Wen-Huang Cheng

Junchen Zhu, Huan Yang, Huiguo He et al. · microsoft-research

In this paper, we present MovieFactory, a powerful framework to generate cinematic-picture (3072$\times$1280), film-style (multi-scene), and multi-modality (sounding) movies on the demand of natural languages. As the first fully automated movie generation model to the best of our knowledge, our approach empowers users to create captivating movies with smooth transitions using simple text inputs, surpassing existing methods that produce soundless videos limited to a single scene of modest quality. To facilitate this distinctive functionality, we leverage ChatGPT to expand user-provided text into detailed sequential scripts for movie generation. Then we bring scripts to life visually and acoustically through vision generation and audio retrieval. To generate videos, we extend the capabilities of a pretrained text-to-image diffusion model through a two-stage process. Firstly, we employ spatial finetuning to bridge the gap between the pretrained image model and the new video dataset. Subsequently, we introduce temporal learning to capture object motion. In terms of audio, we leverage sophisticated retrieval models to select and align audio elements that correspond to the plot and visual content of the movie. Extensive experiments demonstrate that our MovieFactory produces movies with realistic visuals, diverse scenes, and seamlessly fitting audio, offering users a novel and immersive experience. Generated samples can be found in YouTube or Bilibili (1080P).

Junchen Zhu, Huan Yang, Wenjing Wang et al. · microsoft-research

Videos for mobile devices become the most popular access to share and acquire information recently. For the convenience of users' creation, in this paper, we present a system, namely MobileVidFactory, to automatically generate vertical mobile videos where users only need to give simple texts mainly. Our system consists of two parts: basic and customized generation. In the basic generation, we take advantage of the pretrained image diffusion model, and adapt it to a high-quality open-domain vertical video generator for mobile devices. As for the audio, by retrieving from our big database, our system matches a suitable background sound for the video. Additionally to produce customized content, our system allows users to add specified screen texts to the video for enriching visual expression, and specify texts for automatic reading with optional voices as they like.

Andrey Ignatov, Radu Timofte, Cheng-Ming Chiang et al.

Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS training dataset containing video sequences for a 4X video upscaling task. The runtime and power efficiency of all models was evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit capable of accelerating floating-point and quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt / 30 FPS] power consumption. A detailed description of all models developed in the challenge is provided in this paper.

Ruoxuan Zhang, Qiaoqiao Wan, Zhengguang Wang et al.

Theory of Mind (ToM) enables an agent to reason about another actor's beliefs, goals, and intentions, which is essential for human-centered embodied assistance. Existing ToM benchmarks have advanced text and multimodal mental-state recognition, but they mostly evaluate offline question answering or final action prediction. They do not fully test whether an embodied agent can stay connected to a changing environment, update actor-specific beliefs, decide when reasoning is needed, and intervene only when help is useful. Building on MindPower, we extend robot-centric ToM reasoning to a real-time closed-loop setting and introduce MindClaw, a framework for embodied mental-state reasoning with precision intervention. MindClaw connects multi-source inputs, belief memory, an embodied cognitive trigger skill, mental reasoning, and action generation, allowing the agent to output helpful actions at the right time while remaining silent when intervention is unnecessary. Experiments show that direct VLM baselines struggle with task awareness and intervention calibration, while MindClaw achieves the best overall performance, demonstrating the importance of trigger-skill optimization for closed-loop embodied ToM assistance.

Bo-Kai Ruan, Hong-Han Shuai, Wen-Huang Cheng

Transformers have achieved great success in natural language processing. Due to the powerful capability of self-attention mechanism in transformers, researchers develop the vision transformers for a variety of computer vision tasks, such as image recognition, object detection, image segmentation, pose estimation, and 3D reconstruction. This paper presents a comprehensive overview of the literature on different architecture designs and training tricks (including self-supervised learning) for vision transformers. Our goal is to provide a systematic review with the open research opportunities.

Hongxia Xie, Ming-Xian Lee, Tzu-Jui Chen et al.

Group affect refers to the subjective emotion that is evoked by an external stimulus in a group, which is an important factor that shapes group behavior and outcomes. Recognizing group affect involves identifying important individuals and salient objects among a crowd that can evoke emotions. However, most existing methods lack attention to affective meaning in group dynamics and fail to account for the contextual relevance of faces and objects in group-level images. In this work, we propose a solution by incorporating the psychological concept of the Most Important Person (MIP), which represents the most noteworthy face in a crowd and has affective semantic meaning. We present the Dual-branch Cross-Patch Attention Transformer (DCAT) which uses global image and MIP together as inputs. Specifically, we first learn the informative facial regions produced by the MIP and the global context separately. Then, the Cross-Patch Attention module is proposed to fuse the features of MIP and global context together to complement each other. Our proposed method outperforms state-of-the-art methods on GAF 3.0, GroupEmoW, and HECO datasets. Moreover, we demonstrate the potential for broader applications by showing that our proposed model can be transferred to another group affect task, group cohesion, and achieve comparable results.

Jian-Yu Jiang-Lin, Kang-Yang Huang, Ling Lo et al.

Diffusion models revolutionize image generation by leveraging natural language to guide the creation of multimedia content. Despite significant advancements in such generative models, challenges persist in depicting detailed human-object interactions, especially regarding pose and object placement accuracy. We introduce a training-free method named Reasoning and Correcting Diffusion (ReCorD) to address these challenges. Our model couples Latent Diffusion Models with Visual Language Models to refine the generation process, ensuring precise depictions of HOIs. We propose an interaction-aware reasoning module to improve the interpretation of the interaction, along with an interaction correcting module to refine the output image for more precise HOI generation delicately. Through a meticulous process of pose selection and object positioning, ReCorD achieves superior fidelity in generated images while efficiently reducing computational requirements. We conduct comprehensive experiments on three benchmarks to demonstrate the significant progress in solving text-to-image generation tasks, showcasing ReCorD's ability to render complex interactions accurately by outperforming existing methods in HOI classification score, as well as FID and Verb CLIP-Score. Project website is available at https://alberthkyhky.github.io/ReCorD/ .

Sandy Ardianto, Hsueh-Ming Hang, Wen-Huang Cheng

We design a fast car detection and tracking algorithm for traffic monitoring fisheye video mounted on crossroads. We use ICIP 2020 VIP Cup dataset and adopt YOLOv5 as the object detection base model. The nighttime video of this dataset is very challenging, and the detection accuracy (AP50) of the base model is about 54%. We design a reliable car detection and tracking algorithm based on the concept of bounding box propagation among frames, which provides 17.9 percentage points (pp) and 6.2 pp. accuracy improvement over the base model for the nighttime and daytime videos, respectively. To speed up, the grayscale frame difference is used for the intermediate frames in a segment, which can double the processing speed.

Yi Yao, Chan-Feng Hsu, Jhe-Hao Lin et al.

In spite of recent advancements in text-to-image generation, limitations persist in handling complex and imaginative prompts due to the restricted diversity and complexity of training data. This work explores how diffusion models can generate images from prompts requiring artistic creativity or specialized knowledge. We introduce the Realistic-Fantasy Benchmark (RFBench), a novel evaluation framework blending realistic and fantastical scenarios. To address these challenges, we propose the Realistic-Fantasy Network (RFNet), a training-free approach integrating diffusion models with LLMs. Extensive human evaluations and GPT-based compositional assessments demonstrate our approach's superiority over state-of-the-art methods. Our code and dataset is available at https://leo81005.github.io/Reality-and-Fantasy/.

Jeong Hun Yeo, Chae Won Kim, Hyunjun Kim et al.

Lip reading aims to predict spoken language by analyzing lip movements. Despite advancements in lip reading technologies, performance degrades when models are applied to unseen speakers due to their sensitivity to variations in visual information such as lip appearances. To address this challenge, speaker adaptive lip reading technologies have advanced by focusing on effectively adapting a lip reading model to target speakers in the visual modality. However, the effectiveness of adapting language information, such as vocabulary choice, of the target speaker has not been explored in previous works. Additionally, existing datasets for speaker adaptation have limited vocabulary sizes and pose variations, which restrict the validation of previous speaker-adaptive methods in real-world scenarios. To address these issues, we propose a novel speaker-adaptive lip reading method that adapts a pre-trained model to target speakers at both vision and language levels. Specifically, we integrate prompt tuning and the LoRA approach, applying them to a pre-trained lip reading model to effectively adapt the model to target speakers. Furthermore, to validate its effectiveness in real-world scenarios, we introduce a new dataset, VoxLRS-SA, derived from VoxCeleb2 and LRS3. It contains a vocabulary of approximately 100K words, offers diverse pose variations, and enables the validation of adaptation methods in the wild, sentence-level lip reading for the first time in English. Through various experiments, we demonstrate that the existing speaker-adaptive method also improves performance in the wild at the sentence level. Moreover, we show that the proposed method achieves larger improvements compared to the previous works.

Sheng-Hao Liao, Shang-Fu Chen, Tai-Ming Huang et al.

Drag-based image editing using generative models provides intuitive control over image structures. However, existing methods rely heavily on manually provided masks and textual prompts to preserve semantic fidelity and motion precision. Removing these constraints creates a fundamental trade-off: visual artifacts without masks and poor spatial control without prompts. To address these limitations, we propose DirectDrag, a novel mask- and prompt-free editing framework. DirectDrag enables precise and efficient manipulation with minimal user input while maintaining high image fidelity and accurate point alignment. DirectDrag introduces two key innovations. First, we design an Auto Soft Mask Generation module that intelligently infers editable regions from point displacement, automatically localizing deformation along movement paths while preserving contextual integrity through the generative model's inherent capacity. Second, we develop a Readout-Guided Feature Alignment mechanism that leverages intermediate diffusion activations to maintain structural consistency during point-based edits, substantially improving visual fidelity. Despite operating without manual mask or prompt, DirectDrag achieves superior image quality compared to existing methods while maintaining competitive drag accuracy. Extensive experiments on DragBench and real-world scenarios demonstrate the effectiveness and practicality of DirectDrag for high-quality, interactive image manipulation. Project Page: https://frakw.github.io/DirectDrag/. Code is available at: https://github.com/frakw/DirectDrag.

Ruoxuan Zhang, Bin Wen, Hongxia Xie et al.

Cooking is a sequential and visually grounded activity, where each step such as chopping, mixing, or frying carries both procedural logic and visual semantics. While recent diffusion models have shown strong capabilities in text-to-image generation, they struggle to handle structured multi-step scenarios like recipe illustration. Additionally, current recipe illustration methods are unable to adjust to the natural variability in recipe length, generating a fixed number of images regardless of the actual instructions structure. To address these limitations, we present CookAnything, a flexible and consistent diffusion-based framework that generates coherent, semantically distinct image sequences from textual cooking instructions of arbitrary length. The framework introduces three key components: (1) Step-wise Regional Control (SRC), which aligns textual steps with corresponding image regions within a single denoising process; (2) Flexible RoPE, a step-aware positional encoding mechanism that enhances both temporal coherence and spatial diversity; and (3) Cross-Step Consistency Control (CSCC), which maintains fine-grained ingredient consistency across steps. Experimental results on recipe illustration benchmarks show that CookAnything performs better than existing methods in training-based and training-free settings. The proposed framework supports scalable, high-quality visual synthesis of complex multi-step instructions and holds significant potential for broad applications in instructional media, and procedural content creation.

Yi-Xin Huang, Hou-I Liu, Hong-Han Shuai et al.

Despite previous DETR-like methods having performed successfully in generic object detection, tiny object detection is still a challenging task for them since the positional information of object queries is not customized for detecting tiny objects, whose scale is extraordinarily smaller than general objects. Also, DETR-like methods using a fixed number of queries make them unsuitable for aerial datasets, which only contain tiny objects, and the numbers of instances are imbalanced between different images. Thus, we present a simple yet effective model, named DQ-DETR, which consists of three different components: categorical counting module, counting-guided feature enhancement, and dynamic query selection to solve the above-mentioned problems. DQ-DETR uses the prediction and density maps from the categorical counting module to dynamically adjust the number of object queries and improve the positional information of queries. Our model DQ-DETR outperforms previous CNN-based and DETR-like methods, achieving state-of-the-art mAP 30.2% on the AI-TOD-V2 dataset, which mostly consists of tiny objects. Our code will be available at https://github.com/hoiliu-0801/DQ-DETR.

Hongxia Xie, Chu-Jun Peng, Yu-Wen Tseng et al.

Visual Instruction Tuning represents a novel learning paradigm involving the fine-tuning of pre-trained language models using task-specific instructions. This paradigm shows promising zero-shot results in various natural language processing tasks but is still unexplored in vision emotion understanding. In this work, we focus on enhancing the model's proficiency in understanding and adhering to instructions related to emotional contexts. Initially, we identify key visual clues critical to visual emotion recognition. Subsequently, we introduce a novel GPT-assisted pipeline for generating emotion visual instruction data, effectively addressing the scarcity of annotated instruction data in this domain. Expanding on the groundwork established by InstructBLIP, our proposed EmoVIT architecture incorporates emotion-specific instruction data, leveraging the powerful capabilities of Large Language Models to enhance performance. Through extensive experiments, our model showcases its proficiency in emotion classification, adeptness in affective reasoning, and competence in comprehending humor. The comparative analysis provides a robust benchmark for Emotion Visual Instruction Tuning in the era of LLMs, providing valuable insights and opening avenues for future exploration in this domain. Our code is available at \url{https://github.com/aimmemotion/EmoVIT}.

Si-Yu Lu, Po-Ting Chen, Hui-Che Hsu et al.

Reconstructing 3D geometry from streaming video requires continuous inference under bounded resources. Recent geometric foundation models achieve impressive reconstruction quality through all-to-all attention, yet their quadratic cost confines them to short, offline sequences. Causal-attention variants such as StreamVGGT enable single-pass streaming but accumulate an ever-growing KV cache, exhausting GPU memory within hundreds of frames and precluding the long-horizon deployment that motivates streaming inference in the first place. We present OVGGT, a training-free framework that bounds both memory and compute to a fixed budget regardless of sequence length. Our approach combines Self-Selective Caching, which leverages FFN residual magnitudes to compress the KV cache while remaining fully compatible with FlashAttention, with Dynamic Anchor Protection, which shields coordinate-critical tokens from eviction to suppress geometric drift over extended trajectories. Extensive experiments on indoor, outdoor, and ultra-long sequence benchmarks demonstrate that OVGGT processes arbitrarily long videos within a constant VRAM envelope while achieving state-of-the-art 3D geometric accuracy.

Hou-I Liu, Christine Wu, Jen-Hao Cheng et al.

Monocular 3D object detection (Mono3D) holds noteworthy promise for autonomous driving applications owing to the cost-effectiveness and rich visual context of monocular camera sensors. However, depth ambiguity poses a significant challenge, as it requires extracting precise 3D scene geometry from a single image, resulting in suboptimal performance when transferring knowledge from a LiDAR-based teacher model to a camera-based student model. To facilitate effective distillation, we introduce Monocular Teaching Assistant Knowledge Distillation (MonoTAKD), which proposes a camera-based teaching assistant (TA) model to transfer robust 3D visual knowledge to the student model, leveraging the smaller feature representation gap. Additionally, we define 3D spatial cues as residual features that capture the differences between the teacher and the TA models. We then leverage these cues to improve the student model's 3D perception capabilities. Experimental results show that our MonoTAKD achieves state-of-the-art performance on the KITTI3D dataset. Furthermore, we evaluate the performance on nuScenes and KITTI raw datasets to demonstrate the generalization of our model to multi-view 3D and unsupervised data settings. Our code is available at https://github.com/hoiliu-0801/MonoTAKD.

Cheng Zhang, Yuer Liu, Zhiyu Zhou et al.

Multimodal large language models (MLLMs) can produce fluent artwork emotion explanations, but they often suffer from attribute flooding: they enumerate many visible formal attributes without identifying which cues actually support the affective judgment. We therefore formulate artwork emotion understanding as Attribute-Grounded Selective Reasoning (AGSR), where predefined formal attributes serve as evidence units and only emotionally operative attributes should enter the final interpretation. To make this problem measurable, we extend EmoArt, originally introduced at ACM MM 2025 as a 132,664-artwork resource with content, formal-attribute, valence-arousal, and emotion annotations, by adding a 1,400-artwork human salience extension annotated by 15 art-trained annotators. This extension provides instance-level supervision for distinguishing attributes that are merely present from those that are emotionally salient. We further propose FAB-G (Formal-Attribute Bottleneck-Guided reasoning), a supervised multi-agent framework that first predicts attribute-level salience and then constrains downstream emotional analysis to the retained cues. Experiments show that FAB-G yields consistent gains in emotion, arousal, and valence prediction, achieves stronger agreement with human-marked salient attributes under Dice and Tversky metrics, and produces substantially more compact final explanations than prompting-based baselines. Cross-dataset evaluation further suggests that attribute-grounded salience selection transfers beyond the source distribution of EmoArt, while also revealing attribute-specific boundary cases. The dataset and project page are available at https://zhiliangzhang.github.io/EmoArt-130k/

Jhe-Hao Lin, Yi Yao, Chan-Feng Hsu et al.

Knowledge distillation (KD) involves transferring knowledge from a pre-trained heavy teacher model to a lighter student model, thereby reducing the inference cost while maintaining comparable effectiveness. Prior KD techniques typically assume homogeneity between the teacher and student models. However, as technology advances, a wide variety of architectures have emerged, ranging from initial Convolutional Neural Networks (CNNs) to Vision Transformers (ViTs), and Multi-Level Perceptrons (MLPs). Consequently, developing a universal KD framework compatible with any architecture has become an important research topic. In this paper, we introduce a perspective-aware teaching (PAT) KD framework to enable feature distillation across diverse architectures. Our framework comprises two key components. First, we design prompt tuning blocks that incorporate student feedback, allowing teacher features to adapt to the student model's learning process. Second, we propose region-aware attention to mitigate the view mismatch problem between heterogeneous architectures. By leveraging these two modules, effective distillation of intermediate features can be achieved across heterogeneous architectures. Extensive experiments on CIFAR, ImageNet, and COCO demonstrate the superiority of the proposed method. Our code is available at https://github.com/jimmylin0979/PAT.git.

Hou-I Liu, Marco Galindo, Hongxia Xie et al.

Over the past decade, the dominance of deep learning has prevailed across various domains of artificial intelligence, including natural language processing, computer vision, and biomedical signal processing. While there have been remarkable improvements in model accuracy, deploying these models on lightweight devices, such as mobile phones and microcontrollers, is constrained by limited resources. In this survey, we provide comprehensive design guidance tailored for these devices, detailing the meticulous design of lightweight models, compression methods, and hardware acceleration strategies. The principal goal of this work is to explore methods and concepts for getting around hardware constraints without compromising the model's accuracy. Additionally, we explore two notable paths for lightweight deep learning in the future: deployment techniques for TinyML and Large Language Models. Although these paths undoubtedly have potential, they also present significant challenges, encouraging research into unexplored areas.

Ling Lo, Kelvin C. K. Chan, Wen-Huang Cheng et al.

Existing models often struggle with complex temporal changes, particularly when generating videos with gradual attribute transitions. The most common prompt interpolation approach for motion transitions often fails to handle gradual attribute transitions, where inconsistencies tend to become more pronounced. In this work, we propose a simple yet effective method to extend existing models for smooth and consistent attribute transitions, through introducing frame-wise guidance during the denoising process. Our approach constructs a data-specific transitional direction for each noisy latent, guiding the gradual shift from initial to final attributes frame by frame while preserving the motion dynamics of the video. Moreover, we present the Controlled-Attribute-Transition Benchmark (CAT-Bench), which integrates both attribute and motion dynamics, to comprehensively evaluate the performance of different models. We further propose two metrics to assess the accuracy and smoothness of attribute transitions. Experimental results demonstrate that our approach performs favorably against existing baselines, achieving visual fidelity, maintaining alignment with text prompts, and delivering seamless attribute transitions. Code and CATBench are released: https://github.com/lynn-ling-lo/Prompt2Progression.

Tzuhsuan Huang, Cheng Yu Yeo, Tsai-Ling Huang et al.

Recent studies on deep watermarking have predominantly focused on in-processing watermarking, which integrates the watermarking process into image generation. However, post-processing watermarking, which embeds watermarks after image generation, offers more flexibility. It can be applied to outputs from any generative model (e.g. GANs, diffusion models) without needing access to the model's internal structure. It also allows users to embed unique watermarks into individual images. Therefore, this study focuses on post-processing watermarking and enhances its robustness by incorporating an ensemble attack network during training. We construct various versions of attack networks using CNN and Transformer in both spatial and frequency domains to investigate how each combination influences the robustness of the watermarking model. Our results demonstrate that combining a CNN-based attack network in the spatial domain with a Transformer-based attack network in the frequency domain yields the highest robustness in watermarking models. Extensive evaluation on the WAVES benchmark, using average bit accuracy as the metric, demonstrates that our ensemble attack network significantly enhances the robustness of baseline watermarking methods under various stress tests. In particular, for the Regeneration Attack defined in WAVES, our method improves StegaStamp by 18.743%. The code is released at:https://github.com/aiiu-lab/DeepRobustWatermark.

Hou-I Liu, Yu-Wen Tseng, Kai-Cheng Chang et al.

Despite notable advancements in the field of computer vision, the precise detection of tiny objects continues to pose a significant challenge, largely owing to the minuscule pixel representation allocated to these objects in imagery data. This challenge resonates profoundly in the domain of geoscience and remote sensing, where high-fidelity detection of tiny objects can facilitate a myriad of applications ranging from urban planning to environmental monitoring. In this paper, we propose a new framework, namely, DeNoising FPN with Trans R-CNN (DNTR), to improve the performance of tiny object detection. DNTR consists of an easy plug-in design, DeNoising FPN (DN-FPN), and an effective Transformer-based detector, Trans R-CNN. Specifically, feature fusion in the feature pyramid network is important for detecting multiscale objects. However, noisy features may be produced during the fusion process since there is no regularization between the features of different scales. Therefore, we introduce a DN-FPN module that utilizes contrastive learning to suppress noise in each level's features in the top-down path of FPN. Second, based on the two-stage framework, we replace the obsolete R-CNN detector with a novel Trans R-CNN detector to focus on the representation of tiny objects with self-attention. Experimental results manifest that our DNTR outperforms the baselines by at least 17.4% in terms of APvt on the AI-TOD dataset and 9.6% in terms of AP on the VisDrone dataset, respectively. Our code will be available at https://github.com/hoiliu-0801/DNTR.

Ruoxuan Zhang, Hongxia Xie, Yi Yao et al.

Recipe image generation is an important challenge in food computing, with applications from culinary education to interactive recipe platforms. However, there is currently no real-world dataset that comprehensively connects recipe goals, sequential steps, and corresponding images. To address this, we introduce RecipeGen, the first real-world goal-step-image benchmark for recipe generation, featuring diverse ingredients, varied recipe steps, multiple cooking styles, and a broad collection of food categories. Data is in https://github.com/zhangdaxia22/RecipeGen.

Chun-Wei Yang, Thanh-Hai Phung, Hong-Han Shuai et al.

In the absence of vaccines or medicines to stop COVID-19, one of the effective methods to slow the spread of the coronavirus and reduce the overloading of healthcare is to wear a face mask. Nevertheless, to mandate the use of face masks or coverings in public areas, additional human resources are required, which is tedious and attention-intensive. To automate the monitoring process, one of the promising solutions is to leverage existing object detection models to detect the faces with or without masks. As such, security officers do not have to stare at the monitoring devices or crowds, and only have to deal with the alerts triggered by the detection of faces without masks. Existing object detection models usually focus on designing the CNN-based network architectures for extracting discriminative features. However, the size of training datasets of face mask detection is small, while the difference between faces with and without masks is subtle. Therefore, in this paper, we propose a face mask detection framework that uses the context attention module to enable the effective attention of the feed-forward convolution neural network by adapting their attention maps feature refinement. Moreover, we further propose an anchor-free detector with Triplet-Consistency Representation Learning by integrating the consistency loss and the triplet loss to deal with the small-scale training data and the similarity between masks and occlusions. Extensive experimental results show that our method outperforms the other state-of-the-art methods. The source code is released as a public download to improve public health at https://github.com/wei-1006/MaskFaceDetection.

Yu-Jen Ma, Hong-Han Shuai, Wen-Huang Cheng

In this paper, we propose a novel SpatioTemporal convolutional Dense Network (STDNet) to address the video-based crowd counting problem, which contains the decomposition of 3D convolution and the 3D spatiotemporal dilated dense convolution to alleviate the rapid growth of the model size caused by the Conv3D layer. Moreover, since the dilated convolution extracts the multiscale features, we combine the dilated convolution with the channel attention block to enhance the feature representations. Due to the error that occurs from the difficulty of labeling crowds, especially for videos, imprecise or standard-inconsistent labels may lead to poor convergence for the model. To address this issue, we further propose a new patch-wise regression loss (PRL) to improve the original pixel-wise loss. Experimental results on three video-based benchmarks, i.e., the UCSD, Mall and WorldExpo'10 datasets, show that STDNet outperforms both image- and video-based state-of-the-art methods. The source codes are released at \url{https://github.com/STDNet/STDNet}.

Edwin Arkel Rios, Wen-Huang Cheng, Bo-Cheng Lai

In this work we tackle the challenging problem of anime character recognition. Anime, referring to animation produced within Japan and work derived or inspired from it. For this purpose we present DAF:re (DanbooruAnimeFaces:revamped), a large-scale, crowd-sourced, long-tailed dataset with almost 500 K images spread across more than 3000 classes. Additionally, we conduct experiments on DAF:re and similar datasets using a variety of classification models, including CNN based ResNets and self-attention based Vision Transformer (ViT). Our results give new insights into the generalization and transfer learning properties of ViT models on substantially different domain datasets from those used for the upstream pre-training, including the influence of batch and image size in their training. Additionally, we share our dataset, source-code, pre-trained checkpoints and results, as Animesion, the first end-to-end framework for large-scale anime character recognition: https://github.com/arkel23/animesion

Rong Chao, Wen-Huang Cheng, Moreno La Quatra et al. · gatech

This work aims to investigate the use of a recently proposed, attention-free, scalable state-space model (SSM), Mamba, for the speech enhancement (SE) task. In particular, we employ Mamba to deploy different regression-based SE models (SEMamba) with different configurations, namely basic, advanced, causal, and non-causal. Furthermore, loss functions either based on signal-level distances or metric-oriented are considered. Experimental evidence shows that SEMamba attains a competitive PESQ of 3.55 on the VoiceBank-DEMAND dataset with the advanced, non-causal configuration. A new state-of-the-art PESQ of 3.69 is also reported when SEMamba is combined with Perceptual Contrast Stretching (PCS). Compared against Transformed-based equivalent SE solutions, a noticeable FLOPs reduction up to ~12% is observed with the advanced non-causal configurations. Finally, SEMamba can be used as a pre-processing step before automatic speech recognition (ASR), showing competitive performance against recent SE solutions.

Seonghwa Choi, Moonkyeong Choi, Mingyu Jang et al.

Modeling relightable and animatable human avatars from monocular video is a long-standing and challenging task. Recently, Neural Radiance Field (NeRF) and 3D Gaussian Splatting (3DGS) methods have been employed to reconstruct the avatars. However, they often produce unsatisfactory photo-realistic results because of insufficient geometrical details related to body motion, such as clothing wrinkles. In this paper, we propose a 3DGS-based human avatar modeling framework, termed as Relightable and Dynamic Gaussian Avatar (RnD-Avatar), that presents accurate pose-variant deformation for high-fidelity geometrical details. To achieve this, we introduce dynamic skinning weights that define the human avatar's articulation based on pose while also learning additional deformations induced by body motion. We also introduce a novel regularization to capture fine geometric details under sparse visual cues. Furthermore, we present a new multi-view dataset with varied lighting conditions to evaluate relight. Our framework enables realistic rendering of novel poses and views while supporting photo-realistic lighting effects under arbitrary lighting conditions. Our method achieves state-of-the-art performance in novel view synthesis, novel pose rendering, and relighting.

Yu-Wen Tseng, Xingyi Zheng, Ya-Chen Wu et al.

Test-time adaptation (TTA) adapts pre-trained models to distribution shifts at inference using only unlabeled test data. Under the Practical TTA (PTTA) setting, where test streams are temporally correlated and non-i.i.d., memory has become an indispensable component for stable adaptation, yet existing methods universally store amples in a single unstructured pool. We show that this single-cluster design is fundamentally mismatched to PTTA: a stream clusterability analysis reveals that test streams are inherently multi-modal, with the optimal number of mixture components consistently far exceeding one. To close this structural gap, we propose Multi-Cluster Memory (MCM), a plug-and-play framework that organizes stored samples into multiple clusters using lightweight pixel-level statistical descriptors. MCM introduces three complementary mechanisms: descriptor-based cluster assignment to capture distinct distributional modes, Adjacent Cluster Consolidation (ACC) to bound memory usage by merging the most similar temporally adjacent clusters, and Uniform Cluster Retrieval (UCR) to ensure balanced supervision across all modes during adaptation. Integrated with three contemporary TTA methods on CIFAR-10-C, CIFAR-100-C, ImageNet-C, and DomainNet, MCM achieves consistent improvements across all 12 configurations, with gains up to 5.00% on ImageNet-C and 12.13% on DomainNet. Notably, these gains scale with distributional complexity: larger label spaces with greater multi-modality benefit most from multi-cluster organization. GMM-based memory diagnostics further confirm that MCM maintains near-optimal distributional balance, entropy, and mode coverage, whereas single-cluster memory exhibits persistent imbalance and progressive mode loss. These results establish memory organization as a key design axis for practical test-time adaptation.

Bo Wu, Peiye Liu, Wen-Huang Cheng et al.

Social Media Popularity Prediction (SMPP) is a crucial task that involves automatically predicting future popularity values of online posts, leveraging vast amounts of multimodal data available on social media platforms. Studying and investigating social media popularity becomes central to various online applications and requires novel methods of comprehensive analysis, multimodal comprehension, and accurate prediction. SMP Challenge is an annual research activity that has spurred academic exploration in this area. This paper summarizes the challenging task, data, and research progress. As a critical resource for evaluating and benchmarking predictive models, we have released a large-scale SMPD benchmark encompassing approximately half a million posts authored by around 70K users. The research progress analysis provides an overall analysis of the solutions and trends in recent years. The SMP Challenge website (www.smp-challenge.com) provides the latest information and news.

Zhiyu Zhou, Peilin Liu, Ruoxuan Zhang et al.

Small object-centric spatial understanding in indoor videos remains a significant challenge for multimodal large language models (MLLMs), despite its practical value for object search and assistive applications. Although existing benchmarks have advanced video spatial intelligence, embodied reasoning, and diagnostic perception, no existing benchmark directly evaluates whether a model can localize a target object in video and express its position with sufficient precision for downstream use. In this work, we introduce PinpointQA, the first dataset and benchmark for small object-centric spatial understanding in indoor videos. Built from ScanNet++ and ScanNet200, PinpointQA comprises 1,024 scenes and 10,094 QA pairs organized into four progressively challenging tasks: Target Presence Verification (TPV), Nearest Reference Identification (NRI), Fine-Grained Spatial Description (FSD), and Structured Spatial Prediction (SSP). The dataset is built from intermediate spatial representations, with QA pairs generated automatically and further refined through quality control. Experiments on representative MLLMs reveal a consistent capability gap along the progressive chain, with SSP remaining particularly difficult. Supervised fine-tuning on PinpointQA yields substantial gains, especially on the harder tasks, demonstrating that PinpointQA serves as both a diagnostic benchmark and an effective training dataset. The dataset and project page are available at https://rainchowz.github.io/PinpointQA.

Tai-Ming Huang, Wei-Tung Lin, Kai-Lung Hua et al.

The increasing realism of AI-generated images has raised serious concerns about misinformation and privacy violations, highlighting the urgent need for accurate and interpretable detection methods. While existing approaches have made progress, most rely on binary classification without explanations or depend heavily on supervised fine-tuning, resulting in limited generalization. In this paper, we propose ThinkFake, a novel reasoning-based and generalizable framework for AI-generated image detection. Our method leverages a Multimodal Large Language Model (MLLM) equipped with a forgery reasoning prompt and is trained using Group Relative Policy Optimization (GRPO) reinforcement learning with carefully designed reward functions. This design enables the model to perform step-by-step reasoning and produce interpretable, structured outputs. We further introduce a structured detection pipeline to enhance reasoning quality and adaptability. Extensive experiments show that ThinkFake outperforms state-of-the-art methods on the GenImage benchmark and demonstrates strong zero-shot generalization on the challenging LOKI benchmark. These results validate our framework's effectiveness and robustness. Code will be released upon acceptance.

Cheng Zhang, Hongxia xie, Bin Wen et al.

With the rapid advancement of diffusion models, text-to-image generation has achieved significant progress in image resolution, detail fidelity, and semantic alignment, particularly with models like Stable Diffusion 3.5, Stable Diffusion XL, and FLUX 1. However, generating emotionally expressive and abstract artistic images remains a major challenge, largely due to the lack of large-scale, fine-grained emotional datasets. To address this gap, we present the EmoArt Dataset -- one of the most comprehensive emotion-annotated art datasets to date. It contains 132,664 artworks across 56 painting styles (e.g., Impressionism, Expressionism, Abstract Art), offering rich stylistic and cultural diversity. Each image includes structured annotations: objective scene descriptions, five key visual attributes (brushwork, composition, color, line, light), binary arousal-valence labels, twelve emotion categories, and potential art therapy effects. Using EmoArt, we systematically evaluate popular text-to-image diffusion models for their ability to generate emotionally aligned images from text. Our work provides essential data and benchmarks for emotion-driven image synthesis and aims to advance fields such as affective computing, multimodal learning, and computational art, enabling applications in art therapy and creative design. The dataset and more details can be accessed via our project website.

Stephen Ekaputra Limantoro, Jhe-Hao Lin, Chih-Yu Wang et al.

Knowledge distillation (KD) compresses the network capacity by transferring knowledge from a large (teacher) network to a smaller one (student). It has been mainstream that the teacher directly transfers knowledge to the student with its original distribution, which can possibly lead to incorrect predictions. In this article, we propose a logit-based distillation via swapped logit processing, namely Swapped Logit Distillation (SLD). SLD is proposed under two assumptions: (1) the wrong prediction occurs when the prediction label confidence is not the maximum; (2) the "natural" limit of probability remains uncertain as the best value addition to the target cannot be determined. To address these issues, we propose a swapped logit processing scheme. Through this approach, we find that the swap method can be effectively extended to teacher and student outputs, transforming into two teachers. We further introduce loss scheduling to boost the performance of two teachers' alignment. Extensive experiments on image classification tasks demonstrate that SLD consistently performs best among previous state-of-the-art methods.

Jian-Yu Jiang-Lin, Kang-Yang Huang, Ling Zou et al.

Advances in generative modeling have made it increasingly easy to fabricate realistic portrayals of individuals, creating serious risks for security, communication, and public trust. Detecting such person-driven manipulations requires systems that not only distinguish altered content from authentic media but also provide clear and reliable reasoning. In this paper, we introduce TriDF, a comprehensive benchmark for interpretable DeepFake detection. TriDF contains high-quality forgeries from advanced synthesis models, covering 16 DeepFake types across image, video, and audio modalities. The benchmark evaluates three key aspects: Perception, which measures the ability of a model to identify fine-grained manipulation artifacts using human-annotated evidence; Detection, which assesses classification performance across diverse forgery families and generators; and Hallucination, which quantifies the reliability of model-generated explanations. Experiments on state-of-the-art multimodal large language models show that accurate perception is essential for reliable detection, but hallucination can severely disrupt decision-making, revealing the interdependence of these three aspects. TriDF provides a unified framework for understanding the interaction between detection accuracy, evidence identification, and explanation reliability, offering a foundation for building trustworthy systems that address real-world synthetic media threats.

Chi-Han Chen, Chieh-Ming Chen, Wen-Huang Cheng et al.

The study of terrain and landform classification through UAV remote sensing diverges significantly from ground vehicle patrol tasks. Besides grappling with the complexity of data annotation and ensuring temporal consistency, it also confronts the scarcity of relevant data and the limitations imposed by the effective range of many technologies. This research substantiates that, in aerial positioning tasks, both the mean Intersection over Union (mIoU) and temporal consistency (TC) metrics are of paramount importance. It is demonstrated that fully labeled data is not the optimal choice, as selecting only key data lacks the enhancement in TC, leading to failures. Hence, a teacher-student architecture, coupled with key frame selection and key frame updating algorithms, is proposed. This framework successfully performs weakly supervised learning and TC knowledge distillation, overcoming the deficiencies of traditional TC training in aerial tasks. The experimental results reveal that our method utilizing merely 30\% of labeled data, concurrently elevates mIoU and temporal consistency ensuring stable localization of terrain objects. Result demo : https://gitlab.com/prophet.ai.inc/drone-based-riverbed-inspection

Ruoxuan Zhang, Qiyun Zheng, Zhiyu Zhou et al.

Theory of Mind (ToM) refers to the ability to infer others' mental states, such as beliefs, desires, and intentions. Current vision-language embodied agents lack ToM-based decision-making, and existing benchmarks focus solely on human mental states while ignoring the agent's own perspective, hindering coherent decision and action generation. To address this, we propose MindPower, a Robot-Centric framework integrating Perception, Mental Reasoning, Decision Making and Action. Given multimodal inputs, MindPower first perceives the environment and human states, then performs ToM Reasoning to model both self and others, and finally generates decisions and actions guided by inferred mental states. Furthermore, we introduce Mind-Reward, a novel optimization objective that encourages VLMs to produce consistent ToM Reasoning and behavior. Our model outperforms GPT-4o by 12.77% in decision making and 12.49% in action generation.

Kun-Hsiang Lin, Yu-Wen Tseng, Kang-Yang Huang et al.

Face anti-spoofing (FAS) aims to construct a robust system that can withstand diverse attacks. While recent efforts have concentrated mainly on cross-domain generalization, two significant challenges persist: limited semantic understanding of attack types and training redundancy across domains. We address the first by integrating vision-language models (VLMs) to enhance the perception of visual input. For the second challenge, we employ a meta-domain strategy to learn a unified model that generalizes well across multiple domains. Our proposed InstructFLIP is a novel instruction-tuned framework that leverages VLMs to enhance generalization via textual guidance trained solely on a single domain. At its core, InstructFLIP explicitly decouples instructions into content and style components, where content-based instructions focus on the essential semantics of spoofing, and style-based instructions consider variations related to the environment and camera characteristics. Extensive experiments demonstrate the effectiveness of InstructFLIP by outperforming SOTA models in accuracy and substantially reducing training redundancy across diverse domains in FAS. Project website is available at https://kunkunlin1221.github.io/InstructFLIP.

Xinqi Fan, Jingting Li, John See et al.

Facial micro-expressions (MEs) are involuntary movements of the face that occur spontaneously when a person experiences an emotion but attempts to suppress or repress the facial expression, typically found in a high-stakes environment. In recent years, substantial advancements have been made in the areas of ME recognition, spotting, and generation. However, conventional approaches that treat spotting and recognition as separate tasks are suboptimal, particularly for analyzing long-duration videos in realistic settings. Concurrently, the emergence of multimodal large language models (MLLMs) and large vision-language models (LVLMs) offers promising new avenues for enhancing ME analysis through their powerful multimodal reasoning capabilities. The ME grand challenge (MEGC) 2025 introduces two tasks that reflect these evolving research directions: (1) ME spot-then-recognize (ME-STR), which integrates ME spotting and subsequent recognition in a unified sequential pipeline; and (2) ME visual question answering (ME-VQA), which explores ME understanding through visual question answering, leveraging MLLMs or LVLMs to address diverse question types related to MEs. All participating algorithms are required to run on this test set and submit their results on a leaderboard. More details are available at https://megc2025.github.io.

Lu Pan, Yu-Hsuan Huang, Hongxia Xie et al.

Reflective documents often suffer from specular highlights under ambient lighting, severely hindering text readability and degrading overall visual quality. Although recent deep learning methods show promise in highlight removal, they remain suboptimal for document images, primarily due to the lack of dedicated datasets and tailored architectural designs. To tackle these challenges, we present DocHR14K, a large-scale real-world dataset comprising 14,902 high-resolution image pairs across six document categories and various lighting conditions. To the best of our knowledge, this is the first high-resolution dataset for document highlight removal that captures a wide range of real-world lighting conditions. Additionally, motivated by the observation that the residual map between highlighted and clean images naturally reveals the spatial structure of highlight regions, we propose a simple yet effective Highlight Location Prior (HLP) to estimate highlight masks without human annotations. Building on this prior, we present the Location-Aware Laplacian Pyramid Highlight Removal Network (L2HRNet), which effectively removes highlights by leveraging estimated priors and incorporates diffusion module to restore details. Extensive experiments demonstrate that DocHR14K improves highlight removal under diverse lighting conditions. Our L2HRNet achieves state-of-the-art performance across three benchmark datasets, including a 5.01\% increase in PSNR and a 13.17\% reduction in RMSE on DocHR14K.

Pei-Chi Chen, Yi Yao, Chan-Feng Hsu et al.

Camouflaged image generation is emerging as a solution to data scarcity in camouflaged vision perception, offering a cost-effective alternative to data collection and labeling. Recently, the state-of-the-art approach successfully generates camouflaged images using only foreground objects. However, it faces two critical weaknesses: 1) the background knowledge does not integrate effectively with foreground features, resulting in a lack of foreground-background coherence (e.g., color discrepancy); 2) the generation process does not prioritize the fidelity of foreground objects, which leads to distortion, particularly for small objects. To address these issues, we propose a Foreground-Aware Camouflaged Image Generation (FACIG) model. Specifically, we introduce a Foreground-Aware Feature Integration Module (FAFIM) to strengthen the integration between foreground features and background knowledge. In addition, a Foreground-Aware Denoising Loss is designed to enhance foreground reconstruction supervision. Experiments on various datasets show our method outperforms previous methods in overall camouflaged image quality and foreground fidelity.

Hong-Xia Xie, I-Hsuan Li, Ling Lo et al.

In this work, we describe our method for tackling the valence-arousal estimation challenge from ABAW2 ICCV-2021 Competition. The competition organizers provide an in-the-wild Aff-Wild2 dataset for participants to analyze affective behavior in real-life settings. We use a two stream model to learn emotion features from appearance and action respectively. To solve data imbalanced problem, we apply label distribution smoothing (LDS) to re-weight labels. Our proposed method achieves Concordance Correlation Coefficient (CCC) of 0.591 and 0.617 for valence and arousal on the validation set of Aff-wild2 dataset.

Fatma S. Abousaleh, Wen-Huang Cheng, Neng-Hao Yu et al.

Billions of photos are uploaded to the web daily through various types of social networks. Some of these images receive millions of views and become popular, whereas others remain completely unnoticed. This raises the problem of predicting image popularity on social media. The popularity of an image can be affected by several factors, such as visual content, aesthetic quality, user, post metadata, and time. Thus, considering all these factors is essential for accurately predicting image popularity. In addition, the efficiency of the predictive model also plays a crucial role. In this study, motivated by multimodal learning, which uses information from various modalities, and the current success of convolutional neural networks (CNNs) in various fields, we propose a deep learning model, called visual-social convolutional neural network (VSCNN), which predicts the popularity of a posted image by incorporating various types of visual and social features into a unified network model. VSCNN first learns to extract high-level representations from the input visual and social features by utilizing two individual CNNs. The outputs of these two networks are then fused into a joint network to estimate the popularity score in the output layer. We assess the performance of the proposed method by conducting extensive experiments on a dataset of approximately 432K images posted on Flickr. The simulation results demonstrate that the proposed VSCNN model significantly outperforms state-of-the-art models, with a relative improvement of greater than 2.33%, 7.59%, and 14.16% in terms of Spearman's Rho, mean absolute error, and mean squared error, respectively.

Lei Chen, Shao-En Weng, Chu-Jun Peng et al.

Network security has been an active research topic for long. One critical issue is improving the anomaly detection capability of intrusion detection systems (IDSs), such as firewalls. However, existing network anomaly datasets are out of date (i.e., being collected many years ago) or IP-anonymized, making the data characteristics differ from today's network. Therefore, this work introduces a new, large-scale, and real-world dataset, ZYELL-NCTU NetTraffic-1.0, which is collected from the raw output of firewalls in a real network, with the objective to advance the development of network security researches.

Chien-Lung Chou, Chieh-Yun Chen, Chia-Wei Hsieh et al.

The virtual try-on task is so attractive that it has drawn considerable attention in the field of computer vision. However, presenting the three-dimensional (3D) physical characteristic (e.g., pleat and shadow) based on a 2D image is very challenging. Although there have been several previous studies on 2D-based virtual try-on work, most 1) required user-specified target poses that are not user-friendly and may not be the best for the target clothing, and 2) failed to address some problematic cases, including facial details, clothing wrinkles and body occlusions. To address these two challenges, in this paper, we propose an innovative template-free try-on image synthesis (TF-TIS) network. The TF-TIS first synthesizes the target pose according to the user-specified in-shop clothing. Afterward, given an in-shop clothing image, a user image, and a synthesized pose, we propose a novel model for synthesizing a human try-on image with the target clothing in the best fitting pose. The qualitative and quantitative experiments both indicate that the proposed TF-TIS outperforms the state-of-the-art methods, especially for difficult cases.

Hong-Xia Xie, Ling Lo, Hong-Han Shuai et al.

Facial micro-expressions indicate brief and subtle facial movements that appear during emotional communication. In comparison to macro-expressions, micro-expressions are more challenging to be analyzed due to the short span of time and the fine-grained changes. In recent years, micro-expression recognition (MER) has drawn much attention because it can benefit a wide range of applications, e.g. police interrogation, clinical diagnosis, depression analysis, and business negotiation. In this survey, we offer a fresh overview to discuss new research directions and challenges these days for MER tasks. For example, we review MER approaches from three novel aspects: macro-to-micro adaptation, recognition based on key apex frames, and recognition based on facial action units. Moreover, to mitigate the problem of limited and biased ME data, synthetic data generation is surveyed for the diversity enrichment of micro-expression data. Since micro-expression spotting can boost micro-expression analysis, the state-of-the-art spotting works are also introduced in this paper. At last, we discuss the challenges in MER research and provide potential solutions as well as possible directions for further investigation.

Ling Lo, Hong-Xia Xie, Hong-Han Shuai et al.

Micro-Expression (ME) is the spontaneous, involuntary movement of a face that can reveal the true feeling. Recently, increasing researches have paid attention to this field combing deep learning techniques. Action units (AUs) are the fundamental actions reflecting the facial muscle movements and AU detection has been adopted by many researches to classify facial expressions. However, the time-consuming annotation process makes it difficult to correlate the combinations of AUs to specific emotion classes. Inspired by the nodes relationship building Graph Convolutional Networks (GCN), we propose an end-to-end AU-oriented graph classification network, namely MER-GCN, which uses 3D ConvNets to extract AU features and applies GCN layers to discover the dependency laying between AU nodes for ME categorization. To our best knowledge, this work is the first end-to-end architecture for Micro-Expression Recognition (MER) using AUs based GCN. The experimental results show that our approach outperforms CNN-based MER networks.

Wen-Huang Cheng, Sijie Song, Chieh-Yun Chen et al.

Fashion is the way we present ourselves to the world and has become one of the world's largest industries. Fashion, mainly conveyed by vision, has thus attracted much attention from computer vision researchers in recent years. Given the rapid development, this paper provides a comprehensive survey of more than 200 major fashion-related works covering four main aspects for enabling intelligent fashion: (1) Fashion detection includes landmark detection, fashion parsing, and item retrieval, (2) Fashion analysis contains attribute recognition, style learning, and popularity prediction, (3) Fashion synthesis involves style transfer, pose transformation, and physical simulation, and (4) Fashion recommendation comprises fashion compatibility, outfit matching, and hairstyle suggestion. For each task, the benchmark datasets and the evaluation protocols are summarized. Furthermore, we highlight promising directions for future research.

Bo Wu, Wen-Huang Cheng, Peiye Liu et al.

"SMP Challenge" aims to discover novel prediction tasks for numerous data on social multimedia and seek excellent research teams. Making predictions via social multimedia data (e.g. photos, videos or news) is not only helps us to make better strategic decisions for the future, but also explores advanced predictive learning and analytic methods on various problems and scenarios, such as multimedia recommendation, advertising system, fashion analysis etc. In the SMP Challenge at ACM Multimedia 2019, we introduce a novel prediction task Temporal Popularity Prediction, which focuses on predicting future interaction or attractiveness (in terms of clicks, views or likes etc.) of new online posts in social media feeds before uploading. We also collected and released a large-scale SMPD benchmark with over 480K posts from 69K users. In this paper, we define the challenge problem, give an overview of the dataset, present statistics of rich information for data and annotation and design the accuracy and correlation evaluation metrics for temporal popularity prediction to the challenge.

Xutong Ren, Mading Li, Wen-Huang Cheng et al.

Many low-light enhancement methods ignore intensive noise in original images. As a result, they often simultaneously enhance the noise as well. Furthermore, extra denoising procedures adopted by most methods ruin the details. In this paper, we introduce a joint low-light enhancement and denoising strategy, aimed at obtaining well-enhanced low-light images while getting rid of the inherent noise issue simultaneously. The proposed method performs Retinex model based decomposition in a successive sequence, which sequentially estimates a piece-wise smoothed illumination and a noise-suppressed reflectance. After getting the illumination and reflectance map, we adjust the illumination layer and generate our enhancement result. In this noise-suppressed sequential decomposition process we enforce the spatial smoothness on each component and skillfully make use of weight matrices to suppress the noise and improve the contrast. Results of extensive experiments demonstrate the effectiveness and practicability of our method. It performs well for a wide variety of images, and achieves better or comparable quality compared with the state-of-the-art methods.