Yuzhi Zhao

Yuzhi Zhao, Lai-Man Po, Xuehui Wang et al.

The appearances of children are inherited from their parents, which makes it feasible to predict them. Predicting realistic children's faces may help settle many social problems, such as age-invariant face recognition, kinship verification, and missing child identification. It can be regarded as an image-to-image translation task. Existing approaches usually assume domain information in the image-to-image translation can be interpreted by "style", i.e., the separation of image content and style. However, such separation is improper for the child face prediction, because the facial contours between children and parents are not the same. To address this issue, we propose a new disentangled learning strategy for children's face prediction. We assume that children's faces are determined by genetic factors (compact family features, e.g., face contour), external factors (facial attributes irrelevant to prediction, such as moustaches and glasses), and variety factors (individual properties for each child). On this basis, we formulate predictions as a mapping from parents' genetic factors to children's genetic factors, and disentangle them from external and variety factors. In order to obtain accurate genetic factors and perform the mapping, we propose a ChildPredictor framework. It transfers human faces to genetic factors by encoders and back by generators. Then, it learns the relationship between the genetic factors of parents and children through a mapping function. To ensure the generated faces are realistic, we collect a large Family Face Database to train ChildPredictor and evaluate it on the FF-Database validation set. Experimental results demonstrate that ChildPredictor is superior to other well-known image-to-image translation methods in predicting realistic and diverse child faces. Implementation codes can be found at https://github.com/zhaoyuzhi/ChildPredictor.

Wing-Yin Yu, Lai-Man Po, Ray C. C. Cheung et al.

Video-based human pose transfer is a video-to-video generation task that animates a plain source human image based on a series of target human poses. Considering the difficulties in transferring highly structural patterns on the garments and discontinuous poses, existing methods often generate unsatisfactory results such as distorted textures and flickering artifacts. To address these issues, we propose a novel Deformable Motion Modulation (DMM) that utilizes geometric kernel offset with adaptive weight modulation to simultaneously perform feature alignment and style transfer. Different from normal style modulation used in style transfer, the proposed modulation mechanism adaptively reconstructs smoothed frames from style codes according to the object shape through an irregular receptive field of view. To enhance the spatio-temporal consistency, we leverage bidirectional propagation to extract the hidden motion information from a warped image sequence generated by noisy poses. The proposed feature propagation significantly enhances the motion prediction ability by forward and backward propagation. Both quantitative and qualitative experimental results demonstrate superiority over the state-of-the-arts in terms of image fidelity and visual continuity. The source code is publicly available at github.com/rocketappslab/bdmm.

Yuzhi Zhao, Yongzhe Xu, Qiong Yan et al.

Night imaging with modern smartphone cameras is troublesome due to low photon count and unavoidable noise in the imaging system. Directly adjusting exposure time and ISO ratings cannot obtain sharp and noise-free images at the same time in low-light conditions. Though many methods have been proposed to enhance noisy or blurry night images, their performances on real-world night photos are still unsatisfactory due to two main reasons: 1) Limited information in a single image and 2) Domain gap between synthetic training images and real-world photos (e.g., differences in blur area and resolution). To exploit the information from successive long- and short-exposure images, we propose a learning-based pipeline to fuse them. A D2HNet framework is developed to recover a high-quality image by deblurring and enhancing a long-exposure image under the guidance of a short-exposure image. To shrink the domain gap, we leverage a two-phase DeblurNet-EnhanceNet architecture, which performs accurate blur removal on a fixed low resolution so that it is able to handle large ranges of blur in different resolution inputs. In addition, we synthesize a D2-Dataset from HD videos and experiment on it. The results on the validation set and real photos demonstrate our methods achieve better visual quality and state-of-the-art quantitative scores. The D2HNet codes and D2-Dataset can be found at https://github.com/zhaoyuzhi/D2HNet.

Yuzhi Zhao, Lai-Man Po, Kangcheng Liu et al.

In this paper, we propose a scribble-based video colorization network with temporal aggregation called SVCNet. It can colorize monochrome videos based on different user-given color scribbles. It addresses three common issues in the scribble-based video colorization area: colorization vividness, temporal consistency, and color bleeding. To improve the colorization quality and strengthen the temporal consistency, we adopt two sequential sub-networks in SVCNet for precise colorization and temporal smoothing, respectively. The first stage includes a pyramid feature encoder to incorporate color scribbles with a grayscale frame, and a semantic feature encoder to extract semantics. The second stage finetunes the output from the first stage by aggregating the information of neighboring colorized frames (as short-range connections) and the first colorized frame (as a long-range connection). To alleviate the color bleeding artifacts, we learn video colorization and segmentation simultaneously. Furthermore, we set the majority of operations on a fixed small image resolution and use a Super-resolution Module at the tail of SVCNet to recover original sizes. It allows the SVCNet to fit different image resolutions at the inference. Finally, we evaluate the proposed SVCNet on DAVIS and Videvo benchmarks. The experimental results demonstrate that SVCNet produces both higher-quality and more temporally consistent videos than other well-known video colorization approaches. The codes and models can be found at https://github.com/zhaoyuzhi/SVCNet.

Zixuan Zhu, Yitong Hu, Yong Dai et al.

LLM-based agents can solve multi-step interactive tasks by combining reasoning with environment feedback, yet each episode starts from the same fixed context and any useful strategy discovered along the way is lost once the task ends. Existing approaches either limit learning to the current task or pool all experience into a single untyped store, without distinguishing knowledge types, tracking quality through use, or balancing what the library still lacks. We introduce Unified Context Evolution (UCE), a gradient-free framework that externalizes agent experience into an evolving library of typed Evolvable Context Units (ECUs). UCE decomposes experience into four complementary types (Memory, Strategy, Workflow, and Skill), each generated from trajectories under type-specific conditions, retrieved at decision time, scored through repeated usage outcomes, and pruned when no longer valuable. A scheduling module allocates each cycle's generation budget toward the types where the library is weakest. Across two interactive benchmarks, UCE raises ALFWorld success from 75.4% to 96.3% and WebShop task score from 45.1% to 61.3%, and the accumulated library transfers to alternative actor backbones without retraining.

Mingjie Xu, Jinpeng Chen, Yuzhi Zhao et al.

Multimodal large language models (MLLMs) have enabled a wide range of advanced vision-language applications, including fine-grained object recognition and contextual understanding. When querying specific regions or objects in an image, human users naturally use "visual prompts" (VPs), such as bounding boxes, to provide reference. However, no existing benchmark systematically evaluates the ability of MLLMs to interpret such VPs. This gap leaves it unclear whether current MLLMs can effectively recognize VPs, an intuitive prompting method for humans, and use them to solve problems. To address this limitation, we introduce VP-Bench, a benchmark for assessing MLLMs' capability in VP perception and utilization. VP-Bench employs a two-stage evaluation framework: Stage 1 examines models' ability to perceive VPs in natural scenes, using 30k visualized prompts spanning eight shapes and 355 attribute combinations. Stage 2 investigates the impact of VPs on downstream tasks, measuring their effectiveness in real-world problem-solving scenarios. Using VP-Bench, we evaluate 28 MLLMs, including proprietary systems (e.g., GPT-4o) and open-source models (e.g., InternVL3 and Qwen2.5-VL), and provide a comprehensive analysis of factors that affect VP understanding, such as variations in VP attributes, question arrangement, and model scale. VP-Bench establishes a new reference framework for studying how MLLMs comprehend and resolve grounded referring questions.

Mingjie Xu, Mengyang Wu, Yuzhi Zhao et al.

Scene Graph Generation (SGG) converts visual scenes into structured graph representations, providing deeper scene understanding for complex vision tasks. However, existing SGG models often overlook essential spatial relationships and struggle with generalization in open-vocabulary contexts. To address these limitations, we propose LLaVA-SpaceSGG, a multimodal large language model (MLLM) designed for open-vocabulary SGG with enhanced spatial relation modeling. To train it, we collect the SGG instruction-tuning dataset, named SpaceSGG. This dataset is constructed by combining publicly available datasets and synthesizing data using open-source models within our data construction pipeline. It combines object locations, object relations, and depth information, resulting in three data formats: spatial SGG description, question-answering, and conversation. To enhance the transfer of MLLMs' inherent capabilities to the SGG task, we introduce a two-stage training paradigm. Experiments show that LLaVA-SpaceSGG outperforms other open-vocabulary SGG methods, boosting recall by 8.6% and mean recall by 28.4% compared to the baseline. Our codebase, dataset, and trained models are publicly accessible on GitHub at the following URL: https://github.com/Endlinc/LLaVA-SpaceSGG.

Mengyang Wu, Yuzhi Zhao, Jialun Cao et al.

Controversial contents largely inundate the Internet, infringing various cultural norms and child protection standards. Traditional Image Content Moderation (ICM) models fall short in producing precise moderation decisions for diverse standards, while recent multimodal large language models (MLLMs), when adopted to general rule-based ICM, often produce classification and explanation results that are inconsistent with human moderators. Aiming at flexible, explainable, and accurate ICM, we design a novel rule-based dataset generation pipeline, decomposing concise human-defined rules and leveraging well-designed multi-stage prompts to enrich short explicit image annotations. Our ICM-Instruct dataset includes detailed moderation explanation and moderation Q-A pairs. Built upon it, we create our ICM-Assistant model in the framework of rule-based ICM, making it readily applicable in real practice. Our ICM-Assistant model demonstrates exceptional performance and flexibility. Specifically, it significantly outperforms existing approaches on various sources, improving both the moderation classification (36.8% on average) and moderation explanation quality (26.6% on average) consistently over existing MLLMs. Code/Data is available at https://github.com/zhaoyuzhi/ICM-Assistant.

Yuzhi Zhao, Lai-Man Po, Xin Ye et al.

Image degradation caused by noise and blur remains a persistent challenge in imaging systems, stemming from limitations in both hardware and methodology. Single-image solutions face an inherent tradeoff between noise reduction and motion blur. While short exposures can capture clear motion, they suffer from noise amplification. Long exposures reduce noise but introduce blur. Learning-based single-image enhancers tend to be over-smooth due to the limited information. Multi-image solutions using burst mode avoid this tradeoff by capturing more spatial-temporal information but often struggle with misalignment from camera/scene motion. To address these limitations, we propose a physical-model-based image restoration approach leveraging a novel dual-exposure Quad-Bayer pattern sensor. By capturing pairs of short and long exposures at the same starting point but with varying durations, this method integrates complementary noise-blur information within a single image. We further introduce a Quad-Bayer synthesis method (B2QB) to simulate sensor data from Bayer patterns to facilitate training. Based on this dual-exposure sensor model, we design a hierarchical convolutional neural network called QRNet to recover high-quality RGB images. The network incorporates input enhancement blocks and multi-level feature extraction to improve restoration quality. Experiments demonstrate superior performance over state-of-the-art deblurring and denoising methods on both synthetic and real-world datasets. The code, model, and datasets are publicly available at https://github.com/zhaoyuzhi/QRNet.

Donglai Xu, Hongzheng Yang, Yuzhi Zhao et al.

Reinforcement Learning with Verifiable Rewards (RLVR) for Multimodal Large Language Models (MLLMs) is highly dependent on high-quality labeled data, which is often scarce and prone to substantial annotation noise in real-world scenarios. Existing unsupervised RLVR methods, including pure entropy minimization, can overfit to incorrect labels and limit the crucial reward ranking signal for Group-Relative Policy Optimization (GRPO). To address these challenges and enhance noise tolerance, we propose a novel two-stage, token-level entropy optimization method for RLVR. This approach dynamically guides the model from exploration to exploitation during training. In the initial exploration phase, token-level entropy maximization promotes diverse and stochastic output generation, serving as a strong regularizer that prevents premature convergence to noisy labels and ensures sufficient intra-group variation, which enables more reliable reward gradient estimation in GRPO. As training progresses, the method transitions into the exploitation phase, where token-level entropy minimization encourages the model to produce confident and deterministic outputs, thereby consolidating acquired knowledge and refining prediction accuracy. Empirically, across three MLLM backbones - Qwen2-VL-2B, Qwen2-VL-7B, and Qwen2.5-VL-3B - spanning diverse noise settings and multiple tasks, our phased strategy consistently outperforms prior approaches by unifying and enhancing external, internal, and entropy-based methods, delivering robust and superior performance across the board.

Kun Li, Lai-Man Po, Hongzheng Yang et al.

Multimodal Large Language Models (MLLMs) are increasingly applied in Personalized Image Aesthetic Assessment (PIAA) as a scalable alternative to expert evaluations. However, their predictions may reflect subtle biases influenced by demographic factors such as gender, age, and education. In this work, we propose AesBiasBench, a benchmark designed to evaluate MLLMs along two complementary dimensions: (1) stereotype bias, quantified by measuring variations in aesthetic evaluations across demographic groups; and (2) alignment between model outputs and genuine human aesthetic preferences. Our benchmark covers three subtasks (Aesthetic Perception, Assessment, Empathy) and introduces structured metrics (IFD, NRD, AAS) to assess both bias and alignment. We evaluate 19 MLLMs, including proprietary models (e.g., GPT-4o, Claude-3.5-Sonnet) and open-source models (e.g., InternVL-2.5, Qwen2.5-VL). Results indicate that smaller models exhibit stronger stereotype biases, whereas larger models align more closely with human preferences. Incorporating identity information often exacerbates bias, particularly in emotional judgments. These findings underscore the importance of identity-aware evaluation frameworks in subjective vision-language tasks.

Yujia Zhang, Lai-Man Po, Xuyuan Xu et al.

Spatio-temporal representation learning is critical for video self-supervised representation. Recent approaches mainly use contrastive learning and pretext tasks. However, these approaches learn representation by discriminating sampled instances via feature similarity in the latent space while ignoring the intermediate state of the learned representations, which limits the overall performance. In this work, taking into account the degree of similarity of sampled instances as the intermediate state, we propose a novel pretext task - spatio-temporal overlap rate (STOR) prediction. It stems from the observation that humans are capable of discriminating the overlap rates of videos in space and time. This task encourages the model to discriminate the STOR of two generated samples to learn the representations. Moreover, we employ a joint optimization combining pretext tasks with contrastive learning to further enhance the spatio-temporal representation learning. We also study the mutual influence of each component in the proposed scheme. Extensive experiments demonstrate that our proposed STOR task can favor both contrastive learning and pretext tasks. The joint optimization scheme can significantly improve the spatio-temporal representation in video understanding. The code is available at https://github.com/Katou2/CSTP.

Wing-Yin Yu, Lai-Man Po, Yuzhi Zhao et al.

Due to unreliable geometric matching and content misalignment, most conventional pose transfer algorithms fail to generate fine-trained person images. In this paper, we propose a novel framework Spatial Content Alignment GAN (SCAGAN) which aims to enhance the content consistency of garment textures and the details of human characteristics. We first alleviate the spatial misalignment by transferring the edge content to the target pose in advance. Secondly, we introduce a new Content-Style DeBlk which can progressively synthesize photo-realistic person images based on the appearance features of the source image, the target pose heatmap and the prior transferred content in edge domain. We compare the proposed framework with several state-of-the-art methods to show its superiority in quantitative and qualitative analysis. Moreover, detailed ablation study results demonstrate the efficacy of our contributions. Codes are publicly available at github.com/rocketappslab/SCA-GAN.

Xuehui Wang, Qing Wang, Yuzhi Zhao et al.

Despite convolutional network-based methods have boosted the performance of single image super-resolution (SISR), the huge computation costs restrict their practical applicability. In this paper, we develop a computation efficient yet accurate network based on the proposed attentive auxiliary features (A$^2$F) for SISR. Firstly, to explore the features from the bottom layers, the auxiliary feature from all the previous layers are projected into a common space. Then, to better utilize these projected auxiliary features and filter the redundant information, the channel attention is employed to select the most important common feature based on current layer feature. We incorporate these two modules into a block and implement it with a lightweight network. Experimental results on large-scale dataset demonstrate the effectiveness of the proposed model against the state-of-the-art (SOTA) SR methods. Notably, when parameters are less than 320k, A$^2$F outperforms SOTA methods for all scales, which proves its ability to better utilize the auxiliary features. Codes are available at https://github.com/wxxxxxxh/A2F-SR.

Yuzhi Zhao, Lai-Man Po, Qiong Yan et al.

Capturing visual image with a hyperspectral camera has been successfully applied to many areas due to its narrow-band imaging technology. Hyperspectral reconstruction from RGB images denotes a reverse process of hyperspectral imaging by discovering an inverse response function. Current works mainly map RGB images directly to corresponding spectrum but do not consider context information explicitly. Moreover, the use of encoder-decoder pair in current algorithms leads to loss of information. To address these problems, we propose a 4-level Hierarchical Regression Network (HRNet) with PixelShuffle layer as inter-level interaction. Furthermore, we adopt a residual dense block to remove artifacts of real world RGB images and a residual global block to build attention mechanism for enlarging perceptive field. We evaluate proposed HRNet with other architectures and techniques by participating in NTIRE 2020 Challenge on Spectral Reconstruction from RGB Images. The HRNet is the winning method of track 2 - real world images and ranks 3rd on track 1 - clean images. Please visit the project web page https://github.com/zhaoyuzhi/Hierarchical-Regression-Network-for-Spectral-Reconstruction-from-RGB-Images to try our codes and pre-trained models.

Mingjie Xu, Andrew Estornell, Hongzheng Yang et al.

The application of visual instruction tuning and other post-training techniques has significantly enhanced the capabilities of Large Language Models (LLMs) in visual understanding, enriching Vision-Language Models (VLMs) with more comprehensive visual language datasets. However, the effectiveness of VLMs is highly dependent on large-scale, high-quality datasets that ensure precise recognition and accurate reasoning. Two key challenges hinder progress: (1) noisy alignments between images and the corresponding text, which leads to misinterpretation, and (2) ambiguous or misleading text, which obscures visual content. To address these challenges, we propose SCALE (Single modality data quality and Cross modality Alignment Evaluation), a novel quality-driven data selection pipeline for VLM instruction tuning datasets. Specifically, SCALE integrates a cross-modality assessment framework that first assigns each data entry to its appropriate vision-language task, generates general and task-specific captions (covering scenes, objects, style, etc.), and evaluates the alignment, clarity, task rarity, text coherence, and image clarity of each entry based on the generated captions. We reveal that: (1) current unimodal quality assessment methods evaluate one modality while overlooking the rest, which can underestimate samples essential for specific tasks and discard the lower-quality instances that help build model robustness; and (2) appropriately generated image captions provide an efficient way to transfer the image-text multimodal task into a unified text modality.

Ziyi Guan, Jason Chun Lok Li, Zhijian Hou et al.

Despite recent progress, Graphic User Interface (GUI) agents powered by Large Language Models (LLMs) struggle with complex mobile tasks due to limited app-specific knowledge. While UI Transition Graphs (UTGs) offer structured navigation representations, they are underutilized due to poor extraction and inefficient integration. We introduce KG-RAG, a Knowledge Graph-driven Retrieval-Augmented Generation framework that transforms fragmented UTGs into structured vector databases for efficient real-time retrieval. By leveraging an intent-guided LLM search method, KG-RAG generates actionable navigation paths, enhancing agent decision-making. Experiments across diverse mobile apps show that KG-RAG outperforms existing methods, achieving a 75.8% success rate (8.9% improvement over AutoDroid), 84.6% decision accuracy (8.1% improvement), and reducing average task steps from 4.5 to 4.1. Additionally, we present KG-Android-Bench and KG-Harmony-Bench, two benchmarks tailored to the Chinese mobile ecosystem for future research. Finally, KG-RAG transfers to web/desktop (+40% SR on Weibo-web; +20% on QQ Music-desktop), and a UTG cost ablation shows accuracy saturates at ~4h per complex app, enabling practical deployment trade-offs.

Yuzhi Zhao, Lai-Man Po, Wing-Yin Yu et al.

We propose a hybrid recurrent Video Colorization with Hybrid Generative Adversarial Network (VCGAN), an improved approach to video colorization using end-to-end learning. The VCGAN addresses two prevalent issues in the video colorization domain: Temporal consistency and unification of colorization network and refinement network into a single architecture. To enhance colorization quality and spatiotemporal consistency, the mainstream of generator in VCGAN is assisted by two additional networks, i.e., global feature extractor and placeholder feature extractor, respectively. The global feature extractor encodes the global semantics of grayscale input to enhance colorization quality, whereas the placeholder feature extractor acts as a feedback connection to encode the semantics of the previous colorized frame in order to maintain spatiotemporal consistency. If changing the input for placeholder feature extractor as grayscale input, the hybrid VCGAN also has the potential to perform image colorization. To improve the consistency of far frames, we propose a dense long-term loss that smooths the temporal disparity of every two remote frames. Trained with colorization and temporal losses jointly, VCGAN strikes a good balance between color vividness and video continuity. Experimental results demonstrate that VCGAN produces higher-quality and temporally more consistent colorful videos than existing approaches.

Yuzhi Zhao, Lai-Man Po, Kwok-Wai Cheung et al.

Given a grayscale photograph, the colorization system estimates a visually plausible colorful image. Conventional methods often use semantics to colorize grayscale images. However, in these methods, only classification semantic information is embedded, resulting in semantic confusion and color bleeding in the final colorized image. To address these issues, we propose a fully automatic Saliency Map-guided Colorization with Generative Adversarial Network (SCGAN) framework. It jointly predicts the colorization and saliency map to minimize semantic confusion and color bleeding in the colorized image. Since the global features from pre-trained VGG-16-Gray network are embedded to the colorization encoder, the proposed SCGAN can be trained with much less data than state-of-the-art methods to achieve perceptually reasonable colorization. In addition, we propose a novel saliency map-based guidance method. Branches of the colorization decoder are used to predict the saliency map as a proxy target. Moreover, two hierarchical discriminators are utilized for the generated colorization and saliency map, respectively, in order to strengthen visual perception performance. The proposed system is evaluated on ImageNet validation set. Experimental results show that SCGAN can generate more reasonable colorized images than state-of-the-art techniques.

Kai Zhang, Martin Danelljan, Yawei Li et al.

This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor x4 based on a set of prior examples of low and corresponding high resolution images. The goal is to devise a network that reduces one or several aspects such as runtime, parameter count, FLOPs, activations, and memory consumption while at least maintaining PSNR of MSRResNet. The track had 150 registered participants, and 25 teams submitted the final results. They gauge the state-of-the-art in efficient single image super-resolution.

Abdelrahman Abdelhamed, Mahmoud Afifi, Radu Timofte et al.

This paper reviews the NTIRE 2020 challenge on real image denoising with focus on the newly introduced dataset, the proposed methods and their results. The challenge is a new version of the previous NTIRE 2019 challenge on real image denoising that was based on the SIDD benchmark. This challenge is based on a newly collected validation and testing image datasets, and hence, named SIDD+. This challenge has two tracks for quantitatively evaluating image denoising performance in (1) the Bayer-pattern rawRGB and (2) the standard RGB (sRGB) color spaces. Each track ~250 registered participants. A total of 22 teams, proposing 24 methods, competed in the final phase of the challenge. The proposed methods by the participating teams represent the current state-of-the-art performance in image denoising targeting real noisy images. The newly collected SIDD+ datasets are publicly available at: https://bit.ly/siddplus_data.