arXiv subjects

Shuguang Cui

Publications and source records attributed to Shuguang Cui.

At least 19 recordsLinked to original sources

arXiv2026

Federated 3D Gaussian Splatting for Large-Scale Scene Reconstruction at Wireless Edge

Three-dimensional (3D) Gaussian splatting (3D-GS) has emerged as a promising technique for large-scale scene reconstruction due to its high rendering efficiency and fidelity. However, the training of large-scale 3D-GS models at wireless edge faces various technical challenges including the limited communication, computation, and graphics processing unit (GPU) memory resources at edge devices, the structural inconsistency issue across local models hindering their effective aggregation, as well as privacy leakage risks associated with raw visual content and camera parameters. To address these challenges, this paper proposes a novel resource-efficient federated learning framework for efficiently training 3D-GS models of large scenes under severe resource constraints. First, we propose an on-device model lightweighting mechanism that adaptively selects and prunes Gaussian points to balance the rendering quality and training efficiency. In this mechanism, we quantitatively evaluate the importance of different Gaussian points at each device to facilitate the pruning, and use a novel importance-to-latency ratio criterion to determine the number of pruned Gaussian points under GPU memory and computation/communication latency constraints. Furthermore, we develop a 3D-GS model recovery mechanism that restores structural consistency across local 3D-GS models without accessing private camera parameters, enabling their effective aggregation towards a global model. Finally, extensive experiments show that our approach significantly accelerates convergence, maintains high rendering quality, and reduces training latency compared to state-of-the-art federated 3D-GS baselines.

cs.CV↗

arXiv2026

Self-Localizing MIMO Beam Mapping with Continuously Evolving Channel Memory

Machine learning has greatly advanced data-driven channel modeling and resource optimization. However, most existing methods require accurately location-labeled datasets, which are costly to collect and maintain in dynamic environments. This paper develops a self-localizing multiple-input multiple-output (MIMO) beam map framework that constructs a hierarchical wireless memory from highly sparse channel state information (CSI) measurements without explicit location labels. To reduce acquisition and processing overhead, we use beamdomain received signal strength (RSS) as compact inputs and theoretically show that they enable asymptotically unbiased spatial signature estimation. A dual-scale extractor captures intrasnapshot angular dependencies and inter-sample correlations for incomplete observations, and a hybrid temporal encoder is designed to consolidate recent CSI into stable short-term context for physical anchor inference. The inferred anchors spatially index a physically structured radio map embedding that stores long-term channel knowledge, which conditions a diffusion decoder for location-consistent full CSI reconstruction. Such a radio map embedding provides a persistent wireless knowledge representation that can be continuously updated and reused without full CSI acquisition. Experiments show that the proposed framework improves physical-anchor recovery accuracy by over 30% under sparse measurements and achieves more than 20% channel-capacity gain in non-line-of-sight (NLOS) beam tracking over Kalman-filter-based methods.

eess.SP↗

arXiv2026

Modeling Clinical Workflow for SYNTAX Scoring from Coronary Angiography Videos

The SYNTAX score is a clinically established tool for assessing anatomical lesion complexity in coronary artery disease and guiding subsequent treatment. However, automated SYNTAX scoring is commonly formulated as a direct regression problem from coronary angiography videos to patient-level scores. In this work, we reformulate SYNTAX scoring as a vessel segment identity-preserving anatomical reasoning problem and propose a hierarchical modeling framework that explicitly aligns learning with the clinical workflow. Our approach maintains vessel segment identity across frames and views, estimates stenosis severity at the segment level, and aggregates evidence hierarchically according to coronary anatomy. Simultaneously, to address the scarcity of domain-specific data, we integrate and complete multiple public coronary angiography datasets, constructing a large-scale resource featuring completed vessel segmentation and derived structural annotations. Experiments demonstrate that vessel segment-level stenosis embedding enhances explanatory power and reduces prediction variability compared to baseline models, with the R^2 score improving by 0.201 and dev STD decreasing by 18.4%. These results highlight the necessity of structure-aligned modeling for reliable and stable automated SYNTAX scoring from multi-view coronary angiography videos. The GitHub link is https://github.com/VersaceSu7/SYNTAX_score_777.

cs.CV↗

arXiv2026

MaskVLA: Visual Masking Against Trajectory Overfitting of Vision-Language-Action Model

Vision-Language-Action (VLA) models integrate vision-language understanding with executable robot actions, enabling end-to-end learning for robot control. However, our empirical analysis reveals that existing models exhibit severe trajectory overfitting when finetuned on limited datasets. To guide the model in effectively utilizing wrist camera information, we propose MaskVLA, a masking-based fine-tuning strategy. By randomly masking a small portion of the main camera's visual information, the model is guided to autonomously learn more fine-grained, task-relevant, and effective visual features. This process leads to the emergence of robust policies, thereby enhancing the model's capability to tackle complex manipulation tasks and improving its generalization performance. Our method has been comprehensively evaluated on RoboTwin 2.0, achieving an average success rate improvement of 23.2% and 16.8% compared to $π_0$ and OpenVLA-OFT, respectively. Furthermore, experiments on real-world ALOHA robots also demonstrate the effectiveness of our approach.

cs.CV↗

arXiv2026

CosmoH2G: A Hand-to-Gripper Transfer Dataset and Baseline Method for Object Manipulation with Complex Spatial Movements

Transferring human hand demonstrations to robotic grippers has recently emerged as a cost-effective solution for robot learning. However, existing methods are largely confined to simple, planar tasks and fail to handle complex spatial movements (e.g., intricate trajectories involving rotations or flips) that are essential for robot manipulation. Motivated by this gap, we adopt an implicit, data-driven approach guided by fine-grained hand-pose motions. To this end, we introduce a scalable acquisition pipeline to collect hand-gripper paired demonstrations, governed by a rigorous protocol that prioritizes motion complexity and leverages a handheld gripper for seamless action mimicry. This yields a large-scale paired dataset comprising 6,189 episodes across 1,254 unique objects, exhibiting significantly higher spatial complexity than existing benchmarks. However, learning such complex mappings remains challenging. We observe that naive end-to-end generation of full gripper pose sequences is insufficient, as minor trajectory deviations compound rapidly under intricate dynamics. To address this, we propose a two-stage framework: Stage I predicts sparse gripper keyframes (initial and terminal) to simplify the mapping objective, while Stage II generates the full continuous action sequence conditioned on these keyframes. Furthermore, to mitigate cumulative drift, we keep the gripper's orientation being learned while post-optimizing its translation based on the grasping heuristic and kinematic consistency. In both simulation and real-robot experiments, our framework enables stable and precise hand-to-gripper transfer of complex spatial manipulations, significantly outperforming traditional baselines. Project page: https://cosmoh2g.github.io.

cs.RO↗

arXiv2026

PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimation

Recent monocular depth estimators achieve strong zero-shot generalization, yet often struggle to preserve fine-grained structures and object boundaries. We attribute this limitation to the prevalent combination of large-patch ViT encoders and convolutional decoders, as coarse tokenization can weaken pixel-level cues that upsampling cannot fully recover. To address this issue, we propose PXDepth, a discriminative monocular depth model that separates global context modeling from pixel-level depth prediction. Specifically, a large-patch ViT captures global scene context, while a pixel-space predictor composed of Context-Modulated Pixel Transformer blocks maintains high-resolution spatial representations throughout depth estimation. This design preserves fine structures and sharp boundaries without sacrificing global depth consistency. Across diverse zero-shot benchmarks, PXDepth combines faithful local geometry with competitive global depth accuracy while remaining efficient at inference. Our code and model are available at https://yuanzhy29.github.io/PXDepth-Page/.

cs.CV↗

arXiv2026

InfiniVerse: Occupancy Guided Unbounded Scene Generation for Autonomous Driving

Generating realistic, controllable, and temporally coherent urban environments is a critical yet unresolved challenge in the autonomous driving community. In this paper, we introduce InfiniVerse, a unified pipeline for long-range, 2D-3D-aligned, and controllable synthesis of dynamic urban scenes from a single frame. In practice, our approach first reconstructs a 3D occupancy representation from the input multi-view frame. This representation serves as a foundation for autoregressive scene extension along arbitrary trajectories. Subsequently, a video diffusion model translates the coarse occupancy grid into realistic, spatiotemporally consistent video sequences. Moreover, we propose a hierarchical sketch-and-refine paradigm, in which the generated videos are re-projected as image-conditioned feedback to enhance the 3D occupancy representation, establishing cross-modal alignment and mutual enhancement between the visual and spatial domains. Extensive evaluations on the Waymo Open Dataset and nuScenes demonstrate that InfiniVerse achieves state-of-the-art performance, with a FID of 6.4 and FVD of 67.97, significantly outperforming existing benchmarks in both duration and stability.

cs.CV↗

arXiv2026

Pruning-Aware Multi-Cluster Co-Inference for Large AI Models in AI-RANs

The increasing scale and computational demands of large artificial intelligence models (LAIMs) present significant challenges for efficient inference in resource-constrained distributed environments. In this paper, we propose a multi-cluster LAIM co-inference framework, where an edge server equipped with multiple graphics processing units (GPUs) coordinates multiple user clusters to execute inference tasks collaboratively. Within each cluster, devices capture data from diverse perspectives and employ lightweight on-device LAIMs to extract local features. These features are then transmitted to the edge server, where they are aggregated and fused to generate a more accurate inference outcome. To reveal the fundamental trade-off between model pruning and collaborative inference performance, we develop a theoretical framework that characterizes the impact of pruning ratios and device contributions using rate-distortion theory and partial information decomposition. Based on this analysis, we formulate a joint optimization problem that determines the model pruning ratio, the task scheduling strategy, the bandwidth allocation, and the transmission power, with the goal of minimizing the inference distortion while satisfying the constraints of latency, energy consumption, and server capacity. Extensive simulation results demonstrate that the proposed framework significantly outperforms existing benchmark schemes, achieving superior inference accuracy and resource efficiency in multi-cluster edge intelligence networks.

cs.DC↗

arXiv2026

AerialMetric: Benchmarking and Adapting UAV Monocular Metric Depth Estimation in the Real World

This paper addresses the problem of monocular metric depth estimation in aerial UAV imagery. Although recent data-driven methods have achieved remarkable progress in ground-level scenarios, models trained primarily on street-view and indoor datasets exhibit significant domain gaps when applied to aerial viewpoints. To tackle these challenges, we introduce AerialMetric, a benchmark dataset designed to evaluate and facilitate the adaptation of monocular metric depth estimation under UAV aerial viewpoints. The dataset consists of four complementary subsets collected from different sources, jointly covering real-world photogrammetry data, controlled aerial acquisition settings, photorealistic synthetic scenes, and in-the-wild Internet imagery. Totally, AerialMetric provides 52K real-world and 16K synthetic image-depth pairs with reliable metric ground truth. Based on this dataset, we conduct systematic evaluations of existing state-of-the-art models under aerial settings and investigate the impact of viewpoint, altitude, and camera parameters on metric depth prediction. In addition, by fine-tuning representative metric depth model on our dataset, we establish a comprehensive aerial benchmark and achieve state-of-the-art performance across diverse aerial imagery. Our dataset, code, and model weight are publicly available at https://kuieless.github.io/AerialMetric-ECCV2026-page/.

cs.CV↗

arXiv2026

Geometry-Guided Representations for Coherent Lane and Traffic Topology Reasoning in Driving Scenes

Road topology reasoning is fundamental for autonomous driving, requiring both accurate perception of road elements and understanding of their complex connectivity, including lane connectivity (Lane-to-Lane, L2L) and traffic regulation (Lane-to-Traffic signs, L2T). However, existing methods typically treat perception and topology reasoning as fragmented tasks, ignoring their potential for mutual enhancement. Crucially, while topology is inherently relational, prior works often overlook geometric relationships during feature extraction, relying instead on brittle post-processing or coordinate-based heuristics applied only at inference time. To bridge this gap, we propose CoPo (Coherent Perception and toPology), a unified framework that integrates geometry-guided relational modeling across three levels: 1) Perception-level: We introduce a relation-aware lane detector that utilizes geometry-biased self-attention and curve-guided cross-attention to enrich lane representations with structural priors; 2) Reasoning-level: We design relation-enhanced topology heads, including a geometry-enhanced L2L head and a cross-view L2T head, which effectively align features to infer connectivity; and 3) Supervision-level: We implement a contrastive InfoNCE strategy to regularize relational embeddings, pulling connected pairs closer in the latent space. This coherent multi-level design enables end-to-end joint optimization of perception and reasoning. Extensive experiments on OpenLane-V2 demonstrate that CoPo significantly outperforms existing methods, achieving gains of {\textbf{+3.1}} in DET$_l$, {\textbf{+5.3}} in TOP$_{ll}$, {\textbf{+4.9}} in TOP$_{lt}$, and {\textbf{+4.4}} overall in OLS, setting a new state-of-the-art.

cs.CV↗

arXiv2026

One Rewrite to Fix Them All? Type-Aware Repair Allocation for Text-to-Image Prompt Optimization

Text-to-image (T2I) generators often fail to follow their prompts faithfully, producing wrong counts, swapped attributes, ambiguous relations, and illegible text. Prompt optimization repairs such failures by rewriting the user prompt, requiring no generator retraining, and has yielded promising results. However, existing optimizers absorb heterogeneous failures into one uniform prompt expansion, even though each calls for different repair language. We formulate semantic prompt optimization as atomic repair allocation: each failed proposition is routed to a type-conditioned repair operator before the resulting local constraints are compiled into one executable prompt. We instantiate this formulation in the training-free Type-Aware Repair Allocation (TARA) framework, which separates diagnosis, allocation, compilation, and a semantic repair gate, an accept-or-revert controller over exactly one prescribed repair that prevents semantic regressions. Extensive experiments on DSG and TIFA across four frozen generators demonstrate that TARA achieves the best semantic accuracy in all eight benchmark-generator cells, improving over VisualPrompter by 5.6 and 2.6 points on DSG and TIFA, respectively, while maintaining image quality and running fastest in our matched local setting at 16.0 seconds versus 20.0 seconds per prompt.

cs.AI↗

arXiv2026

Environment-Conditioned Diffusion Meta-Learning for Data-Efficient WiFi Localization

Fingerprinting-based localization often suffers from poor cross-environment generalization, especially when only a few labeled samples are available in the target environment. Existing methods mitigate distribution shifts through domain adaptation or improved signal representations, but they usually ignore environmental geometry or use it in a deterministic manner, limiting their ability to capture diverse multipath variations in complex propagation conditions. To address this issue, we propose EnvCoLoc, an environment-conditioned diffusion meta-learning framework for few-shot fingerprinting localization. EnvCoLoc extracts structured descriptors from 3D point clouds and uses them to condition a latent diffusion generator, which produces environment-specific parameter offsets to modulate a shared meta-learned initialization. This design injects geometry-aware priors into the adaptation process and provides more informative initializations for new environments. To learn the stochastic mapping from coarse environmental descriptors to high-dimensional parameter corrections under limited data, the diffusion generator and localization network are jointly optimized within a two-loop meta-learning framework. The generated offsets capture systematic environment-dependent variations, while gradient-based inner-loop adaptation further refines the model to reduce residual task-specific mismatch. We also provide an excess-loss analysis for finite-step adaptation, theoretically supporting the benefit of geometry-aware initialization. Real-world experiments show that EnvCoLoc consistently improves localization accuracy over baseline methods, achieving up to a 20.0% reduction in mean localization error in NLOS scenarios with only 10 support samples.

eess.SP↗

arXiv2026

LLM-Empowered Multimodal Fusion Framework for Autonomous Driving: Semantic Enhancement and Channel-Adaptive Design

Vision-radar fusion is central to robust autonomous driving, combining dense visual semantics with precise range and velocity measurements from radar. However, real-world fusion quality is fundamentally challenged by dynamically varying input quality, stemming from occlusion, adverse weather, and channel noise. To address this, we re-frame the problem from static data fusion to channel-aware semantic reasoning and propose a Large Language Model-centric Semantic-layer Channel-aware Integrated Perception (LM-SCIP) framework. It places a Large Language Model (LLM) as a central reasoning core to fuse a local visual stream with a quality-varying external radar stream used to cover perception-blind spots. Concretely, LM-SCIP couples a hierarchical radar-vision encoder with a Channel-Adaptive Semantic Module (CASM) that maps link indicators into a "Channel Prompt" to dynamically gate external radar features. A parameter-efficient, LoRA-tuned LLM, in conjunction with a heterogeneous Mixture-of-Experts (H-MoE), then arbitrates between local visual cues and the channel-conditioned radar context. Finally, a decoupled multi-task decoder outputs localization, trajectory forecasting, and image reconstruction. Experiments on nuScenes and VIRAT validate our approach. On nuScenes, under a controlled toggle of radar input, LM-SCIP reduces localization RMSE by 40.0% versus a vision-only baseline. On VIRAT, the model attains a 0.214m localization RMSE and 0.179m minFDE (k=1). These results reveal that the proposed LM-SCIP enables a robust vision-dominant fallback at low SNR and synergistic fusion at high SNR.

cs.CV↗

arXiv2026

Sense Smarter, Think Better: A Survey on Edge Perception for Next-Generation Networks

Edge perception has emerged as a foundational capability for future wireless networks, enabling the network edge to proactively sense, interpret, and interact with the physical environment in a task-oriented and resource-aware manner. This survey provides a comprehensive and structured overview of edge perception. We first review representative sensing modalities and edge artificial intelligence (AI) techniques as the fundamental building blocks. We then examine their synergistic interactions. We systematically analyze how edge AI enhances sensing capabilities, encompassing both in-band and out-of-band modalities, as well as multi-modal sensor data fusion. Moreover, we discuss the role of task-driven sensing in facilitating edge AI, including integrated sensing-communication-computation designs, and active perception frameworks that dynamically adapt sensing strategies for downstream applications. Finally, we identify key challenges and open issues. By consolidating fragmented research across sensing, communication, and edge AI, this survey provides forward-looking insights for the design and implementation of edge perception systems for sixth-generation (6G) networks.

eess.SP↗

arXiv2026

ReFPO: Reflow Regularization for Flow Matching Policy Gradients

We present Reflow-regularized Flow Matching Policy Gradients (ReFPO), a simple online RL method that adds explicit Reflow regularization to FPO for efficient flow-based control. We uncover a key structural property: the gradient updates in Flow Matching Policy Gradients (FPO) can be interpreted as an implicit advantage-weighted Reflow process, providing a new geometric perspective on flow-based policy gradients. Building on this insight, ReFPO introduces an explicit geometric regularizer that can be implemented with a single line of code change without incurring additional computational overhead or auxiliary distillation stages. By synergizing advantage-guided updates with path rectification, our method reduces CFM proxy-ratio spikes, stabilizes PPO-style training, and enables high-fidelity one-step inference that often matches or exceeds multi-step performance. We experimentally demonstrate that ReFPO improves average performance and discretization robustness across GridWorld, MuJoCo Playground, and high-dimensional Humanoid Control tasks, providing a scalable and stable approach for generative policies in complex physical simulations.

cs.RO↗

arXiv2026

A Tutorial on Learning-Based Radio Map Construction: Data, Paradigms, and Physics-Awareness

Radio maps (RMs) provide the digital representation of the wireless propagation environment, mapping complex geographical and topological boundary conditions to critical spatial-spectral metrics that range from received signal strength to full channel state information matrices. The integration of artificial intelligence into next generation wireless networks further necessitates the accurate construction of RMs as a foundational prerequisite for electromagnetic digital twins. This paper presents a comprehensive survey of learning-based RM construction, systematically addressing three intertwined dimensions: data, paradigms, and physics-awareness. From the data perspective, we review physical measurement campaigns, ray tracing simulation engines, and publicly available benchmark datasets, identifying their respective strengths and fundamental limitations. From the paradigm perspective, we establish a core taxonomy that categorizes RM construction into source-aware forward prediction and source agnostic inverse reconstruction, and examine five principal neural architecture families spanning convolutional neural networks, vision transformers, graph neural networks, generative adversarial networks, and diffusion models. We further survey optics-inspired methods adapted from neural radiance fields and 3D Gaussian splatting for continuous wireless radiation field modeling. From the physics-awareness perspective, we introduce a three-level integration framework encompassing data-level feature engineering, loss-level partial differential equation regularization, and architecture level structural isomorphism. Open challenges including foundation model development, physical hallucination detection, and mortized inference for real-time deployment are discussed to outline future research directions. The project page is at https://github.com/UNIC-Lab/Awesome-Radio-Map-Categorized.

eess.SY↗

arXiv2026

3DReflecNet: A Large-Scale Dataset for 3D Reconstruction of Reflective, Transparent, and Low-Texture Objects

Accurate 3D reconstruction of objects with reflective, transparent, or low-texture surfaces still remains notoriously challenging. Such materials often violate key assumptions in multi-view reconstruction pipelines, such as photometric consistency and the availability on distinct geometric texture cues. Existing datasets primarily focus on diffuse, textured objects, and therefore provide limited insight into performance under real-world material complexities. We introduce 3DReflecNet, a large-scale hybrid dataset exceeding 22 TB that is specifically designed to benchmark and advance 3D vision methods for these challenging materials. 3DReflecNet combines two types of data: over 120,000 synthetic instances generated via physically-based rendering of more than 12,000 shapes, and over 1,000 real-world objects captured using consumer devices. Together, these data consist of more than 7 million multi-view frames. The dataset spans diverse materials, complex lighting conditions, and a wide range of geometric forms, including shapes generated from both real and LLM-synthesized 2D images using diffusion-based pipelines. To support robust evaluation, we design benchmarks for five core tasks: image matching, structure-from-motion, novel view synthesis, reflection removal, and relighting. Extensive experiments demonstrate that state-of-the-art methods struggle to maintain accuracy across these settings, highlighting the need for more resilient 3D vision models.

cs.CV↗

arXiv2026

Annotation-Free Indoor Radio Mapping via Physics-Informed Trajectory Inference

Constructing indoor radio maps traditionally requires extensive site surveys with precise user-location labels, making the calibration process costly and time-consuming. Existing calibration-reduction methods either depend on partial location annotations or exploit inertial measurement units (IMUs) to provide relative motion cues; however, IMU-assisted solutions are constrained by hardware availability, device-level access restrictions, and accumulated sensor drift. In this paper, we study a location-label-free indoor radio mapping problem under known access-point deployment geometry and a known walkable spatial domain. We propose a physics-informed trajectory inference framework that uses only Channel State Information (CSI), without relying on user-location labels or IMU measurements. The key idea is to recover the latent spatial coordinates of CSI measurements by exploiting the local spatial continuity of multipath propagation. To this end, we construct a Power-Angle-Delay Profile (PADP) feature distance from MIMO-OFDM CSI and show that, within a local neighborhood and under quasi-static multipath conditions, this distance provides a physically meaningful proxy for small spatial displacements. We then incorporate the PADP-based continuity constraint into a spatially regularized Bayesian inference model for joint trajectory recovery and propagation-parameter estimation. Experiments on a real-world industrial CSI dataset demonstrate that the proposed framework achieves an average localization error of 0.88 m and a relative beam map construction error of 6.68%, improving upon representative channel-embedding and IMU-assisted baselines.

cs.IT↗