arXiv subjects

Zihang Cheng

Publications and source records attributed to Zihang Cheng.

11 recordsLinked to original sources

arXiv2026

PointQ-Bench: Benchmarking Diagnostic and Interpretable Point Cloud Quality Assessment

Point cloud quality plays a critical role in 3D acquisition, reconstruction, rendering, and perception, yet existing point cloud quality assessment (PCQA) research remains largely centered on scalar score prediction. In practical inspection scenarios, quality assessment often involves identifying defects, characterizing dominant issue types, assessing downstream usability, and providing evidence-supported descriptions, which are not explicitly evaluated by current benchmarks. We introduce PointQ-Bench, a benchmark designed to extend PCQA from scalar scoring toward comprehensive quality understanding. PointQ-Bench consists of 3,083 point clouds spanning authentic scans, simulated distortions, and AI-generated content, covering eight major issue types. Each sample is annotated with mean opinion scores (MOS), quality levels, issue tags, expert-grounded descriptions, and 12,332 question-answer pairs. The benchmark supports three perception-oriented tasks: anomaly sensing, defect diagnosis, and usability grading, as well as a cognition-oriented task of open-ended quality reporting. To evaluate free-form quality descriptions, we further propose SSFRQ-5D, a five-dimensional evaluation protocol validated through human-AI agreement analysis. Extensive experiments on 14 vision-language models and traditional PCQA baselines reveal a consistent perception-diagnosis gap: while current models exhibit emerging abilities in coarse defect perception, they struggle with grounded diagnosis and quality calibration. Strong 2D MLLMs generally outperform existing 3D VLMs, and the benefit of additional views or point-level inputs is non-uniform, varying across tasks, data sources, and models, particularly under boundary-ambiguous conditions. Overall, PointQ-Bench provides a diagnostic testbed for advancing reliable and interpretable point cloud quality understanding.

cs.CV↗

arXiv2026

ForestHG-Trace: Traceable Long-Horizon Ecological Reasoning over Large-Scale Forest Scenes

Remote sensing question answering (RS-QA) often requires more than direct semantic prediction, especially in large-scale forest scenes where ecological analysis involves multi-step filtering, numerical aggregation, neighborhood reasoning, and verifiable evidence. We introduce ForestHG-Trace, a framework for traceable long-horizon ecological reasoning over forest environments. It represents multimodal NEON forest scenes as ecological hypergraphs, where tree instances, spatial units, semantic groups, and neighborhood relations support higher-order reasoning beyond pairwise scene graphs. An LLM-guided agent then invokes deterministic tools for reading, filtering, expansion, aggregation, comparison, and auditing, producing replayable execution traces and compact evidence records rather than only free-form answers. We further construct ForestTraceQA, an executable benchmark for evaluating ecological QA across diverse task types and reasoning depths. Experiments show that ForestHG-Trace substantially improves answer accuracy and execution faithfulness over single-step baselines and scene-graph agents, while highlighting execution depth as the main bottleneck for long-horizon ecological QA.

cs.CV↗

arXiv2026

Beyond Appearance: Can Multimodal Large Language Models Exploit Vertical Structure for Remote Sensing Natural Scene Understanding?

Multimodal large language models (MLLMs) have advanced rapidly in remote-sensing analysis, yet existing evaluations remain predominantly 2D-centric. Because spectrally confused regions can appear nearly identical yet differ substantially in vertical structure, appearance alone is often insufficient for reliable semantic interpretation in natural scenes. Vertical structure therefore provides decision-critical physical evidence, yet whether current MLLMs can effectively perceive, ground, and utilize such geometric evidence remains underexplored. To bridge this gap, we introduce VertiCue-Bench, the first diagnostic benchmark that uses controlled interventions to probe whether vertical height evidence is actually perceived, grounded, and utilized, and we establish a three-stage evidence-utilization framework of Perception--Grounding--Utilization. By constructing a Representation Intervention Spectrum spanning multiple presentation and interaction modalities, including Raw Visual, Tool-assisted, and Oracle Text conditions, together with controlled counterfactual tests, we conduct an in-depth disentangled diagnosis across 10 state-of-the-art models. Our experiments reveal and formally characterize the Vertical Structure Utilization Gap. Although current models exhibit emerging geometric perception capabilities, they still struggle to accurately ground vertical evidence to relevant spatial entities and integrate it into high-level semantic decisions. This finding identifies a critical bottleneck in developing physically grounded and geometry-aware remote-sensing MLLMs.

cs.CV↗

arXiv2026

HyperVision: A Channel-Adaptive Ground-Based Hyperspectral Vision Pre-trained Backbone

While hyperspectral imaging provides rich spatial-spectral information across hundreds of narrow wavelength bands for precise material identification, ground-based hyperspectral pre-trained backbones remain absent, constrained by varying spectral configurations across sensors, limited annotations and heterogeneous labeling schemes, and the limited scale and scene diversity of existing datasets. To address these challenges and enable universal perception, we propose HyperVision, the first ground-based hyperspectral pre-trained backbone. First, to handle varying spectral configurations, HyperVision adopts a channel-adaptive dynamic embedding mechanism to map heterogeneous inputs into a unified token space. Second, we develop an unsupervised representation learning framework. Specifically, to address limited annotations and heterogeneous labeling schemes, a multi-source pseudo-labeling method is introduced to fuse spatial structures from SAM2 and fine-grained spectral material information from HyperFree. Furthermore, to enrich scene diversity and compensate for limited dataset scale, a cross-modal knowledge distillation mechanism is utilized to transfer rich semantic representations from a pre-trained RGB vision model to our backbone. Pre-trained on a collection of 15k images from 26 diverse ground-based datasets, HyperVision demonstrates exceptional generalization. Requiring only efficient head-only adaptation without adjusting backbone parameters, it outperforms state-of-the-art task-specific methods across three downstream tasks under varying sensor configurations, yielding up to a 16.3% relative improvement in hyperspectral semantic segmentation $\mathrm{Acc}_{\mathrm{M}}$, a 2.1% relative gain in object tracking AUC, and a 35.5% reduction in salient object detection MAE. The source code and pre-trained models are available at https://github.com/lronkitty/HyperVision.

cs.CV↗

arXiv2025

X-SG$^2$S: Safe and Generalizable Gaussian Splatting with X-dimensional Watermarks

3D Gaussian Splatting (3DGS) has been widely used in 3D reconstruction and 3D generation. However, the rapid adoption of 3D Gaussian Splatting raises growing concerns about information leakage and unauthorized use, urging the exploration of effective watermarking techniques. However, existing methods are limited by low capacity, fragility under geometric perturbations, and the infeasible requirement for costly fine-tuning or pipeline modifications, motivating the need for a generalizable, feed-forward framework capable of robust multi-modal embedding with minimal intrusion. In this paper, we propose a new framework X-SG$^2$S which can simultaneously inject 1D to 3D watermarks for copyright protection, while keeping the high fidelity of original 3DGS scenes. Specifically, we first split the watermarks into message patches. A self-adaptive gate is developed to select the injection positions of the watermark messages. Then, we use an XD (multi-dimensional) injection head to inject multi-modal messages into sorted 3DGS points. To restore watermarking messages, a learnable gate is developed to recognize the watermarked locations, from which our XD-extraction heads are used to restore hidden messages. X-SG$^2$S is the first framework to unify 1D-to-3D watermarking and enable simultaneous multi-modal watermark embedding in 3DGS, achieving this with minimal rendering interference and zero modifications to parameters or pipelines. Extensive experiments demonstrate that X-SG$^2$S effectively preserves consistency between the watermark and the original 3DGS, exhibits robustness against model degradation, and maintains accurate judgment capabilities.

cs.CR↗

arXiv2024

Double-Directional V2V Channel Measurement using ReRoMA at 60 GHz

The coordination of vehicles is a crucial element of autonomous driving, as it enhances the efficiency, convenience, and safety of road traffic. In order to fully exploit the capabilities of such coordination, communication with high data rate and low latency is required. It can be reasonably argued that millimeter-wave (mm-wave) vehicle-to-vehicle (V2V) systems are capable of fulfilling the aforementioned requirements. Nevertheless, in order to develop a system that can be deployed in real-world scenarios and to gain an understanding of the various effects of mm-wave propagation, it is necessary to perform radio propagation measurements and to derive radio channel models from them across a range of scenarios and environments. To this end, we have conducted measurement campaigns at 60\,GHz in a variety of situations, including driving in a convoy, driving in opposite direction on a six-lane road, and overtaking. These measurements employ a channel sounder based on ReRoMA, a recently introduced concept that enables the real-time measurement of dynamic double-directional radio channels. The evaluations presented herein encompass key channel parameters, including the path loss (path loss coefficient of approximately 1.9), the root mean square (RMS) delay spread (within a range of 5\,ns to 110\,ns), the angular spreads (in a range of 0.05 to 0.4), the power distribution among multipath components, and the channel stationarity time (multiple seconds).

cs.IT↗

arXiv2024

Large-scale Outdoor Cell-free mMIMO Channel Measurement in an Urban Scenario at 3.5 GHz

The design of cell-free massive MIMO (CF-mMIMO) systems requires accurate, measurement-based channel models. This paper provides the first results from the by far most extensive outdoor measurement campaign for CF-mMIMO channels in an urban environment. We measured impulse responses between over 20,000 potential access point (AP) locations and 80 user equipments (UEs) at 3.5 GHz with 350 MHz bandwidth (BW). Measurements use a "virtual array" approach at the AP and a hybrid switched/virtual approach at the UE. This paper describes the sounder design, measurement environment, data processing, and sample results, particularly the evolution of the power-delay profiles (PDPs) as a function of the AP locations, and its relation to the propagation environment.

eess.SP↗

arXiv2024

Cell-free massive MIMO Channels in an Urban Environment -- Measurements and Channel Statistics

Cell-free massive MIMO (CF-mMIMO), where each user equipment (UE) is connected to multiple access points (APs), is emerging as an important component for 5G and 6G cellular systems. Accurate channel models based on measurements are required to optimize their design and deployment. This paper presents an extensive measurement campaign for CF-mMIMO in an urban environment. A new "virtual AP" technique measures channels between 80 UE locations and more than 20,000 possible microcellular AP locations. Measurements are done at 3.5 GHz carrier frequency with 350 MHz bandwidth (BW). The paper describes the measurement setup and data processing, shows sample results and their physical interpretation, and provides statistics for key quantities such as pathloss, shadowing, delay spread (DS), and delay window. We find pathloss coefficients of 2.9 and 10.4 for line-of-sight (LOS) and non line-of-sight (NLOS), respectively, where the high LOS coefficient is mainly because larger distance leads to more grazing angle of incidence and thus lower antenna gain in our setup. Shadowing standard deviations are 5.1/16.6 dB, and root mean squared (RMS) DSs of -80.6/-72.6 dBs. The measurements can also be used for parameterizing a CUNEC-type model, which will be reported in future work.

eess.SP↗

arXiv2023

A Framework for Developing and Evaluating Algorithms for Estimating Multipath Propagation Parameters from Channel Sounder Measurements

A framework is proposed for developing and evaluating algorithms for extracting multipath propagation components (MPCs) from measurements collected by channel sounders at millimeter-wave frequencies. Sounders equipped with an omnidirectional transmitter and a receiver with a uniform planar array (UPA) are considered. An accurate mathematical model is developed for the spatial frequency response of the sounder that incorporates the non-ideal cross-polar beampatterns for the UPA elements. Due to the limited Field-of-View (FoV) of each element, the model is extended to accommodate multi-FoV measurements in distinct azimuth directions. A beamspace representation of the spatial frequency response is leveraged to develop three progressively complex algorithms aimed at solving the singlesnapshot maximum likelihood estimation problem: greedy matching pursuit (CLEAN), space-alternative generalized expectationmaximization (SAGE), and RiMAX. The first two are based on purely specular MPCs whereas RiMAX also accommodates diffuse MPCs. Two approaches for performance evaluation are proposed, one with knowledge of ground truth parameters, and one based on reconstruction mean-squared error. The three algorithms are compared through a demanding channel model with hundreds of MPCs and through real measurements. The results demonstrate that CLEAN gives quite reasonable estimates which are improved by SAGE and RiMAX. Lessons learned and directions for future research are discussed.

eess.SP↗

arXiv2021

A Framework for Developing Algorithms for Estimating Propagation Parameters from Measurements

A framework is proposed for developing and evaluating algorithms for extracting multipath propagation components (MPCs) from measurements collected by sounders at millimeter-wave (mmW) frequencies. To focus on algorithmic performance, an idealized model is proposed for the spatial frequency response of the propagation environment measured by a sounder. The input to the sounder model is a pre-determined set of MPC parameters that serve as the "ground truth." A three-dimensional angle-delay (beamspace) representation of the measured spatial frequency response serves as a natural domain for implementing and analyzing MPC extraction algorithms. Metrics for quantifying the error in estimated MPC parameters are introduced. Initial results are presented for a greedy matching pursuit algorithm that performs a least-squares (LS) reconstruction of the MPC path gains within the iterations. The results indicate that the simple greedy-LS algorithm has the ability to extract MPCs over a large dynamic range, and suggest several avenues for further performance improvement through extensions of the greedy-LS algorithm as well as by incorporating features of other algorithms, such as SAGE and RIMAX.

cs.IT↗

arXiv2019

Enable Super-resolution Parameter Estimation for Mm-wave Channel Sounding

This paper investigates the capability of millimeter-wave (mmWave) channel sounders with phased arrays to perform super-resolution parameter estimation, i.e., determine the parameters of multipath components (MPC), such as direction of arrival and delay, with resolution better than the Fourier resolution of the setup. We analyze the question both generally, and with respect to a particular novel multi-beam mmWave channel sounder that is capable of performing multiple-input-multiple-output (MIMO) measurements in dynamic environments. We firstly propose a novel two-step calibration procedure that provides higher-accuracy calibration data that are required for Rimax or SAGE. Secondly, we investigate the impact of center misalignment and residual phase noise on the performance of the parameter estimator. Finally we experimentally verify the calibration results and demonstrate the capability of our sounder to perform super-resolution parameter estimation.

cs.IT↗