Qingyu Li

Qingyu Li, Yilei Shi, Xiao Xiang Zhu

Accurate and reliable building footprint maps are vital to urban planning and monitoring, and most existing approaches fall back on convolutional neural networks (CNNs) for building footprint generation. However, one limitation of these methods is that they require strong supervisory information from massive annotated samples for network learning. State-of-the-art semi-supervised semantic segmentation networks with consistency training can help to deal with this issue by leveraging a large amount of unlabeled data, which encourages the consistency of model output on data perturbation. Considering that rich information is also encoded in feature maps, we propose to integrate the consistency of both features and outputs in the end-to-end network training of unlabeled samples, enabling to impose additional constraints. Prior semi-supervised semantic segmentation networks have established the cluster assumption, in which the decision boundary should lie in the vicinity of low sample density. In this work, we observe that for building footprint generation, the low-density regions are more apparent at the intermediate feature representations within the encoder than the encoder's input or output. Therefore, we propose an instruction to assign the perturbation to the intermediate feature representations within the encoder, which considers the spatial resolution of input remote sensing imagery and the mean size of individual buildings in the study area. The proposed method is evaluated on three datasets with different resolutions: Planet dataset (3 m/pixel), Massachusetts dataset (1 m/pixel), and Inria dataset (0.3 m/pixel). Experimental results show that the proposed approach can well extract more complete building structures and alleviate omission errors.

Xiangyang Luo, Qingyu Li, Xiaokun Liu et al.

Current video generation models perform well at single-shot synthesis but struggle with multi-shot videos, facing critical challenges in maintaining character and background consistency across shots and flexibly generating videos of arbitrary length and shot count. To address these limitations, we introduce \textbf{FilmWeaver}, a novel framework designed to generate consistent, multi-shot videos of arbitrary length. First, it employs an autoregressive diffusion paradigm to achieve arbitrary-length video generation. To address the challenge of consistency, our key insight is to decouple the problem into inter-shot consistency and intra-shot coherence. We achieve this through a dual-level cache mechanism: a shot memory caches keyframes from preceding shots to maintain character and scene identity, while a temporal memory retains a history of frames from the current shot to ensure smooth, continuous motion. The proposed framework allows for flexible, multi-round user interaction to create multi-shot videos. Furthermore, due to this decoupled design, our method demonstrates high versatility by supporting downstream tasks such as multi-concept injection and video extension. To facilitate the training of our consistency-aware method, we also developed a comprehensive pipeline to construct a high-quality multi-shot video dataset. Extensive experimental results demonstrate that our method surpasses existing approaches on metrics for both consistency and aesthetic quality, opening up new possibilities for creating more consistent, controllable, and narrative-driven video content. Project Page: https://filmweaver.github.io

Kling Team, Jialu Chen, Yuanzheng Ci et al.

We present Kling-Omni, a generalist generative framework designed to synthesize high-fidelity videos directly from multimodal visual language inputs. Adopting an end-to-end perspective, Kling-Omni bridges the functional separation among diverse video generation, editing, and intelligent reasoning tasks, integrating them into a holistic system. Unlike disjointed pipeline approaches, Kling-Omni supports a diverse range of user inputs, including text instructions, reference images, and video contexts, processing them into a unified multimodal representation to deliver cinematic-quality and highly-intelligent video content creation. To support these capabilities, we constructed a comprehensive data system that serves as the foundation for multimodal video creation. The framework is further empowered by efficient large-scale pre-training strategies and infrastructure optimizations for inference. Comprehensive evaluations reveal that Kling-Omni demonstrates exceptional capabilities in in-context generation, reasoning-based editing, and multimodal instruction following. Moving beyond a content creation tool, we believe Kling-Omni is a pivotal advancement toward multimodal world simulators capable of perceiving, reasoning, generating and interacting with the dynamic and complex worlds.

Chenying Liu, Conrad M Albrecht, Yi Wang et al.

While the volume of remote sensing data is increasing daily, deep learning in Earth Observation faces lack of accurate annotations for supervised optimization. Crowdsourcing projects such as OpenStreetMap distribute the annotation load to their community. However, such annotation inevitably generates noise due to insufficient control of the label quality, lack of annotators, frequent changes of the Earth's surface as a result of natural disasters and urban development, among many other factors. We present Adaptively trIggered Online Object-wise correction (AIO2) to address annotation noise induced by incomplete label sets. AIO2 features an Adaptive Correction Trigger (ACT) module that avoids label correction when the model training under- or overfits, and an Online Object-wise Correction (O2C) methodology that employs spatial information for automated label modification. AIO2 utilizes a mean teacher model to enhance training robustness with noisy labels to both stabilize the training accuracy curve for fitting in ACT and provide pseudo labels for correction in O2C. Moreover, O2C is implemented online without the need to store updated labels every training epoch. We validate our approach on two building footprint segmentation datasets with different spatial resolutions. Experimental results with varying degrees of building label noise demonstrate the robustness of AIO2. Source code will be available at https://github.com/zhu-xlab/AIO2.git.

Xiangyang Luo, Qingyu Li, Yuming Li et al.

Recent advances in video generation models have achieved impressive results. However, these models heavily rely on the use of high-quality data that combines both high visual quality and high motion quality. In this paper, we identify a key challenge in video data curation: the Motion-Vision Quality Dilemma. We discovered that visual quality and motion intensity inherently exhibit a negative correlation, making it hard to obtain golden data that excels in both aspects. To address this challenge, we first examine the hierarchical learning dynamics of video diffusion models and conduct gradient-based analysis on quality-degraded samples. We discover that quality-imbalanced data can produce gradients similar to golden data at appropriate timesteps. Based on this, we introduce the novel concept of Timestep selection in Training Process. We propose Timestep-aware Quality Decoupling (TQD), which modifies the data sampling distribution to better match the model's learning process. For certain types of data, the sampling distribution is skewed toward higher timesteps for motion-rich data, while high visual quality data is more likely to be sampled during lower timesteps. Through extensive experiments, we demonstrate that TQD enables training exclusively on separated imbalanced data to achieve performance surpassing conventional training with better data, challenging the necessity of perfect data in video generation. Moreover, our method also boosts model performance when trained on high-quality data, showcasing its effectiveness across different data scenarios.

Zhichao Liao, Xiaole Xian, Qingyu Li et al.

Existing concept customization methods have achieved remarkable outcomes in high-fidelity and multi-concept customization. However, they often neglect the influence on the original model's behavior and capabilities when learning new personalized concepts. To address this issue, we propose PureCC. PureCC introduces a novel decoupled learning objective for concept customization, which combines the implicit guidance of the target concept with the original conditional prediction. This separated form enables PureCC to substantially focus on the original model during training. Moreover, based on this objective, PureCC designs a dual-branch training pipeline that includes a frozen extractor providing purified target concept representations as implicit guidance and a trainable flow model producing the original conditional prediction, jointly achieving pure learning for personalized concepts. Furthermore, PureCC introduces a novel adaptive guidance scale $λ^\star$ to dynamically adjust the guidance strength of the target concept, balancing customization fidelity and model preservation. Extensive experiments show that PureCC achieves state-of-the-art performance in preserving the original behavior and capabilities while enabling high-fidelity concept customization. The code is available at https://github.com/lzc-sg/PureCC.

Yuming Li, Qingyu Li, Chengyu Bai et al.

Reinforcement learning from human feedback (RLHF) shows promise for aligning diffusion and flow models, yet policy optimization methods such as GRPO suffer from inefficient and static sampling strategies. These methods treat all prompts and denoising steps uniformly, ignoring substantial variations in sample learning value as well as the dynamic nature of critical exploration moments. To address this issue, we conduct a detailed analysis of the internal attention dynamics during GRPO training and uncover a key insight: attention entropy can serve as a powerful dual-signal proxy. First, across different samples, the relative change in attention entropy (ΔEntropy), which reflects the divergence between the current policy and the base policy, acts as a robust indicator of sample learning value. Second, during the denoising process, the peaks of absolute attention entropy (Entropy(t)), which quantify attention dispersion, effectively identify critical timesteps where high-value exploration occurs. Building on this observation, we propose Adaptive Entropy-Guided Policy Optimization (AEGPO), a novel dual-signal, dual-level adaptive optimization strategy. At the global level, AEGPO uses ΔEntropy to dynamically allocate rollout budgets, prioritizing prompts with higher learning value. At the local level, it exploits the peaks of Entropy(t) to guide exploration selectively at critical high-dispersion timesteps rather than uniformly across all denoising steps. By focusing computation on the most informative samples and the most critical moments, AEGPO enables more efficient and effective policy optimization. Experiments on text-to-image generation tasks demonstrate that AEGPO significantly accelerates convergence and achieves superior alignment performance compared to standard GRPO variants.

Junsheng Yao, Lichao Mou, Qingyu Li

Monocular 3D building reconstruction from remote sensing imagery is essential for scalable urban modeling, yet existing methods often require task-specific architectures and intensive supervision. This paper presents the first systematic evaluation of SAM 3D, a general-purpose image-to-3D foundation model, for monocular remote sensing building reconstruction. We benchmark SAM 3D against TRELLIS on samples from the NYC Urban Dataset, employing Frechet Inception Distance (FID) and CLIP-based Maximum Mean Discrepancy (CMMD) as evaluation metrics. Experimental results demonstrate that SAM 3D produces more coherent roof geometry and sharper boundaries compared to TRELLIS. We further extend SAM 3D to urban scene reconstruction through a segment-reconstruct-compose pipeline, demonstrating its potential for urban scene modeling. We also analyze practical limitations and discuss future research directions. These findings provide practical guidance for deploying foundation models in urban 3D reconstruction and motivate future integration of scene-level structural priors.

Zhichao Liao, Xiaokun Liu, Wenyu Qin et al.

Image Aesthetic Assessment (IAA) is a long-standing and challenging research task. However, its subset, Human Image Aesthetic Assessment (HIAA), has been scarcely explored. To bridge this research gap, our work pioneers a holistic implementation framework tailored for HIAA. Specifically, we introduce HumanBeauty, the first dataset purpose-built for HIAA, which comprises 108k high-quality human images with manual annotations. To achieve comprehensive and fine-grained HIAA, 50K human images are manually collected through a rigorous curation process and annotated leveraging our trailblazing 12-dimensional aesthetic standard, while the remaining 58K with overall aesthetic labels are systematically filtered from public datasets. Based on the HumanBeauty database, we propose HumanAesExpert, a powerful Vision Language Model for aesthetic evaluation of human images. We innovatively design an Expert head to incorporate human knowledge of aesthetic sub-dimensions while jointly utilizing the Language Modeling (LM) and Regression heads. This approach empowers our model to achieve superior proficiency in both overall and fine-grained HIAA. Furthermore, we introduce a MetaVoter, which aggregates scores from all three heads, to effectively balance the capabilities of each head, thereby realizing improved assessment precision. Extensive experiments demonstrate that our HumanAesExpert models deliver significantly better performance in HIAA than other state-of-the-art models. Project webpage: https://humanaesexpert.github.io/HumanAesExpert/

Xiao Xiang Zhu, Qingyu Li, Yilei Shi et al.

Understanding how buildings are distributed globally is crucial to revealing the human footprint on our home planet. This built environment affects local climate, land surface albedo, resource distribution, and many other key factors that influence well-being and human health. Despite this, quantitative and comprehensive data on the distribution and properties of buildings worldwide is lacking. To this end, by using a big data analytics approach and nearly 800,000 satellite images, we generated the highest resolution and highest accuracy building map ever created: the GlobalBuildingMap (GBM). A joint analysis of building maps and solar potentials indicates that rooftop solar energy can supply the global energy consumption need at a reasonable cost. Specifically, if solar panels were placed on the roofs of all buildings, they could supply 1.1-3.3 times -- depending on the efficiency of the solar device -- the global energy consumption in 2020, which is the year with the highest consumption on record. We also identified a clear geospatial correlation between building areas and key socioeconomic variables, which indicates our global building map can serve as an important input to modeling global socioeconomic needs and drivers.

Xiaole Xian, Zhichao Liao, Qingyu Li et al.

Fine-tuning a pre-trained Text-to-Image (T2I) model on a tailored portrait dataset is the mainstream method for text-to-portrait customization. However, existing methods often severely impact the original model's behavior (e.g., changes in ID, layout, etc.) while customizing portrait attributes. To address this issue, we propose SPF-Portrait, a pioneering work to purely understand customized target semantics and minimize disruption to the original model. In our SPF-Portrait, we design a dual-path contrastive learning pipeline, which introduces the original model as a behavioral alignment reference for the conventional fine-tuning path. During the contrastive learning, we propose a novel Semantic-Aware Fine Control Map that indicates the intensity of response regions of the target semantics, to spatially guide the alignment process between the contrastive paths. It adaptively balances the behavioral alignment across different regions and the responsiveness of the target semantics. Furthermore, we propose a novel response enhancement mechanism to reinforce the presentation of target semantics, while mitigating representation discrepancy inherent in direct cross-modal supervision. Through the above strategies, we achieve incremental learning of customized target semantics for pure text-to-portrait customization. Extensive experiments show that SPF-Portrait achieves state-of-the-art performance. Project page: https://spf-portrait.github.io/SPF-Portrait/

Qingyu Li, Lichao Mou, Yuansheng Hua et al.

Building segmentation is of great importance in the task of remote sensing imagery interpretation. However, the existing semantic segmentation and instance segmentation methods often lead to segmentation masks with blurred boundaries. In this paper, we propose a novel instance segmentation network for building segmentation in high-resolution remote sensing images. More specifically, we consider segmenting an individual building as detecting several keypoints. The detected keypoints are subsequently reformulated as a closed polygon, which is the semantic boundary of the building. By doing so, the sharp boundary of the building could be preserved. Experiments are conducted on selected Aerial Imagery for Roof Segmentation (AIRS) dataset, and our method achieves better performance in both quantitative and qualitative results with comparison to the state-of-the-art methods. Our network is a bottom-up instance segmentation method that could well preserve geometric details.

Qingyu Li, Yilei Shi, Xin Huang et al.

Building footprint maps are vital to many remote sensing applications, such as 3D building modeling, urban planning, and disaster management. Due to the complexity of buildings, the accurate and reliable generation of the building footprint from remote sensing imagery is still a challenging task. In this work, an end-to-end building footprint generation approach that integrates convolution neural network (CNN) and graph model is proposed. CNN serves as the feature extractor, while the graph model can take spatial correlation into consideration. Moreover, we propose to implement the feature pairwise conditional random field (FPCRF) as a graph model to preserve sharp boundaries and fine-grained segmentation. Experiments are conducted on four different datasets: (1) Planetscope satellite imagery of the cities of Munich, Paris, Rome, and Zurich; (2) ISPRS benchmark data from the city of Potsdam, (3) Dstl Kaggle dataset; and (4) Inria Aerial Image Labeling data of Austin, Chicago, Kitsap County, Western Tyrol, and Vienna. It is found that the proposed end-to-end building footprint generation framework with the FPCRF as the graph model can further improve the accuracy of building footprint generation by using only CNN, which is the current state-of-the-art.

Yilei Shi, Qingyu Li, Xiao Xiang Zhu

Automatic building extraction from optical imagery remains a challenge due to, for example, the complexity of building shapes. Semantic segmentation is an efficient approach for this task. The latest development in deep convolutional neural networks (DCNNs) has made accurate pixel-level classification tasks possible. Yet one central issue remains: the precise delineation of boundaries. Deep architectures generally fail to produce fine-grained segmentation with accurate boundaries due to their progressive down-sampling. Hence, we introduce a generic framework to overcome the issue, integrating the graph convolutional network (GCN) and deep structured feature embedding (DSFE) into an end-to-end workflow. Furthermore, instead of using a classic graph convolutional neural network, we propose a gated graph convolutional network, which enables the refinement of weak and coarse semantic predictions to generate sharp borders and fine-grained pixel-level classification. Taking the semantic segmentation of building footprints as a practical example, we compared different feature embedding architectures and graph neural networks. Our proposed framework with the new GCN architecture outperforms state-of-the-art approaches. Although our main task in this work is building footprint extraction, the proposed method can be generally applied to other binary or multi-label segmentation tasks.

Yilei Shi, Qingyu Li, Xiao Xiang Zhu

Building footprint information is an essential ingredient for 3-D reconstruction of urban models. The automatic generation of building footprints from satellite images presents a considerable challenge due to the complexity of building shapes. In this work, we have proposed improved generative adversarial networks (GANs) for the automatic generation of building footprints from satellite images. We used a conditional GAN with a cost function derived from the Wasserstein distance and added a gradient penalty term. The achieved results indicated that the proposed method can significantly improve the quality of building footprint generation compared to conditional generative adversarial networks, the U-Net, and other networks. In addition, our method nearly removes all hyperparameters tuning.