Yongwei Nie

Lingwei Dang, Yongwei Nie, Chengjiang Long et al.

Diverse human motion prediction aims at predicting multiple possible future pose sequences from a sequence of observed poses. Previous approaches usually employ deep generative networks to model the conditional distribution of data, and then randomly sample outcomes from the distribution. While different results can be obtained, they are usually the most likely ones which are not diverse enough. Recent work explicitly learns multiple modes of the conditional distribution via a deterministic network, which however can only cover a fixed number of modes within a limited range. In this paper, we propose a novel sampling strategy for sampling very diverse results from an imbalanced multimodal distribution learned by a deep generative model. Our method works by generating an auxiliary space and smartly making randomly sampling from the auxiliary space equivalent to the diverse sampling from the target distribution. We propose a simple yet effective network architecture that implements this novel sampling strategy, which incorporates a Gumbel-Softmax coefficient matrix sampling method and an aggressive diversity promoting hinge loss function. Extensive experiments demonstrate that our method significantly improves both the diversity and accuracy of the samplings compared with previous state-of-the-art sampling approaches. Code and pre-trained models are available at https://github.com/Droliven/diverse_sampling.

Maomao Li, Ge Yuan, Cairong Wang et al.

This paper proposes a novel approach to face swapping from the perspective of fine-grained facial editing, dubbed "editing for swapping" (E4S). The traditional face swapping methods rely on global feature extraction and fail to preserve the detailed source identity. In contrast, we propose a Regional GAN Inversion (RGI) method, which allows the explicit disentanglement of shape and texture. Specifically, our E4S performs face swapping in the latent space of a pretrained StyleGAN, where a multi-scale mask-guided encoder is applied to project the texture of each facial component into regional style codes and a mask-guided injection module manipulating feature maps with the style codes. Based on this disentanglement, face swapping can be simplified as style and mask swapping. Besides, due to the large lighting condition gap, transferring the source skin into the target image may lead to disharmony lighting. We propose a re-coloring network to make the swapped face maintain the target lighting condition while preserving the source skin. Further, to deal with the potential mismatch areas during mask exchange, we design a face inpainting module to refine the face shape. The extensive comparisons with state-of-the-art methods demonstrate that our E4S outperforms existing methods in preserving texture, shape, and lighting. Our implementation is available at https://github.com/e4s2024/E4S2024.

Zhian Liu, Maomao Li, Yong Zhang et al.

We present a novel paradigm for high-fidelity face swapping that faithfully preserves the desired subtle geometry and texture details. We rethink face swapping from the perspective of fine-grained face editing, \textit{i.e., ``editing for swapping'' (E4S)}, and propose a framework that is based on the explicit disentanglement of the shape and texture of facial components. Following the E4S principle, our framework enables both global and local swapping of facial features, as well as controlling the amount of partial swapping specified by the user. Furthermore, the E4S paradigm is inherently capable of handling facial occlusions by means of facial masks. At the core of our system lies a novel Regional GAN Inversion (RGI) method, which allows the explicit disentanglement of shape and texture. It also allows face swapping to be performed in the latent space of StyleGAN. Specifically, we design a multi-scale mask-guided encoder to project the texture of each facial component into regional style codes. We also design a mask-guided injection module to manipulate the feature maps with the style codes. Based on the disentanglement, face swapping is reformulated as a simplified problem of style and mask swapping. Extensive experiments and comparisons with current state-of-the-art methods demonstrate the superiority of our approach in preserving texture and shape details, as well as working with high resolution images. The project page is http://e4s2022.github.io

Wenju Xu, Chengjiang Long, Yongwei Nie

Arbitrary style transfer has been demonstrated to be efficient in artistic image generation. Previous methods either globally modulate the content feature ignoring local details, or overly focus on the local structure details leading to style leakage. In contrast to the literature, we propose a new scheme \textit{``style kernel"} that learns {\em spatially adaptive kernels} for per-pixel stylization, where the convolutional kernels are dynamically generated from the global style-content aligned feature and then the learned kernels are applied to modulate the content feature at each spatial position. This new scheme allows flexible both global and local interactions between the content and style features such that the wanted styles can be easily transferred to the content image while at the same time the content structure can be easily preserved. To further enhance the flexibility of our style transfer method, we propose a Style Alignment Encoding (SAE) module complemented with a Content-based Gating Modulation (CGM) module for learning the dynamic style kernels in focusing regions. Extensive experiments strongly demonstrate that our proposed method outperforms state-of-the-art methods and exhibits superior performance in terms of visual quality and efficiency.

Yongwei Nie, Changzhen Liu, Chengjiang Long et al.

Besides a 3D mesh, Human Mesh Recovery (HMR) methods usually need to estimate a camera for computing 2D reprojection loss. Previous approaches may encounter the following problem: both the mesh and camera are not correct but the combination of them can yield a low reprojection loss. To alleviate this problem, we define multiple RoIs (region of interest) containing the same human and propose a multiple-RoI-based HMR method. Our key idea is that with multiple RoIs as input, we can estimate multiple local cameras and have the opportunity to design and apply additional constraints between cameras to improve the accuracy of the cameras and, in turn, the accuracy of the corresponding 3D mesh. To implement this idea, we propose a RoI-aware feature fusion network by which we estimate a 3D mesh shared by all RoIs as well as local cameras corresponding to the RoIs. We observe that local cameras can be converted to the camera of the full image through which we construct a local camera consistency loss as the additional constraint imposed on local cameras. Another benefit of introducing multiple RoIs is that we can encapsulate our network into a contrastive learning framework and apply a contrastive loss to regularize the training of our network. Experiments demonstrate the effectiveness of our multi-RoI HMR method and superiority to recent prior arts. Our code is available at https://github.com/CptDiaos/Multi-RoI.

Yongwei Nie, Mingxian Fan, Chengjiang Long et al.

Human Mesh Recovery (HMR) is the task of estimating a parameterized 3D human mesh from an image. There is a kind of methods first training a regression model for this problem, then further optimizing the pretrained regression model for any specific sample individually at test time. However, the pretrained model may not provide an ideal optimization starting point for the test-time optimization. Inspired by meta-learning, we incorporate the test-time optimization into training, performing a step of test-time optimization for each sample in the training batch before really conducting the training optimization over all the training samples. In this way, we obtain a meta-model, the meta-parameter of which is friendly to the test-time optimization. At test time, after several test-time optimization steps starting from the meta-parameter, we obtain much higher HMR accuracy than the test-time optimization starting from the simply pretrained regression model. Furthermore, we find test-time HMR objectives are different from training-time objectives, which reduces the effectiveness of the learning of the meta-model. To solve this problem, we propose a dual-network architecture that unifies the training-time and test-time objectives. Our method, armed with meta-learning and the dual networks, outperforms state-of-the-art regression-based and optimization-based HMR approaches, as validated by the extensive experiments. The codes are available at https://github.com/fmx789/Meta-HMR.

Lingwei Dang, Yongwei Nie, Chengjiang Long et al.

Human motion prediction is a challenging task due to the stochasticity and aperiodicity of future poses. Recently, graph convolutional network has been proven to be very effective to learn dynamic relations among pose joints, which is helpful for pose prediction. On the other hand, one can abstract a human pose recursively to obtain a set of poses at multiple scales. With the increase of the abstraction level, the motion of the pose becomes more stable, which benefits pose prediction too. In this paper, we propose a novel Multi-Scale Residual Graph Convolution Network (MSR-GCN) for human pose prediction task in the manner of end-to-end. The GCNs are used to extract features from fine to coarse scale and then from coarse to fine scale. The extracted features at each scale are then combined and decoded to obtain the residuals between the input and target poses. Intermediate supervisions are imposed on all the predicted poses, which enforces the network to learn more representative features. Our proposed approach is evaluated on two standard benchmark datasets, i.e., the Human3.6M dataset and the CMU Mocap dataset. Experimental results demonstrate that our method outperforms the state-of-the-art approaches. Code and pre-trained models are available at https://github.com/Droliven/MSRGCN.

Zhian Liu, Yongwei Nie, Chengjiang Long et al.

In this paper, we propose $\text{HF}^2$-VAD, a Hybrid framework that integrates Flow reconstruction and Frame prediction seamlessly to handle Video Anomaly Detection. Firstly, we design the network of ML-MemAE-SC (Multi-Level Memory modules in an Autoencoder with Skip Connections) to memorize normal patterns for optical flow reconstruction so that abnormal events can be sensitively identified with larger flow reconstruction errors. More importantly, conditioned on the reconstructed flows, we then employ a Conditional Variational Autoencoder (CVAE), which captures the high correlation between video frame and optical flow, to predict the next frame given several previous frames. By CVAE, the quality of flow reconstruction essentially influences that of frame prediction. Therefore, poorly reconstructed optical flows of abnormal events further deteriorate the quality of the final predicted future frame, making the anomalies more detectable. Experimental results demonstrate the effectiveness of the proposed method. Code is available at \href{https://github.com/LiUzHiAn/hf2vad}{https://github.com/LiUzHiAn/hf2vad}.

Chenxi Zheng, Yihong Lin, Bangzhen Liu et al.

Current text-to-3D generation methods based on score distillation often suffer from geometric inconsistencies, leading to repeated patterns across different poses of 3D assets. This issue, known as the Multi-Face Janus problem, arises because existing methods struggle to maintain consistency across varying poses and are biased toward a canonical pose. While recent work has improved pose control and approximation, these efforts are still limited by this inherent bias, which skews the guidance during generation. To address this, we propose a solution called RecDreamer, which reshapes the underlying data distribution to achieve a more consistent pose representation. The core idea behind our method is to rectify the prior distribution, ensuring that pose variation is uniformly distributed rather than biased toward a canonical form. By modifying the prescribed distribution through an auxiliary function, we can reconstruct the density of the distribution to ensure compliance with specific marginal constraints. In particular, we ensure that the marginal distribution of poses follows a uniform distribution, thereby eliminating the biases introduced by the prior knowledge. We incorporate this rectified data distribution into existing score distillation algorithms, a process we refer to as uniform score distillation. To efficiently compute the posterior distribution required for the auxiliary function, RecDreamer introduces a training-free classifier that estimates pose categories in a plug-and-play manner. Additionally, we utilize various approximation techniques for noisy states, significantly improving system performance. Our experimental results demonstrate that RecDreamer effectively mitigates the Multi-Face Janus problem, leading to more consistent 3D asset generation across different poses.

Jinchen Yu, Yongwei Nie, Fei Qi et al.

The Segment Anything Model (SAM) has gained popularity as a versatile image segmentation method, thanks to its strong generalization capabilities across various domains. However, when applied to optic disc (OD) and optic cup (OC) segmentation tasks, SAM encounters challenges due to the complex structures, low contrast, and blurred boundaries typical of fundus images, leading to suboptimal performance. To overcome these challenges, we introduce a novel model, FunduSAM, which incorporates several Adapters into SAM to create a deep network specifically designed for OD and OC segmentation. The FunduSAM utilizes Adapter into each transformer block after encoder for parameter fine-tuning (PEFT). It enhances SAM's feature extraction capabilities by designing a Convolutional Block Attention Module (CBAM), addressing issues related to blurred boundaries and low contrast. Given the unique requirements of OD and OC segmentation, polar transformation is used to convert the original fundus OD images into a format better suited for training and evaluating FunduSAM. A joint loss is used to achieve structure preservation between the OD and OC, while accurate segmentation. Extensive experiments on the REFUGE dataset, comprising 1,200 fundus images, demonstrate the superior performance of FunduSAM compared to five mainstream approaches.

Chaohong Guo, Xun Mo, Yongwei Nie et al.

Temporal Video Grounding (TVG) aims to precisely localize video segments corresponding to natural language queries, which is a critical capability for long-form video understanding. Although existing reinforcement learning approaches encourage models to generate reasoning chains before predictions, they fail to explicitly constrain the reasoning process to ensure the quality of the final temporal predictions. To address this limitation, we propose Timestamp Anchor-constrained Reasoning for Temporal Video Grounding (TAR-TVG), a novel framework that introduces timestamp anchors within the reasoning process to enforce explicit supervision to the thought content. These anchors serve as intermediate verification points. More importantly, we require each reasoning step to produce increasingly accurate temporal estimations, thereby ensuring that the reasoning process contributes meaningfully to the final prediction. To address the challenge of low-probability anchor generation in models (e.g., Qwen2.5-VL-3B), we develop an efficient self-distillation training strategy: (1) initial GRPO training to collect 30K high-quality reasoning traces containing multiple timestamp anchors, (2) supervised fine-tuning (SFT) on distilled data, and (3) final GRPO optimization on the SFT-enhanced model. This three-stage training strategy enables robust anchor generation while maintaining reasoning quality. Experiments show that our model achieves state-of-the-art performance while producing interpretable, verifiable reasoning chains with progressively refined temporal estimations.

Xuyi Yang, Wenhao Zhang, Hongbo Jin et al.

Current Multimodal Large Language Models (MLLMs) often perform poorly in long video understanding, primarily due to resource limitations that prevent them from processing all video frames and their associated information. Efficiently extracting relevant information becomes a challenging task. Existing frameworks and evaluation tasks focus on identifying specific frames containing core objects from a large number of irrelevant frames, which does not align with the practical needs of real-world applications. To address this issue, we propose a new scenario under the video question-answering task, SceneQA, which emphasizes scene-based detail perception and reasoning abilities. And we develop the LVSQA dataset to support the SceneQA task, which is built upon carefully selected videos from LVBench and contains a new collection of question-answer pairs to promote a more fair evaluation of MLLMs' scene perception abilities in long videos. Inspired by human cognition, we introduce a novel method called SLFG. The core idea of SLFG is to combine individual frames into semantically coherent scene frames. By leveraging scene localization methods and dynamic frame reassembly mechanisms, SLFG significantly enhances the understanding capabilities of existing MLLMs in long videos. SLFG requires no modification to the original model architecture and boasts excellent plug-and-play usability. Experimental results show that this method performs exceptionally well in several long video benchmark tests. Code and dataset will be released at http://www.slfg.pkuzwh.cn.

Juntong Li, Lingwei Dang, Yukun Su et al.

Video Anomaly Detection (VAD) methods based on reconstruction or prediction face two critical challenges: (1) strong generalization capability often results in accurate reconstruction or prediction of abnormal events, making it difficult to distinguish normal from abnormal patterns; (2) reliance only on low-level appearance and motion cues limits their ability to identify high-level semantic in abnormal events from complex scenes. To address these limitations, we propose a novel VAD framework with two key innovations. First, to suppress excessive generalization, we introduce the Sparse Feature Filtering Module (SFFM) that employs bottleneck filters to dynamically and adaptively remove abnormal information from features. Unlike traditional memory modules, it does not need to memorize the normal prototypes across the training dataset. Further, we design the Mixture of Experts (MoE) architecture for SFFM. Each expert is responsible for extracting specialized principal features during running time, and different experts are selectively activated to ensure the diversity of the learned principal features. Second, to overcome the neglect of semantics in existing methods, we integrate a Vision-Language Model (VLM) to generate textual descriptions for video clips, enabling comprehensive joint modeling of semantic, appearance, and motion cues. Additionally, we enforce modality consistency through semantic similarity constraints and motion frame-difference contrastive loss. Extensive experiments on multiple public datasets validate the effectiveness of our multimodal joint modeling framework and sparse feature filtering paradigm. Project page at https://qzfm.github.io/sfn_vad_project_page/.

Chaohong Guo, Yihan He, Yongwei Nie et al.

Video Temporal Grounding (VTG) aims to localize the video segment that corresponds to a natural language query, which requires a comprehensive understanding of complex temporal dynamics. Existing Vision-LMMs typically perceive temporal dynamics via positional encoding, text-based timestamps, or visual frame numbering. However, these approaches exhibit notable limitations: assigning each frame a text-based timestamp token introduces additional computational overhead and leads to sparsity in visual attention, positional encoding struggles to capture absolute temporal information, and visual frame numbering often compromises spatial detail. To address these issues, we propose Temporal to Spatial Gridification (T2SGrid), a novel framework that reformulates video temporal understanding as a spatial understanding task. The core idea of T2SGrid is to process video content in clips rather than individual frames. we employ a overlapping sliding windows mechanism to segment the video into temporal clips. Within each window, frames are arranged chronologically in a row-major order into a composite grid image, effectively transforming temporal sequences into structured 2D layouts. The gridification not only encodes temporal information but also enhances local attention within each grid. Furthermore, T2SGrid enables the use of composite text timestamps to establish global temporal awareness. Experiments on standard VTG benchmarks demonstrate that T2SGrid achieves superior performance.

Yuyang Yu, Zhengwei Chen, Xuemiao Xu et al.

3D anomaly detection in point-cloud data is critical for industrial quality control, aiming to identify structural defects with high reliability. However, current memory bank-based methods often suffer from inconsistent feature transformations and limited discriminative capacity, particularly in capturing local geometric details and achieving rotation invariance. These limitations become more pronounced when registration fails, leading to unreliable detection results. We argue that point-cloud registration plays an essential role not only in aligning geometric structures but also in guiding feature extraction toward rotation-invariant and locally discriminative representations. To this end, we propose a registration-induced, rotation-invariant feature extraction framework that integrates the objectives of point-cloud registration and memory-based anomaly detection. Our key insight is that both tasks rely on modeling local geometric structures and leveraging feature similarity across samples. By embedding feature extraction into the registration learning process, our framework jointly optimizes alignment and representation learning. This integration enables the network to acquire features that are both robust to rotations and highly effective for anomaly detection. Extensive experiments on the Anomaly-ShapeNet and Real3D-AD datasets demonstrate that our method consistently outperforms existing approaches in effectiveness and generalizability.

Zhaoyu Chen, Hongnan Lin, Yongwei Nie et al.

Temporal Video Grounding (TVG) seeks to localize video segments matching a given textual query. Current methods, while optimizing for high temporal Intersection-over-Union (IoU), often overfit to this metric, compromising semantic action understanding in the video and query, a critical factor for robust TVG. To address this, we introduce Inversion Tasks for TVG (Invert4TVG), a novel framework that enhances both localization accuracy and action understanding without additional data. Our approach leverages three inversion tasks derived from existing TVG annotations: (1) Verb Completion, predicting masked action verbs in queries from video segments; (2) Action Recognition, identifying query-described actions; and (3) Video Description, generating descriptions of video segments that explicitly embed query-relevant actions. These tasks, integrated with TVG via a reinforcement learning framework with well-designed reward functions, ensure balanced optimization of localization and semantics. Experiments show our method outperforms state-of-the-art approaches, achieving a 7.1\% improvement in R1@0.7 on Charades-STA for a 3B model compared to Time-R1. By inverting TVG to derive query-related actions from segments, our approach strengthens semantic understanding, significantly raising the ceiling of localization accuracy.

Guide Yang, Chao Hou, Weilong Peng et al.

Deep neural networks (DNNs) often exhibit overconfidence when encountering out-of-distribution (OOD) samples, posing significant challenges for deployment. Since DNNs are trained on in-distribution (ID) datasets, the information flow of ID samples through DNNs inevitably differs from that of OOD samples. In this paper, we propose an Entropy-based Out-Of-distribution Detection (EOOD) framework. EOOD first identifies specific block where the information flow differences between ID and OOD samples are more pronounced, using both ID and pseudo-OOD samples. It then calculates the conditional entropy on the selected block as the OOD confidence score. Comprehensive experiments conducted across various ID and OOD settings demonstrate the effectiveness of EOOD in OOD detection and its superiority over state-of-the-art methods.

Yongwei Nie, Hao Huang, Chengjiang Long et al.

Video Anomaly Detection (VAD) has been extensively studied under the settings of One-Class Classification (OCC) and Weakly-Supervised learning (WS), which however both require laborious human-annotated normal/abnormal labels. In this paper, we study Unsupervised VAD (UVAD) that does not depend on any label by combining OCC and WS into a unified training framework. Specifically, we extend OCC to weighted OCC (wOCC) and propose a wOCC-WS interleaving training module, where the two models automatically generate pseudo-labels for each other. We face two challenges to make the combination effective: (1) Models' performance fluctuates occasionally during the training process due to the inevitable randomness of the pseudo labels. (2) Thresholds are needed to divide pseudo labels, making the training depend on the accuracy of user intervention. For the first problem, we propose to use wOCC requiring soft labels instead of OCC trained with hard zero/one labels, as soft labels exhibit high consistency throughout different training cycles while hard labels are prone to sudden changes. For the second problem, we repeat the interleaving training module multiple times, during which we propose an adaptive thresholding strategy that can progressively refine a rough threshold to a relatively optimal threshold, which reduces the influence of user interaction. A benefit of employing OCC and WS methods to compose a UVAD method is that we can incorporate the most recent OCC or WS model into our framework. Experiments demonstrate the effectiveness of the proposed UVAD framework.

Wenju Xu, Chengjiang Long, Yongwei Nie et al.

In this paper, we propose a novel framework named DRL-CPG to learn disentangled latent representation for controllable person image generation, which can produce realistic person images with desired poses and human attributes (e.g., pose, head, upper clothes, and pants) provided by various source persons. Unlike the existing works leveraging the semantic masks to obtain the representation of each component, we propose to generate disentangled latent code via a novel attribute encoder with transformers trained in a manner of curriculum learning from a relatively easy step to a gradually hard one. A random component mask-agnostic strategy is introduced to randomly remove component masks from the person segmentation masks, which aims at increasing the difficulty of training and promoting the transformer encoder to recognize the underlying boundaries between each component. This enables the model to transfer both the shape and texture of the components. Furthermore, we propose a novel attribute decoder network to integrate multi-level attributes (e.g., the structure feature and the attribute representation) with well-designed Dual Adaptive Denormalization (DAD) residual blocks. Extensive experiments strongly demonstrate that the proposed approach is able to transfer both the texture and shape of different human parts and yield realistic results. To our knowledge, we are the first to learn disentangled latent representations with transformers for person image generation.

Qing Zhang, Hao Jiang, Yongwei Nie et al.

We present a simple but effective technique to smooth out textures while preserving the prominent structures. Our method is built upon a key observation -- the coarsest level in a Gaussian pyramid often naturally eliminates textures and summarizes the main image structures. This inspires our central idea for texture filtering, which is to progressively upsample the very low-resolution coarsest Gaussian pyramid level to a full-resolution texture smoothing result with well-preserved structures, under the guidance of each fine-scale Gaussian pyramid level and its associated Laplacian pyramid level. We show that our approach is effective to separate structure from texture of different scales, local contrasts, and forms, without degrading structures or introducing visual artifacts. We also demonstrate the applicability of our method on various applications including detail enhancement, image abstraction, HDR tone mapping, inverse halftoning, and LDR image enhancement.

Tiezheng Ma, Yongwei Nie, Chengjiang Long et al.

This paper presents a high-quality human motion prediction method that accurately predicts future human poses given observed ones. Our method is based on the observation that a good initial guess of the future poses is very helpful in improving the forecasting accuracy. This motivates us to propose a novel two-stage prediction framework, including an init-prediction network that just computes the good guess and then a formal-prediction network that predicts the target future poses based on the guess. More importantly, we extend this idea further and design a multi-stage prediction framework where each stage predicts initial guess for the next stage, which brings more performance gain. To fulfill the prediction task at each stage, we propose a network comprising Spatial Dense Graph Convolutional Networks (S-DGCN) and Temporal Dense Graph Convolutional Networks (T-DGCN). Alternatively executing the two networks helps extract spatiotemporal features over the global receptive field of the whole pose sequence. All the above design choices cooperating together make our method outperform previous approaches by large margins: 6%-7% on Human3.6M, 5%-10% on CMU-MoCap, and 13%-16% on 3DPW.

Qing Zhang, Yongwei Nie, Wei-Shi Zheng

Exposure correction is one of the fundamental tasks in image processing and computational photography. While various methods have been proposed, they either fail to produce visually pleasing results, or only work well for limited types of image (e.g., underexposed images). In this paper, we present a novel automatic exposure correction method, which is able to robustly produce high-quality results for images of various exposure conditions (e.g., underexposed, overexposed, and partially under- and over-exposed). At the core of our approach is the proposed dual illumination estimation, where we separately cast the under- and over-exposure correction as trivial illumination estimation of the input image and the inverted input image. By performing dual illumination estimation, we obtain two intermediate exposure correction results for the input image, with one fixes the underexposed regions and the other one restores the overexposed regions. A multi-exposure image fusion technique is then employed to adaptively blend the visually best exposed parts in the two intermediate exposure correction images and the input image into a globally well-exposed image. Experiments on a number of challenging images demonstrate the effectiveness of the proposed approach and its superiority over the state-of-the-art methods and popular automatic exposure correction tools.

Qing Zhang, Yongwei Nie, Lei Zhu et al.

Although remarkable progress has been made, existing methods for enhancing underexposed photos tend to produce visually unpleasing results due to the existence of visual artifacts (e.g., color distortion, loss of details and uneven exposure). We observed that this is because they fail to ensure the perceptual consistency of visual information between the source underexposed image and its enhanced output. To obtain high-quality results free of these artifacts, we present a novel underexposed photo enhancement approach that is able to maintain the perceptual consistency. We achieve this by proposing an effective criterion, referred to as perceptually bidirectional similarity, which explicitly describes how to ensure the perceptual consistency. Particularly, we adopt the Retinex theory and cast the enhancement problem as a constrained illumination estimation optimization, where we formulate perceptually bidirectional similarity as constraints on illumination and solve for the illumination which can recover the desired artifact-free enhancement results. In addition, we describe a video enhancement framework that adopts the presented illumination estimation for handling underexposed videos. To this end, a probabilistic approach is introduced to propagate illuminations of sampled keyframes to the entire video by tackling a Bayesian Maximum A Posteriori problem. Extensive experiments demonstrate the superiority of our method over the state-of-the-art methods.

Qiuxia Lai, Salman Khan, Yongwei Nie et al.

Human visual system can selectively attend to parts of a scene for quick perception, a biological mechanism known as Human attention. Inspired by this, recent deep learning models encode attention mechanisms to focus on the most task-relevant parts of the input signal for further processing, which is called Machine/Neural/Artificial attention. Understanding the relation between human and machine attention is important for interpreting and designing neural networks. Many works claim that the attention mechanism offers an extra dimension of interpretability by explaining where the neural networks look. However, recent studies demonstrate that artificial attention maps do not always coincide with common intuition. In view of these conflicting evidence, here we make a systematic study on using artificial attention and human attention in neural network design. With three example computer vision tasks, diverse representative backbones, and famous architectures, corresponding real human gaze data, and systematically conducted large-scale quantitative studies, we quantify the consistency between artificial attention and human visual attention and offer novel insights into existing artificial attention mechanisms by giving preliminary answers to several key questions related to human and artificial attention mechanisms. Overall results demonstrate that human attention can benchmark the meaningful `ground-truth' in attention-driven tasks, where the more the artificial attention is close to human attention, the better the performance; for higher-level vision tasks, it is case-by-case. It would be advisable for attention-driven tasks to explicitly force a better alignment between artificial and human attention to boost the performance; such alignment would also improve the network explainability for higher-level computer vision tasks.

Yongwei Nie, Xu Cao, Chengjiang Long et al.

Current face alignment algorithms can robustly find a set of landmarks along face contour. However, the landmarks are sparse and lack curve details, especially in chin and cheek areas where a lot of concave-convex bending information exists. In this paper, we propose a local to global seam cutting and integrating algorithm (L2GSCI) to extract continuous and accurate face contour. Our method works in three steps with the help of a rough initial curve. First, we sample small and overlapped squares along the initial curve. Second, the seam cutting part of L2GSCI extracts a local seam in each square region. Finally, the seam integrating part of L2GSCI connects all the redundant seams together to form a continuous and complete face curve. Overall, the proposed method is much more straightforward than existing face alignment algorithms, but can achieve pixel-level continuous face curves rather than discrete and sparse landmarks. Moreover, experiments on two face benchmark datasets (i.e., LFPW and HELEN) show that our method can precisely reveal concave-convex bending details of face contours, which has significantly improved the performance when compared with the state-ofthe- art face alignment approaches.