Image Aesthetic Assessment (IAA) is a vital and intricate task that entails analyzing and assessing an image's aesthetic values, and identifying its highlights and areas for improvement. Traditional methods of IAA often concentrate on a single aesthetic task and suffer from inadequate labeled datasets, thus impairing in-depth aesthetic comprehension. Despite efforts to overcome this challenge through the application of Multi-modal Large Language Models (MLLMs), such models remain underdeveloped for IAA purposes. To address this, we propose a comprehensive aesthetic MLLM capable of nuanced aesthetic insight. Central to our approach is an innovative multi-scale text-guided self-supervised learning technique. This technique features a multi-scale feature alignment module and capitalizes on a wealth of unlabeled data in a self-supervised manner to structurally and functionally enhance aesthetic ability. The empirical evidence indicates that accompanied with extensive instruct-tuning, our model sets new state-of-the-art benchmarks across multiple tasks, including aesthetic scoring, aesthetic commenting, and personalized image aesthetic assessment. Remarkably, it also demonstrates zero-shot learning capabilities in the emerging task of aesthetic suggesting. Furthermore, for personalized image aesthetic assessment, we harness the potential of in-context learning and showcase its inherent advantages.

Multi-Domain Face Anti-Spoofing (MD-FAS) is a practical setting that aims to update models on new domains using only novel data while ensuring that the knowledge acquired from previous domains is not forgotten. Prior methods utilize the responses from models to represent the previous domain knowledge or map the different domains into separated feature spaces to prevent forgetting. However, due to domain gaps, the responses of new data are not as accurate as those of previous data. Also, without the supervision of previous data, separated feature spaces might be destroyed by new domains while updating, leading to catastrophic forgetting. Inspired by the challenges posed by the lack of previous data, we solve this issue from a new standpoint that generates hallucinated previous data for updating FAS model. To this end, we propose a novel Domain-Hallucinated Updating (DHU) framework to facilitate the hallucination of data. Specifically, Domain Information Explorer learns representative domain information of the previous domains. Then, Domain Information Hallucination module transfers the new domain data to pseudo-previous domain ones. Moreover, Hallucinated Features Joint Learning module is proposed to asymmetrically align the new and pseudo-previous data for real samples via dual levels to learn more generalized features, promoting the results on all domains. Our experimental results and visualizations demonstrate that the proposed method outperforms state-of-the-art competitors in terms of effectiveness.

The generalizable face anti-spoofing (FAS) has attracted much attention recently. Even though many existing methods perform well under intra-domain settings, the model’s performance in the unseen domain is not satisfying. In this paper, we shift our attention to the frequency domain to seek a solution. Specifically, we examine the characteristics of different frequency band components of FAS images and observe that the model’s cross-domain performance is very sensitive to low-frequency features. To alleviate this sensitivity and improve the model’s performance in FAS cross-domain tasks, we propose a new approach called Masked Frequency Autoencoders (MFAE). MFAE randomly masks a portion of frequencies on the low-frequency spectrum of the image and then reconstructs the image from the resulting embedding. This innovative Masked Image Modeling (MIM) strategy can be used as a self-supervised task for pre-training vision transformers (ViTs), which can reduce the ViT encoder’s sensitivity to domain shifts. Additionally, we add an auxiliary content-regularization decoder in our MFAE to encourage the encoder to be insensitive to low-frequency features. The results show that the model insensitive to low-frequency features performs well on extensive public datasets and outperforms other state-of-the-art methods in cross-domain FAS tasks.

Although existing face anti-spoofing (FAS) methods achieve high accuracy in intra-domain experiments, their effects drop severely in cross-domain scenarios because of poor generalization. Recently, multifarious techniques have been explored, such as domain generalization and representation disentanglement. However, the improvement is still limited by two issues: 1) It is difficult to perfectly map all faces to a shared feature space. If faces from unknown domains are not mapped to the known region in the shared feature space, accidentally inaccurate predictions will be obtained. 2) It is hard to completely consider various spoof traces for disentanglement. In this paper, we propose a Feature Generation and Hypothesis Verification framework to alleviate the two issues. Above all, feature generation networks which generate hypotheses of real faces and known attacks are introduced for the first time in the FAS task. Subsequently, two hypothesis verification modules are applied to judge whether the input face comes from the real-face space and the real-face distribution respectively. Furthermore, some analyses of the relationship between our framework and Bayesian uncertainty estimation are given, which provides theoretical support for reliable defense in unknown domains. Experimental results show our framework achieves promising results and outperforms the state-of-the-art approaches on extensive public datasets.

In pursuit of consolidating the face verification systems, prior face anti-spoofing studies excavate the hidden cues in original images to discriminate real person and diverse attack types with the assistance of auxiliary supervision. However, limited by the following two inherent disturbances in their training process: 1) Complete facial structure in a single image. 2) Implicit subdomains in the whole dataset, these methods are prone to stick on memorization of the entire training dataset and show sensitivity to non-homologous domain distribution. In this paper, we propose Structure Destruction Module and Content Combination Module to address these two limitations separately. The former mechanism destroys images into patches to construct a non-structural input, while the latter mechanism recombines patches from different subdomains or classes into a mixup construct. Based on this splitting-and-splicing operation, Local Relation Modeling Module is further proposed to model the second-order relationship between patches. We evaluate our method on extensive public datasets and promising experimental results to demonstrate the reliability of our method against the state-of-the-art competitors.

Unsupervised video prediction is a very challenging task due to the complexity and diversity in natural scenes. Prior works directly predicting pixels or optical flows either have the blurring problem or require additional assumptions. We highlight that the crux for video frame prediction lies in precisely capturing the inter-frame variations which encompass the movement of objects and the evolution of the surrounding environment. We then present an unsupervised video prediction framework - Variation Network (VarNet) to directly predict the variations between adjacent frames which are then fused with current frame to generate the future frame. In addition, we propose an adaptively re-weighting mechanism for loss function to offer each pixel a fair weight according to the amplitude of its variation. Extensive experiments for both short-term and long-term video prediction are implemented on two advanced datasets - KTH and KITTI with two evaluating metrics - PSNR and SSIM. For the KTH dataset, the VarNet outperforms the state-of-the-art works up to 11.9% on PSNR and 9.5% on SSIM. As for the KITTI dataset, the performance boosts are up to 55.1% on PSNR and 15.9% on SSIM. Moreover, we verify that the generalization ability of our model excels other state-of-the-art methods by testing on the unseen CalTech Pedestrian dataset after being trained on the KITTI dataset. Source code and video are available at https://github.com/jinbeibei/VarNet.

Semantic scene completion predicts volumetric occupancy and object category of a 3D scene, which helps intelligent agents to understand and interact with the surroundings. In this work, we propose a disentangled framework, sequentially carrying out 2D semantic segmentation, 2D-3D reprojection and 3D semantic scene completion. This three-stage framework has three advantages: (1) explicit semantic segmentation significantly boosts performance; (2) flexible fusion ways of sensor data bring good extensibility; (3) progress in any subtask will promote the holistic performance. Experimental results show that regardless of inputing a single depth or RGB-D, our framework can generate high-quality semantic scene completion, and outperforms state-of-the-art approaches on both synthetic and real datasets.

Depth estimation from a single image is very challenging due to the inherent ambiguity of mapping a color image to a depth map. Previous work tackles this problem by exploiting various levels of features with multi-scale deep convolutional neural networks. However, most of the local geometric structure related monocular depth cues are lost when being propagated through convolutional neural network. Moreover, the error of depth cues related to local geometric structures is not considered in the loss function. In this work, we propose the GeoCueDepth convolutional neural network to exploit local geometric structure cues and propose a training loss that takes the geometric error into consideration, which significantly improve the performance of depth prediction in both accuracy and sharpness. Experiments show that the proposed method achieves 0.122 average relative error and 0.078 square relative error on the NYU Depth v2 data set, which outperforms state-of-the-art monocular depth estimation approaches.