer was extensively evaluated on the CVPR2013 Online Object Tracking Benchmark (OOTB) and ALOV++ datasets. The experimental results demonstrated the superior performance of MUSTer in comparison with other state-of-art trackers.

Various sparse-representation-based methods have been proposed to solve tracking problems, and most of them employ least squares (LSs) criteria to learn the sparse representation. In many tracking scenarios, traditional LS-based methods may not perform well owing to the presence of heavy-tailed noise. In this paper, we present a tracking approach using an approximate least absolute deviation (LAD)-based multitask multiview sparse learning method to enjoy robustness of LAD and take advantage of multiple types of visual features, such as intensity, color, and texture. The proposed method is integrated in a particle filter framework, where learning the sparse representation for each view of the single particle is regarded as an individual task. The underlying relationship between tasks across different views and different particles is jointly exploited in a unified robust multitask formulation based on LAD. In addition, to capture the frequently emerging outlier tasks, we decompose the representation matrix to two collaborative components that enable a more robust and accurate approximation. We show that the proposed formulation can be effectively approximated by Nesterov's smoothing method and efficiently solved using the accelerated proximal gradient method. The presented tracker is implemented using four types of features and is tested on numerous synthetic sequences and real-world video sequences, including the CVPR2013 tracking benchmark and ALOV++ data set. Both the qualitative and quantitative results demonstrate the superior performance of the proposed approach compared with several state-of-the-art trackers.

In traditional multi-instance learning (MIL), instances are typically represented by using a single feature view. As MIL becoming popular in domain specific learning tasks, aggregating multiple feature views to represent multi-instance bags has recently shown promising results, mainly because multiple views provide extra information for MIL tasks. Nevertheless, multiple views also increase the risk of involving redundant views and irrelevant features for learning. In this paper, we formulate a new cross-view feature selection problem that aims to identify the most representative features across all feature views for MIL. To achieve the goal, we design a new optimization problem by integrating both multi-view representation and multi-instance bag constraints. The solution to the objective function will ensure that the identified top-m features are the most informative ones across all feature views. Experiments on two real-world applications demonstrate the performance of the cross-view feature selection for content-based image retrieval and social media content recommendation.

Graph classification has traditionally focused on graphs generated from a single feature view. In many applications, it is common to have useful information from different channels/views to describe objects, which naturally results in a new representation with multiple graphs generated from different feature views being used to describe one object. In this paper, we formulate a new Multi-Graph-View learning task for graph classification, where each object to be classified contains graphs from multiple graph-views. This problem setting is essentially different from traditional single-graph-view graph classification, where graphs are from one single feature view. To solve the problem, we propose a Cross Graph-View Sub graph Feature based Learning (gCGVFL) algorithm that explores an optimal set of sub graphs, across multiple graph-views, as features to represent graphs. Specifically, we derive an evaluation criterion to estimate the discriminative power and the redundancy of sub graph features across all views, and assign proper weight values to each view to indicate its importance for graph classification. The iterative cross graph-view sub graph scoring and graph-view weight updating form a closed loop to find optimal sub graphs to represent graphs for multi-graph-view learning. Experiments and comparisons on real-world tasks demonstrate the algorithm's performance.

In this paper, we formulate a new multi-graph learning task with only positive and unlabeled bags, where labels are only available for bags but not for individual graphs inside the bag. This problem setting raises significant challenges because bag-of-graph setting does not have features to directly represent graph data, and no negative bags exits for deriving discriminative classification models. To solve the challenge, we propose a puMGL learning framework which relies on two iteratively combined processes for multigraph learning: (1) deriving features to represent graphs for learning; and (2) deriving discriminative models with only positive and unlabeled graph bags. For the former, we derive a subgraph scoring criterion to select a set of informative subgraphs to convert each graph into a feature space. To handle unlabeled bags, we assign a weight value to each bag and use the adjusted weight values to select most promising unlabeled bags as negative bags. A margin graph pool (MGP), which contains some representative graphs from positive bags and identified negative bags, is used for selecting subgraphs and training graph classifiers. The iterative subgraph scoring, bag weight updating, and MGP based graph classification forms a closed loop to find optimal subgraphs and most suitable unlabeled bags for multi-graph learning. Experiments and comparisons on real-world multigraph data demonstrate the algorithm performance.

Combining multiple observation views has proven beneficial for tracking. In this paper, we cast tracking as a novel multi-task multi-view sparse learning problem and exploit the cues from multiple views including various types of visual features, such as intensity, color, and edge, where each feature observation can be sparsely represented by a linear combination of atoms from an adaptive feature dictionary. The proposed method is integrated in a particle filter framework where every view in each particle is regarded as an individual task. We jointly consider the underlying relationship between tasks across different views and different particles, and tackle it in a unified robust multi-task formulation. In addition, to capture the frequently emerging outlier tasks, we decompose the representation matrix to two collaborative components which enable a more robust and accurate approximation. We show that the proposed formulation can be efficiently solved using the Accelerated Proximal Gradient method with a small number of closed-form updates. The presented tracker is implemented using four types of features and is tested on numerous benchmark video sequences. Both the qualitative and quantitative results demonstrate the superior performance of the proposed approach compared to several state-of-the-art trackers.