arXiv subjects

Chunxiang Wang

Publications and source records attributed to Chunxiang Wang.

At least 19 recordsLinked to original sources

arXiv2026

LOGOS: LiDAR-Only Gaussian Elevation Splatting for Unified Tiny Obstacle Segmentation

Robust obstacle segmentation is essential for the safety of intelligent robots, where LiDAR-based perception systems play a fundamental role in the robot-environment interaction. While extensive LiDAR-based approaches have demonstrated high performance on common obstacles in urban scenarios, their results on tiny obstacles such as curbs, gravel, and potholes remain unsatisfactory due to the significant similarity between tiny obstacles and inherent road undulations. Moreover, their segmentation accuracy even deteriorates sharply when the LiDAR scans suffer from degradation in challenging off-road scenes. To overcome these bottlenecks, we propose LOGOS, a LiDAR-only unified tiny obstacle segmentation system, which models the road surface as a continuous mixture of 2D Gaussian primitives and distinguishes tiny obstacles via high-presicion elevation estimation. Unlike existing Gaussian splatting methods that rely on iterative RGB training, LOGOS is a backpropagation-free LiDAR-only approach. It directly estimates Gaussian parameters via a freespace-aware initialization by incrementally pruning non-road primitives using smoothness constraints. Subsequently, pointwise signed distances are computed via a novel normal-aware elevation splatting function, ensuring robustness to both flat and sloped terrains. We evaluate LOGOS on a highly heterogeneous benchmark of point cloud frames collected from urban mobility scenarios and mining haulage off-road environments. These data are practically acquired using different LiDAR sensors and exhibit large variations in point density, terrain roughness, and obstacle types. Experiments on the road and off-road scenes demonstrate that LOGOS significantly outperforms other state-of-the-art methods, particularly in degraded point cloud regions and challenging off-road scenarios, while maintaining real-time efficiency.

cs.RO↗

arXiv2026

Generating Roadside LiDAR Datasets from Vehicle-Side Datasets via Novel View Synthesis

Intelligent Transportation Systems (ITS) require reliable environmental perception to support safe and efficient transportation. With the rapid development of Vehicle-to-everything (V2X), roadside perception has become an effective means to extend sensing coverage and improve traffic safety. However, the scarcity of large-scale annotated roadside LiDAR datasets poses a major challenge for training high-performance roadside perception models. In this paper, we introduce Vehicle-to-Roadside LiDAR Synthesis (VRS), a data synthesis framework that generates labeled roadside LiDAR datasets from vehicle-side datasets via LiDAR novel view synthesis. To mitigate the vehicle-to-roadside domain gap, VRS employs vehicle point cloud completion to compensate for missing geometry in vehicle-side observations, and introduces an occupancy-based visibility constraint to handle large viewpoint changes during cross-view rendering. The proposed framework enables flexible multi-view rendering for scalable roadside data generation. Extensive experiments on roadside 3D object detection demonstrate that the synthesized data effectively complements real roadside data, mitigates the limitations of limited real-world roadside data, and improves generalization to unseen roadside viewpoints.

cs.RO↗

arXiv2026

AMFD: Distillation via Adaptive Multimodal Fusion for Multispectral Pedestrian Detection

Multispectral pedestrian detection has been shown to be effective in improving performance within complex illumination scenarios. However, prevalent double-stream networks in multispectral detection employ two separate feature extraction branches for multi-modal data, leading to nearly double the inference time compared to single-stream networks utilizing only one feature extraction branch. This increased inference time has hindered the widespread employment of multispectral pedestrian detection in embedded devices for autonomous systems. To address this limitation, various knowledge distillation methods have been proposed. However, traditional distillation methods focus only on the fusion features and ignore the large amount of information in the original multi-modal features, thereby restricting the student network's performance. To tackle the challenge, we introduce the Adaptive Modal Fusion Distillation (AMFD) framework, which can fully utilize the original modal features of the teacher network. Specifically, a Modal Extraction Alignment (MEA) module is utilized to derive learning weights for student networks, integrating focal and global attention mechanisms. This methodology enables the student network to acquire optimal fusion strategies independent from that of teacher network without necessitating an additional feature fusion module. Furthermore, we present the SMOD dataset, a well-aligned challenging multispectral dataset for detection. Extensive experiments on the challenging KAIST, LLVIP and SMOD datasets are conducted to validate the effectiveness of AMFD. The results demonstrate that our method outperforms existing state-of-the-art methods in both reducing log-average Miss Rate and improving mean Average Precision. The code is available at https://github.com/bigD233/AMFD.git.

cs.CV↗

arXiv2026

RadarXFormer: Robust Object Detection via Cross-Dimension Fusion of 4D Radar Spectra and Images for Autonomous Driving

Reliable perception is essential for autonomous driving systems to operate safely under diverse real-world traffic conditions. However, camera- and LiDAR-based perception systems suffer from performance degradation under adverse weather and lighting conditions, limiting their robustness and large-scale deployment in intelligent transportation systems. Radar-vision fusion provides a promising alternative by combining the environmental robustness and cost efficiency of millimeter-wave (mmWave) radar with the rich semantic information captured by cameras. Nevertheless, conventional 3D radar measurements lack height resolution and remain highly sparse, while emerging 4D mmWave radar introduces elevation information but also brings challenges such as signal noise and large data volume. To address these issues, this paper proposes RadarXFormer, a 3D object detection framework that enables efficient cross-modal fusion between 4D radar spectra and RGB images. Instead of relying on sparse radar point clouds, RadarXFormer directly leverages raw radar spectra and constructs an efficient 3D representation that reduces data volume while preserving complete 3D spatial information. The "X" highlights the proposed cross-dimension (3D-2D) fusion mechanism, in which multi-scale 3D spherical radar feature cubes are fused with complementary 2D image feature maps. Experiments on the K-Radar dataset demonstrate improved detection accuracy and robustness under challenging conditions while maintaining real-time inference capability.

cs.CV↗

arXiv2025

Which LiDAR scanning pattern is better for roadside perception: Repetitive or Non-repetitive?

LiDAR-based roadside perception is a cornerstone of advanced Intelligent Transportation Systems (ITS). While considerable research has addressed optimal LiDAR placement for infrastructure, the profound impact of differing LiDAR scanning patterns on perceptual performance remains comparatively under-investigated. The inherent nature of various scanning modes - such as traditional repetitive (mechanical/solid-state) versus emerging non-repetitive (e.g. prism-based) systems - leads to distinct point cloud distributions at varying distances, critically dictating the efficacy of object detection and overall environmental understanding. To systematically investigate these differences in infrastructure-based contexts, we introduce the "InfraLiDARs' Benchmark," a novel dataset meticulously collected in the CARLA simulation environment using concurrently operating infrastructure-based LiDARs exhibiting both scanning paradigms. Leveraging this benchmark, we conduct a comprehensive statistical analysis of the respective LiDAR scanning abilities and evaluate the impact of these distinct patterns on the performance of various leading 3D object detection algorithms. Our findings reveal that non-repetitive scanning LiDAR and the 128-line repetitive LiDAR were found to exhibit comparable detection performance across various scenarios. Despite non-repetitive LiDAR's limited perception range, it's a cost-effective option considering its low price. Ultimately, this study provides insights for setting up roadside perception system with optimal LiDAR scanning patterns and compatible algorithms for diverse roadside applications, and publicly releases the "InfraLiDARs' Benchmark" dataset to foster further research.

cs.CV↗

arXiv2025

Bench-RNR: Dataset for Benchmarking Repetitive and Non-repetitive Scanning LiDAR for Infrastructure-based Vehicle Localization

Vehicle localization using roadside LiDARs can provide centimeter-level accuracy for cloud-controlled vehicles while simultaneously serving multiple vehicles, enhanc-ing safety and efficiency. While most existing studies rely on repetitive scanning LiDARs, non-repetitive scanning LiDAR offers advantages such as eliminating blind zones and being more cost-effective. However, its application in roadside perception and localization remains limited. To address this, we present a dataset for infrastructure-based vehicle localization, with data collected from both repetitive and non-repetitive scanning LiDARs, in order to benchmark the performance of different LiDAR scanning patterns. The dataset contains 5,445 frames of point clouds across eight vehicle trajectory sequences, with diverse trajectory types. Our experiments establish base-lines for infrastructure-based vehicle localization and compare the performance of these methods using both non-repetitive and repetitive scanning LiDARs. This work offers valuable insights for selecting the most suitable LiDAR scanning pattern for infrastruc-ture-based vehicle localization. Our dataset is a signifi-cant contribution to the scientific community, supporting advancements in infrastructure-based perception and vehicle localization. The dataset and source code are publicly available at: https://github.com/sjtu-cyberc3/BenchRNR.

cs.RO↗

arXiv2025

A Comparative Study of Halo Mass Estimates from Group Catalogs and Lensing Signals

We compare halo mass estimates from three galaxy group catalogs (redMaPPer, Yang21, and Zou21) with those derived from gravitational lensing measurements. Each catalog employs distinct methodologies, including mass-richness relations, abundance matching, and luminosity-based calibration. A linear correlation is observed between catalog-estimated and lensing-derived masses. The redMaPPer catalog shows the best agreement, especially for lower-redshift groups, with minor deviations in higher-redshift bins. Yang21 is the only catalog containing low mass groups, which gives a reasonably good mass estimation, except for the lowest mass bin. Cross-matched groups between redMaPPer and Yang21 reveal the former catalog provides more accurate mass estimation, while the Yang21 makes under-estimation of halo mass for those sharing the central galaxy with redMaPPer and over-estimation of halo mass for those with different center determination with redMaPPer and for the unique Yang21 groups. These findings emphasize the importance of redshift-dependent calibration and refined group definitions for accurate mass estimation.

astro-ph.CO↗

arXiv2025

Weather-Magician: Reconstruction and Rendering Framework for 4D Weather Synthesis In Real Time

For tasks such as urban digital twins, VR/AR/game scene design, or creating synthetic films, the traditional industrial approach often involves manually modeling scenes and using various rendering engines to complete the rendering process. This approach typically requires high labor costs and hardware demands, and can result in poor quality when replicating complex real-world scenes. A more efficient approach is to use data from captured real-world scenes, then apply reconstruction and rendering algorithms to quickly recreate the authentic scene. However, current algorithms are unable to effectively reconstruct and render real-world weather effects. To address this, we propose a framework based on gaussian splatting, that can reconstruct real scenes and render them under synthesized 4D weather effects. Our work can simulate various common weather effects by applying Gaussians modeling and rendering techniques. It supports continuous dynamic weather changes and can easily control the details of the effects. Additionally, our work has low hardware requirements and achieves real-time rendering performance. The result demos can be accessed on our project homepage: weathermagician.github.io

cs.CV↗

arXiv2025

From Imitation to Exploration: End-to-end Autonomous Driving based on World Model

In recent years, end-to-end autonomous driving architectures have gained increasing attention due to their advantage in avoiding error accumulation. Most existing end-to-end autonomous driving methods are based on Imitation Learning (IL), which can quickly derive driving strategies by mimicking expert behaviors. However, IL often struggles to handle scenarios outside the training dataset, especially in high-dynamic and interaction-intensive traffic environments. In contrast, Reinforcement Learning (RL)-based driving models can optimize driving decisions through interaction with the environment, improving adaptability and robustness. To leverage the strengths of both IL and RL, we propose RAMBLE, an end-to-end world model-based RL method for driving decision-making. RAMBLE extracts environmental context information from RGB images and LiDAR data through an asymmetrical variational autoencoder. A transformer-based architecture is then used to capture the dynamic transitions of traffic participants. Next, an actor-critic structure reinforcement learning algorithm is applied to derive driving strategies based on the latent features of the current state and dynamics. To accelerate policy convergence and ensure stable training, we introduce a training scheme that initializes the policy network using IL, and employs KL loss and soft update mechanisms to smoothly transition the model from IL to RL. RAMBLE achieves state-of-the-art performance in route completion rate on the CARLA Leaderboard 1.0 and completes all 38 scenarios on the CARLA Leaderboard 2.0, demonstrating its effectiveness in handling complex and dynamic traffic scenarios. The model will be open-sourced upon paper acceptance at https://github.com/SCP-CN-001/ramble to support further research and development in autonomous driving.

cs.AI↗

arXiv2025

HOPE: A Reinforcement Learning-based Hybrid Policy Path Planner for Diverse Parking Scenarios

Automated parking stands as a highly anticipated application of autonomous driving technology. However, existing path planning methodologies fall short of addressing this need due to their incapability to handle the diverse and complex parking scenarios in reality. While non-learning methods provide reliable planning results, they are vulnerable to intricate occasions, whereas learning-based ones are good at exploration but unstable in converging to feasible solutions. To leverage the strengths of both approaches, we introduce Hybrid pOlicy Path plannEr (HOPE). This novel solution integrates a reinforcement learning agent with Reeds-Shepp curves, enabling effective planning across diverse scenarios. HOPE guides the exploration of the reinforcement learning agent by applying an action mask mechanism and employs a transformer to integrate the perceived environmental information with the mask. To facilitate the training and evaluation of the proposed planner, we propose a criterion for categorizing the difficulty level of parking scenarios based on space and obstacle distribution. Experimental results demonstrate that our approach outperforms typical rule-based algorithms and traditional reinforcement learning methods, showing higher planning success rates and generalization across various scenarios. We also conduct real-world experiments to verify the practicability of HOPE. The code for our solution is openly available on https://github.com/jiamiya/HOPE.

cs.RO↗

arXiv2025

Depth-aware Fusion Method based on Image and 4D Radar Spectrum for 3D Object Detection

Safety and reliability are crucial for the public acceptance of autonomous driving. To ensure accurate and reliable environmental perception, intelligent vehicles must exhibit accuracy and robustness in various environments. Millimeter-wave radar, known for its high penetration capability, can operate effectively in adverse weather conditions such as rain, snow, and fog. Traditional 3D millimeter-wave radars can only provide range, Doppler, and azimuth information for objects. Although the recent emergence of 4D millimeter-wave radars has added elevation resolution, the radar point clouds remain sparse due to Constant False Alarm Rate (CFAR) operations. In contrast, cameras offer rich semantic details but are sensitive to lighting and weather conditions. Hence, this paper leverages these two highly complementary and cost-effective sensors, 4D millimeter-wave radar and camera. By integrating 4D radar spectra with depth-aware camera images and employing attention mechanisms, we fuse texture-rich images with depth-rich radar data in the Bird's Eye View (BEV) perspective, enhancing 3D object detection. Additionally, we propose using GAN-based networks to generate depth images from radar spectra in the absence of depth sensors, further improving detection accuracy.

cs.CV↗

arXiv2024

Cross-Modal Visual Relocalization in Prior LiDAR Maps Utilizing Intensity Textures

Cross-modal localization has drawn increasing attention in recent years, while the visual relocalization in prior LiDAR maps is less studied. Related methods usually suffer from inconsistency between the 2D texture and 3D geometry, neglecting the intensity features in the LiDAR point cloud. In this paper, we propose a cross-modal visual relocalization system in prior LiDAR maps utilizing intensity textures, which consists of three main modules: map projection, coarse retrieval, and fine relocalization. In the map projection module, we construct the database of intensity channel map images leveraging the dense characteristic of panoramic projection. The coarse retrieval module retrieves the top-K most similar map images to the query image from the database, and retains the top-K' results by covisibility clustering. The fine relocalization module applies a two-stage 2D-3D association and a covisibility inlier selection method to obtain robust correspondences for 6DoF pose estimation. The experimental results on our self-collected datasets demonstrate the effectiveness in both place recognition and pose estimation tasks.

cs.CV↗

arXiv2024

SS-ADA: A Semi-Supervised Active Domain Adaptation Framework for Semantic Segmentation

Semantic segmentation plays an important role in intelligent vehicles, providing pixel-level semantic information about the environment. However, the labeling budget is expensive and time-consuming when semantic segmentation model is applied to new driving scenarios. To reduce the costs, semi-supervised semantic segmentation methods have been proposed to leverage large quantities of unlabeled images. Despite this, their performance still falls short of the accuracy required for practical applications, which is typically achieved by supervised learning. A significant shortcoming is that they typically select unlabeled images for annotation randomly, neglecting the assessment of sample value for model training. In this paper, we propose a novel semi-supervised active domain adaptation (SS-ADA) framework for semantic segmentation that employs an image-level acquisition strategy. SS-ADA integrates active learning into semi-supervised semantic segmentation to achieve the accuracy of supervised learning with a limited amount of labeled data from the target domain. Additionally, we design an IoU-based class weighting strategy to alleviate the class imbalance problem using annotations from active learning. We conducted extensive experiments on synthetic-to-real and real-to-real domain adaptation settings. The results demonstrate the effectiveness of our method. SS-ADA can achieve or even surpass the accuracy of its supervised learning counterpart with only 25% of the target labeled data when using a real-time segmentation model. The code for SS-ADA is available at https://github.com/ywher/SS-ADA.

cs.CV↗

arXiv2024

The measurement of the splashback radius of dark matter halo

In the hierarchical evolution framework of cosmology, larger halos grow through matter accretion and halo mergers. To clarify the halo evolution, we need to define the halo mass and radius physically. However, the pseudo-evolution problem makes the process difficult. Thus, we aim to measure the splashback radius, a physically defined halo radius for a large number of halos with various mass and redshift, and to determine the most important parameters to affect it. We use the typical definition of splashback radius (Rsp) as the radius with the steepest radial density profile. In this work, we measure Rsp of dark matter halos within the mass of 1e13-3e15Msun and redshifts spanning 0.08-0.65. This is the measurement of the Rsp in the largest range of halo mass and redshift. Using the shear catalog of the DECaLS DR8, we investigate Rsp of halos associated with galaxies and galaxy clusters identified in the various catalogs. Our finding reveals a trend wherein massive halos demonstrate a larger Rsp, and the normalized splashback radius (Rsp/R200m) shows a U-shaped mass evolution. The upturn in these relations mainly comes from the contribution of massive halos with low redshifts. We further find Rsp increases with the peak height, while Rsp/R200m has a negative relation with the peak height. We also find the Rsp >~R200m for most halos, indicating their low accretion rates. Our result is consistent with previous literature across a wide range of mass, redshift, and peak height, as well as the simulation work from More et al. (2015).

astro-ph.CO↗

arXiv2024

Tactics2D: A Highly Modular and Extensible Simulator for Driving Decision-making

Simulation is a prospective method for generating diverse and realistic traffic scenarios to aid in the development of driving decision-making systems. However, existing simulators often fall short in diverse scenarios or interactive behavior models for traffic participants. This deficiency underscores the need for a flexible, reliable, user-friendly open-source simulator. Addressing this challenge, Tactics2D adopts a modular approach to traffic scenario construction, encompassing road elements, traffic regulations, behavior models, physics simulations for vehicles, and event detection mechanisms. By integrating numerous commonly utilized algorithms and configurations, Tactics2D empowers users to construct their driving scenarios effortlessly, just like assembling building blocks. Users can effectively evaluate the performance of driving decision-making models across various scenarios by leveraging both public datasets and user-collected real-world data. For access to the source code and community support, please visit the official GitHub page for Tactics2D at https://github.com/WoodOxen/Tactics2D.

cs.LG↗

arXiv2024

CURLING - I. The Influence of Point-like Image Approximation on the Outcomes of Cluster Strong Lens Modeling

Cluster-scale strong lensing is a powerful tool for exploring the properties of dark matter and constraining cosmological models. However, due to the complex parameter space, pixelized strong lens modeling in galaxy clusters is computationally expensive, leading to the point-source approximation of strongly lensed extended images, potentially introducing systematic biases. Herein, as the first paper of the ClUsteR strong Lens modelIng for the Next-Generation observations (CURLING) program, we use lensing ray-tracing simulations to quantify the biases and uncertainties arising from the point-like image approximation for JWST-like observations. Our results indicate that the approximation works well for reconstructing the total cluster mass distribution, but can bias the magnification measurements near critical curves and the constraints on the cosmological parameters, the total matter density of the Universe $Ω_{\rm m}$, and dark energy equation of state parameter $w$. To mitigate the biases, we propose incorporating the extended surface brightness distribution of lensed sources into the modeling. This approach reduces the bias in magnification from 46.2 per cent to 0.09 per cent for $μ\sim 1000$. Furthermore, the median values of cosmological parameters align more closely with the fiducial model. In addition to the improved accuracy, we also demonstrate that the constraining power can be substantially enhanced. In conclusion, it is necessary to model cluster-scale strong lenses with pixelized multiple images, especially for estimating the intrinsic luminosity of highly magnified sources and accurate cosmography in the era of high-precision observations.

astro-ph.CO↗

arXiv2024

MaNGA DynPop -- VI. Matter density slopes from dynamical models of 6000 galaxies versus cosmological simulations: the interplay between baryonic and dark matter

We try to understand the trends in the mass density slopes as a function of galaxy properties. We use the results from the best Jeans Anisotropic Modelling (JAM) of the integral-field stellar kinematics for near 6000 galaxies from the MaNGA DynPop project, with stellar masses of $10^{9-12}\ {\rm M_{\odot}}$, including both early-type and late-type galaxies. We use the mass-weighted density slopes for the stellar $\overlineγ_*$, dark $\overlineγ_{\rm DM}$, and total $\overlineγ_{\rm T}$ mass from the MaNGA DynPop project. The $\overlineγ_{\rm T}$ approaches a constant value of 2.2 for high $σ_{\rm e}$ galaxies, and flattens for lg$(σ_{\rm e}/{\rm km\ s^{-1}})\lesssim2.3$, reaching 1.5 for lg$(σ_{\rm e}/{\rm km\ s^{-1}})\approx1.8$. The total and stellar slopes track each other tightly, with $\overlineγ_{\rm T}\approx\overlineγ_*-0.174$ over the full $σ_{\rm e}$ range. This confirms the dominance of stellar matter within $R_{\rm e}$. We also show that there is no perfect conspiracy between baryonic and dark matter, as $\overlineγ_*$ and $\overlineγ_{\rm DM}$ do not vary inversely within the $σ_{\rm e}$ range. We find that the central galaxies from TNG50 and TNG100 simulations do not reproduce the observed galaxy mass distribution, which we attribute to the overestimated dark matter fraction, possibly due to a constant IMF and excessive adiabatic contraction effects in the simulations. Finally, we present the stacked dark matter density profiles and show that they are slightly steeper than the pure dark matter simulation prediction of $\overlineγ_{\rm DM}\approx1$, suggesting moderate adiabatic contraction in the central region of galaxies. Our work demonstrate the power of stellar dynamics modelling for probing the interaction between stellar and dark matter and testing galaxy formation theories.

astro-ph.GA↗

arXiv2024

Assessing Mass Loss and Stellar-to-Halo Mass Ratio of Satellite Galaxies: A Galaxy-Galaxy Lensing Approach Utilizing DECaLS DR8 Data

The galaxy-galaxy lensing technique allows us to measure the subhalo mass of satellite galaxies, studying their mass loss and evolution within galaxy clusters and providing direct observational validation for theories of galaxy formation. In this study, we use the weak gravitational lensing observations from DECaLS DR8, in combination with the redMaPPer galaxy cluster catalog from Sloan Digital Sky Survey data (SDSS) DR8 to accurately measure the dark matter halo mass of satellite galaxies. We confirm a significant increase in the stellar-to-halo mass ratio of satellite galaxies with their halo-centric radius, indicating clear evidence of mass loss due to tidal stripping. Additionally, we find that this mass loss is strongly dependent on the mass of the satellite galaxies, with satellite galaxies above $10^{11}~{\rm M_{\odot}/h}$ experiencing more pronounced mass loss compared to lower mass satellites, reaching 86\% at projected halo-centric radius $0.5R_{\rm 200c}$. The average mass loss rate, when not considering halo-centric radius, displays a U-shaped variation with stellar mass, with galaxies of approximately $4\times10^{10}~{\rm M_{\odot}/h}$ exhibiting the least mass loss, around 60\%. We compare our results with state-of-the-art hydrodynamical numerical simulations and find that the satellite galaxy stellar-to-halo mass ratio in the outskirts of galaxy clusters is higher compared to the predictions of the Illustris-TNG project about factor 5. Furthermore, the Illustris-TNG project's numerical simulations did not predict the observed dependence of satellite galaxy mass loss rate on satellite galaxy mass.

astro-ph.GA↗