Dehong Kong

Dehong Kong, Lina Lei, Lingtao Zheng et al.

Prior work on aesthetic composition typically produces a single aesthetically pleasing crop, overlooking the narrative value of composing multiple shots from one scene. In practice, multi-shot composition is critical for downstream creative workflows: commercial posters often require multiple crops with different emphases (e.g., context, subject, and emotion/product details) to present key story beats. Therefore, we propose \textbf{Triple-Shot Compositions (TSC)}, a composition task that generates a three-shot set -- establishing, medium, and close-up -- from a single human-centric image, each paired with a brief shot description to support visual narration. To learn TSC with limited expert annotations, we introduce \textbf{ShotCrop} which undergoes a three-stage training process: it first applies Chain-of-Thought supervised fine-tuning to establish basic reasoning and aesthetic shot-cropping skills, then performs semi-supervised fine-tuning with high-confidence pseudo labels to further enhance aesthetic capability, and is finally optimized with Group Relative Policy Optimization for \textbf{ShotCrop} (GRPO-S) using a composite reward tailored for it. Specifically, our pseudo-labeling strategy combines MLLM-based scoring, aesthetic assessment, and CLIP similarity to retain high-confidence training signals. In addition, we present TSC-Bench, a benchmark of 1.2k expert-annotated test cases. Notably, ShotCrop achieves an average improvement of \textbf{2.82} times over GPT-5 in shot localization accuracy.

Chenyang Wu, Lina Lei, Fan Li et al.

Recent advances in Diffusion Transformer (DiT)-based video generation technologies have shown impressive results for video object removal. However, these methods still suffer from substantial inference latency. For instance, although MiniMax Remover achieves state-of-the-art visual quality, it operates at only around 10FPS, primarily due to dense computations over the entire spatiotemporal token space, even when only a small masked region actually requires processing. In this paper, we present YOSE, You Only Select Essential Tokens, an efficient fine-tuning framework. YOSE introduces two key components: Batch Variable-length Indexing (BVI) and Diffusion Process Simulator (DiffSim) Module. BVI is a differentiable dynamic indexing operator that adaptively selects essential tokens based on mask information, enabling variable-length token processing across samples. DiffSim provides a diffusion process approximation mechanism for unmasked tokens, which simulates the influence of unmasked regions within DiT self-attention to maintain semantic consistency for masked tokens. With these designs, YOSE achieves mask-aware acceleration, where the inference time scales approximately linearly with the masked regions, in contrast to full-token diffusion methods whose computation remains constant regardless of the mask size. Extensive experiments demonstrate that YOSE achieves up to 2.5X speedup in 70% of cases while maintaining visual quality comparable to the baseline. Code is available at: https://github.com/Wucy0519/YOSE-CVPR26.

Ailing Zhang, Lina Lei, Dehong Kong et al.

Generative diffusion models are developing rapidly and attracting increasing attention due to their wide range of applications. Image-to-Video (I2V) generation has become a major focus in the field of video synthesis. However, existing evaluation benchmarks primarily focus on aspects such as video quality and temporal consistency, while largely overlooking the model's ability to understand the semantics of specific subjects in the input image or to ensure that the generated video aligns with physical laws and human commonsense. To address this gap, we propose UI2V-Bench, a novel benchmark for evaluating I2V models with a focus on semantic understanding and reasoning. It introduces four primary evaluation dimensions: spatial understanding, attribute binding, category understanding, and reasoning. To assess these dimensions, we design two evaluation methods based on Multimodal Large Language Models (MLLMs): an instance-level pipeline for fine-grained semantic understanding, and a feedback-based reasoning pipeline that enables step-by-step causal assessment for more accurate evaluation. UI2V-Bench includes approximately 500 carefully constructed text-image pairs and evaluates a range of both open source and closed-source I2V models across all defined dimensions. We further incorporate human evaluations, which show strong alignment with the proposed MLLM-based metrics. Overall, UI2V-Bench fills a critical gap in I2V evaluation by emphasizing semantic comprehension and reasoning ability, offering a robust framework and dataset to support future research and model development in the field.

Dehong Kong, Siyuan Liang, Wenqi Ren

Object detection techniques for Unmanned Aerial Vehicles (UAVs) rely on Deep Neural Networks (DNNs), which are vulnerable to adversarial attacks. Nonetheless, adversarial patches generated by existing algorithms in the UAV domain pay very little attention to the naturalness of adversarial patches. Moreover, imposing constraints directly on adversarial patches makes it difficult to generate patches that appear natural to the human eye while ensuring a high attack success rate. We notice that patches are natural looking when their overall color is consistent with the environment. Therefore, we propose a new method named Environmental Matching Attack(EMA) to address the issue of optimizing the adversarial patch under the constraints of color. To the best of our knowledge, this paper is the first to consider natural patches in the domain of UAVs. The EMA method exploits strong prior knowledge of a pretrained stable diffusion to guide the optimization direction of the adversarial patch, where the text guidance can restrict the color of the patch. To better match the environment, the contrast and brightness of the patch are appropriately adjusted. Instead of optimizing the adversarial patch itself, we optimize an adversarial perturbation patch which initializes to zero so that the model can better trade off attacking performance and naturalness. Experiments conducted on the DroneVehicle and Carpk datasets have shown that our work can reach nearly the same attack performance in the digital attack(no greater than 2 in mAP$\%$), surpass the baseline method in the physical specific scenarios, and exhibit a significant advantage in terms of naturalness in visualization and color difference with the environment.

Dehong Kong, Fan Li, Zhixin Wang et al.

Recent state-of-the-art image restoration methods mostly adopt latent diffusion models with U-Net backbones, yet still facing challenges in achieving high-quality restoration due to their limited capabilities. Diffusion transformers (DiTs), like SD3, are emerging as a promising alternative because of their better quality with scalability. In this paper, we introduce DPIR (Dual Prompting Image Restoration), a novel image restoration method that effectivly extracts conditional information of low-quality images from multiple perspectives. Specifically, DPIR consits of two branches: a low-quality image conditioning branch and a dual prompting control branch. The first branch utilizes a lightweight module to incorporate image priors into the DiT with high efficiency. More importantly, we believe that in image restoration, textual description alone cannot fully capture its rich visual characteristics. Therefore, a dual prompting module is designed to provide DiT with additional visual cues, capturing both global context and local appearance. The extracted global-local visual prompts as extra conditional control, alongside textual prompts to form dual prompts, greatly enhance the quality of the restoration. Extensive experimental results demonstrate that DPIR delivers superior image restoration performance.

Dehong Kong, Sifan Yu, Siyuan Liang et al.

Visual language modeling for automated driving is emerging as a promising research direction with substantial improvements in multimodal reasoning capabilities. Despite its advanced reasoning abilities, VLM-AD remains vulnerable to serious security threats from adversarial attacks, which involve misleading model decisions through carefully crafted perturbations. Existing attacks have obvious challenges: 1) Physical adversarial attacks primarily target vision modules. They are difficult to directly transfer to VLM-AD systems because they typically attack low-level perceptual components. 2) Adversarial attacks against VLM-AD have largely concentrated on the digital level. To address these challenges, we propose the first Universal Camouflage Attack (UCA) framework for VLM-AD. Unlike previous methods that focus on optimizing the logit layer, UCA operates in the feature space to generate physically realizable camouflage textures that exhibit strong generalization across different user commands and model architectures. Motivated by the observed vulnerability of encoder and projection layers in VLM-AD, UCA introduces a feature divergence loss (FDL) that maximizes the representational discrepancy between clean and adversarial images. In addition, UCA incorporates a multi-scale learning strategy and adjusts the sampling ratio to enhance its adaptability to changes in scale and viewpoint diversity in real-world scenarios, thereby improving training stability. Extensive experiments demonstrate that UCA can induce incorrect driving commands across various VLM-AD models and driving scenarios, significantly surpassing existing state-of-the-art attack methods (improving 30\% in 3-P metrics). Furthermore, UCA exhibits strong attack robustness under diverse viewpoints and dynamic conditions, indicating high potential for practical deployment.