Qing Cheng

Qing Cheng, Xiaofeng Yang, Jie Shen

In this paper, we consider numerical approximations of a hydrodynamically coupled phase field diblock copolymer model, in which the free energy contains a kinetic potential, a gradient entropy, a Ginzburg-Landau double well potential, and a long range nonlocal type potential. We develop a set of second order time marching schemes for this system using the "Invariant Energy Quadratization" approach for the double well potential, the projection method for the Navier-Stokes equation, and a subtle implicit-explicit treatment for the stress and convective term. The resulting schemes are linear and lead to symmetric positive definite systems at each time step, thus they can be efficiently solved. We further prove that these schemes are unconditionally energy stable. Various numerical experiments are performed to validate the accuracy and energy stability of the proposed schemes.

Qing Cheng, Niclas Zeller, Daniel Cremers

In this paper, we present a complete pipeline for 3D semantic mapping solely based on a stereo camera system. The pipeline comprises a direct sparse visual odometry front-end as well as a back-end for global optimization including GNSS integration, and semantic 3D point cloud labeling. We propose a simple but effective temporal voting scheme which improves the quality and consistency of the 3D point labels. Qualitative and quantitative evaluations of our pipeline are performed on the KITTI-360 dataset. The results show the effectiveness of our proposed voting scheme and the capability of our pipeline for efficient large-scale 3D semantic mapping. The large-scale mapping capabilities of our pipeline is furthermore demonstrated by presenting a very large-scale semantic map covering 8000 km of roads generated from data collected by a fleet of vehicles.

Guangming Zhu, Siyuan Wang, Qing Cheng et al.

With the recent surge in the use of touchscreen devices, free-hand sketching has emerged as a promising modality for human-computer interaction. While previous research has focused on tasks such as recognition, retrieval, and generation of familiar everyday objects, this study aims to create a Sketch Input Method Editor (SketchIME) specifically designed for a professional C4I system. Within this system, sketches are utilized as low-fidelity prototypes for recommending standardized symbols in the creation of comprehensive situation maps. This paper also presents a systematic dataset comprising 374 specialized sketch types, and proposes a simultaneous recognition and segmentation architecture with multilevel supervision between recognition and segmentation to improve performance and enhance interpretability. By incorporating few-shot domain adaptation and class-incremental learning, the network's ability to adapt to new users and extend to new task-specific classes is significantly enhanced. Results from experiments conducted on both the proposed dataset and the SPG dataset illustrate the superior performance of the proposed architecture. Our dataset and code are publicly available at https://github.com/GuangmingZhu/SketchIME.

Ruotong Liao, Guowen Huang, Qing Cheng et al.

Text-to-video (T2V) generation faces challenging questions when generating videos with long horizons containing multiple events. Inspired by the intrinsics of the diffusion process, we probe video diffusion transformers (DiTs) and uncover intrinsic turning points in the DiT denoising trajectory where conditioning text affects generation from global layout to fine-grained details. Building on this finding, we present TunerDiT, a simple yet effective progressive steering method that requires no additional training for multi-event generation. TunerDiT comprises two steering handles: (1) Event-Partitioned Masking that enforces event boundaries while allowing cross-event transition bands; (2) Cross-Event Prompt Fusion that injects neighboring event semantics for late-stage refinement. We contribute a self-curated prompt suite for benchmarking multi-event generation, i.e., Meve. TunerDiT achieves state-of-the-art performance across 8 metrics and offers a tunable trade-off between video consistency and event separation, compared with other training-free methods. The improvement in text alignment increases with the event count, indicating a scaling possibility with increasing event count.

Sen Wang, Qing Cheng, Stefano Gasperini et al.

The generation of high-fidelity view synthesis is essential for robotic navigation and interaction but remains challenging, particularly in indoor environments and real-time scenarios. Existing techniques often require significant computational resources for both training and rendering, and they frequently result in suboptimal 3D representations due to insufficient geometric structuring. To address these limitations, we introduce VoxNeRF, a novel approach that utilizes easy-to-obtain geometry priors to enhance both the quality and efficiency of neural indoor reconstruction and novel view synthesis. We propose an efficient voxel-guided sampling technique that allocates computational resources selectively to the most relevant segments of rays based on a voxel-encoded geometry prior, significantly reducing training and rendering time. Additionally, we incorporate a robust depth loss to improve reconstruction and rendering quality in sparse view settings. Our approach is validated with extensive experiments on ScanNet and ScanNet++ where VoxNeRF outperforms existing state-of-the-art methods and establishes a new benchmark for indoor immersive interpolation and extrapolation settings.

Wei Zhang, Tiecheng Sun, Sen Wang et al.

In this letter, we present a neural field-based real-time monocular mapping framework for accurate and dense Simultaneous Localization and Mapping (SLAM). Recent neural mapping frameworks show promising results, but rely on RGB-D or pose inputs, or cannot run in real-time. To address these limitations, our approach integrates dense-SLAM with neural implicit fields. Specifically, our dense SLAM approach runs parallel tracking and global optimization, while a neural field-based map is constructed incrementally based on the latest SLAM estimates. For the efficient construction of neural fields, we employ multi-resolution grid encoding and signed distance function (SDF) representation. This allows us to keep the map always up-to-date and adapt instantly to global updates via loop closing. For global consistency, we propose an efficient Sim(3)-based pose graph bundle adjustment (PGBA) approach to run online loop closing and mitigate the pose and scale drift. To enhance depth accuracy further, we incorporate learned monocular depth priors. We propose a novel joint depth and scale adjustment (JDSA) module to solve the scale ambiguity inherent in depth priors. Extensive evaluations across synthetic and real-world datasets validate that our approach outperforms existing methods in accuracy and map completeness while preserving real-time performance.

Qing Cheng, Damiano Bertolini, Wei Zhang et al.

Panoptic segmentation requires the simultaneous recognition of countable thing instances and amorphous stuff regions, placing joint demands on long-range context modelling, multi-scale feature representation, and efficient dense prediction. Existing convolutional and transformer-based methods struggle to satisfy all three requirements concurrently: convolutional architectures are limited in their capacity to model long-range dependencies, while transformer-based methods incur quadratic computational cost that is prohibitive at high resolutions. In this paper, we propose MambaPanoptic, a fully Mamba-based panoptic segmentation framework that addresses these limitations through two principal contributions. First, we introduce MambaFPN, a top-down feature pyramid that leverages Mamba blocks to generate globally coherent, multi-scale feature representations with linear computational complexity. Second, we adopt a PanopticFCN-style kernel generator that produces unified thing and stuff kernels for proposal-free panoptic prediction, enhanced by a QuadMamba-based feature refinement module applied at multiple network stages. Experiments on the Cityscapes and COCO panoptic segmentation benchmarks demonstrate that MambaPanoptic consistently outperforms PanopticDeepLab and PanopticFCN under comparable model sizes, and matches or surpasses Mask2Former on Cityscapes in PQ and AP while requiring fewer parameters.

Hongyi Luo, Qing Cheng, Daniel Matos et al.

Humans can interpret geospatial information through natural language, while the geospatial cognition capabilities of Large Language Models (LLMs) remain underexplored. Prior research in this domain has been constrained by non-quantifiable metrics, limited evaluation datasets and unclear research hierarchies. Therefore, we propose a large-scale benchmark and conduct a comprehensive evaluation of the geospatial route cognition of LLMs. We create a large-scale evaluation dataset comprised of 36000 routes from 12 metropolises worldwide. Then, we introduce PathBuilder, a novel tool for converting natural language instructions into navigation routes, and vice versa, bridging the gap between geospatial information and natural language. Finally, we propose a new evaluation framework and metrics to rigorously assess 11 state-of-the-art (SOTA) LLMs on the task of route reversal. The benchmark reveals that LLMs exhibit limitation to reverse routes: most reverse routes neither return to the starting point nor are similar to the optimal route. Additionally, LLMs face challenges such as low robustness in route generation and high confidence for their incorrect answers. Code\ \&\ Data available here: \href{https://github.com/bghjmn32/EMNLP2025_Turnback}{TurnBack.}

Lei Cheng, Mahdi Saleh, Qing Cheng et al.

Despite the advancements in 3D full-shape generation, accurately modeling complex geometries and semantics of shape parts remains a significant challenge, particularly for shapes with varying numbers of parts. Current methods struggle to effectively integrate the contextual and structural information of 3D shapes into their generative processes. We address these limitations with PRISM, a novel compositional approach for 3D shape generation that integrates categorical diffusion models with Statistical Shape Models (SSM) and Gaussian Mixture Models (GMM). Our method employs compositional SSMs to capture part-level geometric variations and uses GMM to represent part semantics in a continuous space. This integration enables both high fidelity and diversity in generated shapes while preserving structural coherence. Through extensive experiments on shape generation and manipulation tasks, we demonstrate that our approach significantly outperforms previous methods in both quality and controllability of part-level operations. Our code will be made publicly available.

Wei Zhang, Qing Cheng, David Skuddis et al.

We present HI-SLAM2, a geometry-aware Gaussian SLAM system that achieves fast and accurate monocular scene reconstruction using only RGB input. Existing Neural SLAM or 3DGS-based SLAM methods often trade off between rendering quality and geometry accuracy, our research demonstrates that both can be achieved simultaneously with RGB input alone. The key idea of our approach is to enhance the ability for geometry estimation by combining easy-to-obtain monocular priors with learning-based dense SLAM, and then using 3D Gaussian splatting as our core map representation to efficiently model the scene. Upon loop closure, our method ensures on-the-fly global consistency through efficient pose graph bundle adjustment and instant map updates by explicitly deforming the 3D Gaussian units based on anchored keyframe updates. Furthermore, we introduce a grid-based scale alignment strategy to maintain improved scale consistency in prior depths for finer depth details. Through extensive experiments on Replica, ScanNet, and ScanNet++, we demonstrate significant improvements over existing Neural SLAM methods and even surpass RGB-D-based methods in both reconstruction and rendering quality. The project page and source code will be made available at https://hi-slam2.github.io/.

Fan Ye, Qing Cheng, Weifeng Hao et al.

The spatiotemporally continuous data of normalized difference snow index (NDSI) are key to understanding the mechanisms of snow occurrence and development as well as the patterns of snow distribution changes. However, the presence of clouds, particularly prevalent in polar regions such as the Greenland Ice Sheet (GrIS), introduces a significant number of missing pixels in the MODIS NDSI daily data. To address this issue, this study proposes the utilization of a spatiotemporal extreme gradient boosting (STXGBoost) model generate a comprehensive NDSI dataset. In the proposed model, various input variables are carefully selected, encompassing terrain features, geometry-related parameters, and surface property variables. Moreover, the model incorporates spatiotemporal variation information, enhancing its capacity for reconstructing the NDSI dataset. Verification results demonstrate the efficacy of the STXGBoost model, with a coefficient of determination of 0.962, root mean square error of 0.030, mean absolute error of 0.011, and negligible bias (0.0001). Furthermore, simulation comparisons involving missing data and cross-validation with Landsat NDSI data illustrate the model's capability to accurately reconstruct the spatial distribution of NDSI data. Notably, the proposed model surpasses the performance of traditional machine learning models, showcasing superior NDSI predictive capabilities. This study highlights the potential of leveraging auxiliary data to reconstruct NDSI in GrIS, with implications for broader applications in other regions. The findings offer valuable insights for the reconstruction of NDSI remote sensing data, contributing to the further understanding of spatiotemporal dynamics in snow-covered regions.

Antonio Ruiz, Tao Wu, Andrew Melnik et al.

Methods that synthesize indoor 3D scenes from text prompts have wide-ranging applications in film production, interior design, video games, virtual reality, and synthetic data generation for training embodied agents. Existing approaches typically either train generative models from scratch or leverage vision-language models (VLMs). While VLMs achieve strong performance, particularly for complex or open-ended prompts, smaller task-specific models remain necessary for deployment on resource-constrained devices such as extended reality (XR) glasses or mobile phones. However, many generative approaches that train from scratch overlook the inherent graph structure of indoor scenes, which can limit scene coherence and realism. Conversely, methods that incorporate scene graphs either demand a user-provided semantic graph, which is generally inconvenient and restrictive, or rely on ground-truth relationship annotations, limiting their capacity to capture more varied object interactions. To address these challenges, we introduce GeoSceneGraph, a method that synthesizes 3D scenes from text prompts by leveraging the graph structure and geometric symmetries of 3D scenes, without relying on predefined relationship classes. Despite not using ground-truth relationships, GeoSceneGraph achieves performance comparable to methods that do. Our model is built on equivariant graph neural networks (EGNNs), but existing EGNN approaches are typically limited to low-dimensional conditioning and are not designed to handle complex modalities such as text. We propose a simple and effective strategy for conditioning EGNNs on text features, and we validate our design through ablation studies.

Ruotong Liao, Guowen Huang, Qing Cheng et al.

Text-to-video (T2V) generation has surged in response to challenging questions, especially when a long video must depict multiple sequential events with temporal coherence and controllable content. Existing methods that extend to multi-event generation omit an inspection of the intrinsic factor in event shifting. The paper aims to answer the central question: When and where multi-event prompts control event transition during T2V generation. This work introduces MEve, a self-curated prompt suite for evaluating multi-event text-to-video (T2V) generation, and conducts a systematic study of two representative model families, i.e., OpenSora and CogVideoX. Extensive experiments demonstrate the importance of early intervention in denoising steps and block-wise model layers, revealing the essential factor for multi-event video generation and highlighting the possibilities for multi-event conditioning in future models.

Yuehang Si, Zefan Zeng, Jincai Huang et al.

Temporal Knowledge Graph (TKG) is an efficient method for describing the dynamic development of facts along a timeline. Most research on TKG reasoning (TKGR) focuses on modelling the repetition of global facts and designing patterns of local historical facts. However, they face two significant challenges: inadequate modeling of the event distribution shift between training and test samples, and reliance on random entity substitution for generating negative samples, which often results in low-quality sampling. To this end, we propose a novel distributional feature modeling approach for training TKGR models, Test-Time Training-guided Distribution shift Modelling (T3DM), to adjust the model based on distribution shift and ensure the global consistency of model reasoning. In addition, we design a negative-sampling strategy to generate higher-quality negative quadruples based on adversarial training. Extensive experiments show that T3DM provides better and more robust results than the state-of-the-art baselines in most cases.

Qing Cheng, Zefan Zeng, Xingchen Hu et al.

Event Causality Identification (ECI) has become an essential task in Natural Language Processing (NLP), focused on automatically detecting causal relationships between events within texts. This comprehensive survey systematically investigates fundamental concepts and models, developing a systematic taxonomy and critically evaluating diverse models. We begin by defining core concepts, formalizing the ECI problem, and outlining standard evaluation protocols. Our classification framework divides ECI models into two primary tasks: Sentence-level Event Causality Identification (SECI) and Document-level Event Causality Identification (DECI). For SECI, we review models employing feature pattern-based matching, machine learning classifiers, deep semantic encoding, prompt-based fine-tuning, and causal knowledge pre-training, alongside data augmentation strategies. For DECI, we focus on approaches utilizing deep semantic encoding, event graph reasoning, and prompt-based fine-tuning. Special attention is given to recent advancements in multi-lingual and cross-lingual ECI, as well as zero-shot ECI leveraging Large Language Models (LLMs). We analyze the strengths, limitations, and unresolved challenges associated with each approach. Extensive quantitative evaluations are conducted on four benchmark datasets to rigorously assess the performance of various ECI models. We conclude by discussing future research directions and highlighting opportunities to advance the field further.

Sihai Guan, Qing Cheng, Yong Zhao

In this paper, a family of novel diffusion adaptive estimation algorithm is proposed from the asymmetric cost function perspective by combining diffusion strategy and the linear-linear cost (LLC), quadratic-quadratic cost (QQC), and linear-exponential cost (LEC), at all distributed network nodes, and named diffusion LLCLMS (DLLCLMS), diffusion QQCLMS (DQQCLMS), and diffusion LECLMS (DLECLMS), respectively. Then the stability of mean estimation error and computational complexity of those three diffusion algorithms are analyzed theoretically. Finally, several experiment simulation results are designed to verify the superiority of those three proposed diffusion algorithms. Experimental simulation results show that DLLCLMS, DQQCLMS, and DLECLMS algorithms are more robust to the input signal and impulsive noise than the DSELMS, DRVSSLMS, and DLLAD algorithms. In brief, theoretical analysis and experiment results show that those proposed DLLCLMS, DQQCLMS, and DLECLMS algorithms have superior performance when estimating the unknown linear system under the changeable impulsive noise environments and different types of input signals.

Patrick Wenzel, Rui Wang, Nan Yang et al.

We present a novel dataset covering seasonal and challenging perceptual conditions for autonomous driving. Among others, it enables research on visual odometry, global place recognition, and map-based re-localization tracking. The data was collected in different scenarios and under a wide variety of weather conditions and illuminations, including day and night. This resulted in more than 350 km of recordings in nine different environments ranging from multi-level parking garage over urban (including tunnels) to countryside and highway. We provide globally consistent reference poses with up-to centimeter accuracy obtained from the fusion of direct stereo visual-inertial odometry with RTK-GNSS. The full dataset is available at https://go.vision.in.tum.de/4seasons.

Zhiwei Li, Huanfeng Shen, Qing Cheng et al.

Cloud detection is an important preprocessing step for the precise application of optical satellite imagery. In this paper, we propose a deep learning based cloud detection method named multi-scale convolutional feature fusion (MSCFF) for remote sensing images of different sensors. In the network architecture of MSCFF, the symmetric encoder-decoder module, which provides both local and global context by densifying feature maps with trainable convolutional filter banks, is utilized to extract multi-scale and high-level spatial features. The feature maps of multiple scales are then up-sampled and concatenated, and a novel multi-scale feature fusion module is designed to fuse the features of different scales for the output. The two output feature maps of the network are cloud and cloud shadow maps, which are in turn fed to binary classifiers outside the model to obtain the final cloud and cloud shadow mask. The MSCFF method was validated on hundreds of globally distributed optical satellite images, with spatial resolutions ranging from 0.5 to 50 m, including Landsat-5/7/8, Gaofen-1/2/4, Sentinel-2, Ziyuan-3, CBERS-04, Huanjing-1, and collected high-resolution images exported from Google Earth. The experimental results show that MSCFF achieves a higher accuracy than the traditional rule-based cloud detection methods and the state-of-the-art deep learning models, especially in bright surface covered areas. The effectiveness of MSCFF means that it has great promise for the practical application of cloud detection for multiple types of medium and high-resolution remote sensing images. Our established global high-resolution cloud detection validation dataset has been made available online.

Chengyue Zhang, Zhiwei Li, Qing Cheng et al.

Remote sensing images often suffer from cloud cover. Cloud removal is required in many applications of remote sensing images. Multitemporal-based methods are popular and effective to cope with thick clouds. This paper contributes to a summarization and experimental comparation of the existing multitemporal-based methods. Furthermore, we propose a spatiotemporal-fusion with poisson-adjustment method to fuse multi-sensor and multi-temporal images for cloud removal. The experimental results show that the proposed method has potential to address the problem of accuracy reduction of cloud removal in multi-temporal images with significant changes.

Qing Cheng, Huiqing Liu, Huanfeng Shen et al.

The trade-off in remote sensing instruments that balances the spatial resolution and temporal frequency limits our capacity to monitor spatial and temporal dynamics effectively. The spatiotemporal data fusion technique is considered as a cost-effective way to obtain remote sensing data with both high spatial resolution and high temporal frequency, by blending observations from multiple sensors with different advantages or characteristics. In this paper, we develop the spatial and temporal non-local filter based fusion model (STNLFFM) to enhance the prediction capacity and accuracy, especially for complex changed landscapes. The STNLFFM method provides a new transformation relationship between the fine-resolution reflectance images acquired from the same sensor at different dates with the help of coarse-resolution reflectance data, and makes full use of the high degree of spatiotemporal redundancy in the remote sensing image sequence to produce the final prediction. The proposed method was tested over both the Coleambally Irrigation Area study site and the Lower Gwydir Catchment study site. The results show that the proposed method can provide a more accurate and robust prediction, especially for heterogeneous landscapes and temporally dynamic areas.