arXiv subjects

Ping Zhong

Publications and source records attributed to Ping Zhong.

At least 19 recordsLinked to original sources

arXiv2026

From Uncertainty to Determinism: Coarse-to-Fine Visual Floorplan Localization without Ray Matching

Visual Floorplan Localization (FLoc) has emerged as a promising solution for indoor localization by matching egocentric images against minimalist structural maps. However, due to cross-modal information asymmetry and repetitive indoor layouts, visual FLoc is fundamentally challenged by multimodal pose distributions, where visually identical observations map to distinct, spatially separated locations. Existing ray-matching-based methods tackle this by explicitly predicting sparse geometric or semantic rays, which inherently incur information loss and demand resource-intensive preprocessing alongside exhaustive matching during inference. In this paper, we bypass the intermediate ray-matching paradigm and propose a coarse-to-fine visual FLoc framework that progresses from uncertainty to determinism. In the coarse stage, we design an image-conditioned pose diffusion model to parameterize the continuous multimodal pose distribution, effectively routing stochastically initialized pose particles toward distinct candidate modes. In the refinement stage, we propose a localized refiner that predicts bounded sub-meter pose residuals from candidate-centered floorplan crops, where structural ambiguities are largely eliminated. Our method effectively balances global multi-hypothesis tracking and local sub-meter refinement without requiring any offline map preprocessing or test-time lookup tables. Comprehensive results on the S3D (full) and ZInD benchmarks demonstrate that our approach achieves state-of-the-art accuracy and robustness.

cs.RO↗

arXiv2026

FloAff-Kitchen: Bridging Navigation and Manipulation via Canonical and Progressive Floor Affordance Learning

Mobile manipulation requires robots to identify Floor Affordance (FloAff) that maximizes downstream manipulation success rather than merely ensuring navigation feasibility. FloAff prediction is a target-conditioned local spatial reasoning problem, yet existing methods suffer from representation ambiguity caused by irrelevant spatial context and arbitrary object orientations, while entangling shared and task-specific knowledge across heterogeneous manipulation skills. To address these challenges, we propose a unified framework for FloAff prediction from egocentric multimodal perception, consisting of canonical representation learning and progressive affordance prior learning. Specifically, we introduce a Canonical Floor Affordance Representation (CFAR), which learns canonical interaction geometry by preserving affordance-relevant local structure while eliminating nuisance spatial variations unrelated to robot base placement. We further propose Progressive Floor Affordance Learning (PFAL), which learns transferable FloAff priors from a foundation manipulation task and progressively adapts them to heterogeneous downstream manipulation skills. To facilitate systematic evaluation, we establish the first cross-scene, multi-view FloAff-Kitchen benchmark covering diverse manipulation skills, scene layouts, furniture styles, and viewpoints. Extensive experiments on three benchmark settings demonstrate that our method consistently outperforms strong baselines, while ablation studies validate the contribution of each proposed component. Project page: https://csu-hero-lab.github.io/FloAff-Kitchen_Web/

cs.RO↗

arXiv2026

BMCR: Adaptive Backbone Module Composition via Reinforcement Learning for Remote Sensing Object Detection

In remote sensing object detection, Convolutional Neural Networks (CNNs) excel at capturing local details while Vision Transformers (ViTs) are better at global context modeling. However, existing detectors typically rely on a single fixed backbone or a manually designed hybrid architecture, and thus fail to adaptively exploit these complementary strengths across inputs of diverse complexity. To address this limitation, we propose Backbone Module Composition via Reinforcement Learning (BMCR). BMCR dynamically assembles input-adaptive inference paths from reusable modules decomposed from off-the-shelf CNN and ViT backbones. To enable such cross-family composition, we first construct an extensible module toolbox. Specifically, we decompose representative CNN and ViT backbones into reusable functional modules and encapsulate each module with explicit structural, semantic, and computational metadata for compatibility-aware assembly. To bridge the gap between grid-based CNN features and token-based ViT representations, we design a lightweight Optimal Transport (OT) based transition interface that ensures distribution-aware alignment while respecting spatial consistency. The backbone composition process is then formulated as a sequential decision problem, in which a policy network progressively selects task-relevant modules according to intermediate multi-scale observations. To stabilize the joint optimization of reusable modules and the routing policy, we further develop an Adaptive Module Cooperative Optimization (AMCO) strategy that coordinates module updating, routing exploration, and reward assignment during training. On DOTA-v1.0, DOTA-v1.5 and DIOR-R, BMCR achieves 79.31\%, 73.41\% and 71.86\% mAP, respectively, surpassing strong static and dynamic baselines by up to 2.5 points while maintaining competitive efficiency.

cs.CV↗

arXiv2026

TAE: Target-aware enhancer for nighttime UAV tracking

Severe image degradation under low-light nighttime conditions constitutes a core bottleneck preventing all-day applications for UAV-based single object tracking. Existing image enhancement methods often struggle to distinguish between target and background regions, which can easily lead to amplified background noise or compromise target features. To overcome this limitation, we propose TAE, a target-aware low-light enhancement framework tailored for nighttime object tracking. Guided explicitly by weak supervisory signals from tracking bounding boxes, the framework performs region-aware enhancement to ensure operations focus on the target area. It further adopts an adaptive RGB multi-curve fusion mechanism to achieve refined modeling and adaptive adjustment across different regions. To facilitate research in this domain, we also contribute DarkSOT, a new benchmark for nighttime UAV tracking, comprising 268 sequences across 9 target categories. Experimental results on the DarkSOT and UAVDark135 demonstrate that TAE significantly improves tracking performance in low-light nighttime scenarios, exhibiting strong robustness and generalization. The DarkSOT dataset is available at https://github.com/Fu0511/DarkSOT-Dataset.

cs.CV↗

arXiv2026

Freely infinitely divisible $R$-diagonal elements and Brown measure

We study freely infinitely divisible $R$-diagonal elements in the unbounded setting and Brown measures for free additive perturbations by such elements. This class includes circular elements, circular Cauchy elements, and other previously studied $R$-diagonal models. We construct examples and prove stability under several algebraic operations, including homogeneous noncommutative polynomials in bounded, freely independent elements from this class. Using results for general $R$-diagonal perturbations, together with several analytic estimates specific to freely infinitely divisible $R$-diagonal elements, we prove that, in the bounded case, the support of the Brown measure coincides with the spectrum, and we obtain a criterion for property (H) in this non-normal setting. Finally, we study the free convolution semigroup associated with the symmetrized law of the modulus and derive a Hamilton--Jacobi equation for the regularized logarithmic potential.

math.OA↗

arXiv2026

Spatially Generalizable Mobile Manipulation via Adaptive Experience Selection and Dynamic Imagination

Mobile Manipulation (MM) involves long-horizon decision-making over multi-stage compositions of heterogeneous skills, such as navigation and picking up objects. Despite recent progress, existing MM methods still face two key limitations: (i) low sample efficiency, due to ineffective use of redundant data generated during long-term MM interactions; and (ii) poor spatial generalization, as policies trained on specific tasks struggle to transfer to new spatial layouts without additional training. In this paper, we address these challenges through Adaptive Experience Selection (AES) and model-based dynamic imagination. In particular, AES makes MM agents pay more attention to critical experience fragments in long trajectories that affect task success, improving skill chain learning and mitigating skill forgetting. Based on AES, a Recurrent State-Space Model (RSSM) is introduced for Model-Predictive Forward Planning (MPFP) by capturing the coupled dynamics between the mobile base and the manipulator and imagining the dynamics of future manipulations. RSSM-based MPFP can reinforce MM skill learning on the current task while enabling effective generalization to new spatial layouts. Comparative studies across different experimental configurations demonstrate that our method significantly outperforms existing MM policies. Real-world experiments further validate the feasibility and practicality of our method.

cs.RO↗

arXiv2026

DisCo-FLoc: Semantic-Free Floorplan Localization via $SE(2)$-Aware Contrastive Disambiguation

Visual Floorplan Localization (FLoc) struggles with severe structural aliasing caused by repetitive minimalist layouts. This occurs because physically distant poses share highly similar visual-geometric features, which degrades spatial separability and angular discriminability. While existing methods attempt to mitigate these ambiguities by relying on costly semantic annotations, the resulting performance gains remain inherently limited. To address the above issues, we propose DisCo-FLoc, a semantic-free method for visual-geometric Contrastive Disambiguation. First, we introduce a depth-aware Ray Regression Predictor (RRP) that serves as a dense-to-ray geometric projector. By explicitly suppressing visual clutter along the vertical dimension, RRP projects monocular RGB images into 2D ray primitives, which are matched with floorplans to produce geometry-aware FLoc candidates. Second, to resolve the remaining ambiguity among these candidates, we propose a spatially perturbed contrastive objective to align RGB images with local floorplan structures and formulate a visual-geometric compatibility function. In particular, we meticulously construct positive and negative samples at both positional and directional levels through $SE(2)$ pose perturbations for contrastive learning, effectively achieving pose smoothness, spatial separability, and angular discriminability. The compatibility function enables DisCo-FLoc to disambiguate FLoc by using richer visual context beyond pure geometric layouts, without requiring any semantic annotations. Extensive experiments on two challenging visual FLoc benchmarks demonstrate that DisCo-FLoc significantly outperforms state-of-the-art semantic-based methods, especially narrowing the performance gap between positional and directional FLoc accuracy.

cs.RO↗

arXiv2025

On the Brown measure of $x + i y$, with $x,y$ selfadjoint and $y$ free Poisson

Let $x,y$ be freely independent selfadjoint elements in a $W^{*}$-probability space, where $y$ has free Poisson distribution of parameter $p$. We pursue a methodology for computing the Brown measure of $x + i y$, which relies on the matrix-valued subordination function $\Omega$ of the hermitization of $x + i y$, and on the fact that $\Omega$ has an explicitly described left inverse $H$. Our main point is that the Brown measure of $x + i y$ becomes more approachable when it is reparametrized via a certain change of variable $h : \mathcal{D} \to \mathcal{M}$, with $\mathcal{D}, \mathcal{M}$ open subsets of $\mathbb{C}$, where $\\mathcal{D}$ and $h$ are defined in terms of the aforementioned left inverse $H$, and $\mathrm{cl} \,(\mathcal{M})$ contains the support of the absolutely continuous part of Brown measure. More precisely, we find (with some conditions on the distribution of $x$) the following formula: \[ f(s + i \, t) =\frac{1}{2 \pi}\left[\frac{1}{t}\left(\frac{\partial \alpha}{\partial s} +\frac{\partial \beta}{\partial t}\right)-\frac{1}{t}-\frac{\beta}{t^2}\right], \ \ s + i \, t \in \mathcal{M}, \] where $f$ is the density of the absolutely continuous part of the Brown measure and the functions $\alpha, \beta : \mathcal{M} \to \mathbb{R}$ are the real and respectively the imaginary part of $h^{-1}$. We show that if $x$ has an atom $\alpha$ with $\mu_x(\alpha)>p$, then the Brown measure of $x+iy$ has an atom of mass $\mu_x(\alpha)-p$ at the same point $\alpha$. Moreover we prove that if $\alpha_1,\ldots,\alpha_k$ is the list of atoms of $x$ with mass bigger than $p$, then the Brown measure of $x+iy$ is supported on $\mathrm{cl}(\mathcal{M})\cup\{\alpha_1,\ldots,\alpha_k\}$.

math.OA↗

arXiv2025

Fusion Meets Diverse Conditions: A High-diversity Benchmark and Baseline for UAV-based Multimodal Object Detection with Condition Cues

Unmanned aerial vehicles (UAV)-based object detection with visible (RGB) and infrared (IR) images facilitates robust around-the-clock detection, driven by advancements in deep learning techniques and the availability of high-quality dataset. However, the existing dataset struggles to fully capture real-world complexity for limited imaging conditions. To this end, we introduce a high-diversity dataset ATR-UMOD covering varying scenarios, spanning altitudes from 80m to 300m, angles from 0{\deg} to 75{\deg}, and all-day, all-year time variations in rich weather and illumination conditions. Moreover, each RGB-IR image pair is annotated with 6 condition attributes, offering valuable high-level contextual information. To meet the challenge raised by such diverse conditions, we propose a novel prompt-guided condition-aware dynamic fusion (PCDF) to adaptively reassign multimodal contributions by leveraging annotated condition cues. By encoding imaging conditions as text prompts, PCDF effectively models the relationship between conditions and multimodal contributions through a task-specific soft-gating transformation. A prompt-guided condition-decoupling module further ensures the availability in practice without condition annotations. Experiments on ATR-UMOD dataset reveal the effectiveness of PCDF.

cs.CV↗

arXiv2025

EditMF: Drawing an Invisible Fingerprint for Your Large Language Models

Training large language models (LLMs) is resource-intensive and expensive, making protecting intellectual property (IP) for LLMs crucial. Recently, embedding fingerprints into LLMs has emerged as a prevalent method for establishing model ownership. However, existing back-door-based methods suffer from limited stealth and efficiency. To simultaneously address these issues, we propose EditMF, a training-free fingerprinting paradigm that achieves highly imperceptible fingerprint embedding with minimal computational overhead. Ownership bits are mapped to compact, semantically coherent triples drawn from an encrypted artificial knowledge base (e.g., virtual author-novel-protagonist facts). Causal tracing localizes the minimal set of layers influencing each triple, and a zero-space update injects the fingerprint without perturbing unrelated knowledge. Verification requires only a single black-box query and succeeds when the model returns the exact pre-embedded protagonist. Empirical results on LLaMA and Qwen families show that EditMF combines high imperceptibility with negligible model's performance loss, while delivering robustness far beyond LoRA-based fingerprinting and approaching that of SFT embeddings. Extensive experiments demonstrate that EditMF is an effective and low-overhead solution for secure LLM ownership verification.

cs.CR↗

arXiv2025

Perspective from a Broader Context: Can Room Style Knowledge Help Visual Floorplan Localization?

Since a building's floorplan remains consistent over time and is inherently robust to changes in visual appearance, visual Floorplan Localization (FLoc) has received increasing attention from researchers. However, as a compact and minimalist representation of the building's layout, floorplans contain many repetitive structures (e.g., hallways and corners), thus easily result in ambiguous localization. Existing methods either pin their hopes on matching 2D structural cues in floorplans or rely on 3D geometry-constrained visual pre-trainings, ignoring the richer contextual information provided by visual images. In this paper, we suggest using broader visual scene context to empower FLoc algorithms with scene layout priors to eliminate localization uncertainty. In particular, we propose an unsupervised learning technique with clustering constraints to pre-train a room discriminator on self-collected unlabeled room images. Such a discriminator can empirically extract the hidden room type of the observed image and distinguish it from other room types. By injecting the scene context information summarized by the discriminator into an FLoc algorithm, the room style knowledge is effectively exploited to guide definite visual FLoc. We conducted sufficient comparative studies on two standard visual Floc benchmarks. Our experiments show that our approach outperforms state-of-the-art methods and achieves significant improvements in robustness and accuracy.

cs.CV↗

arXiv2025

Recursive Visual Imagination and Adaptive Linguistic Grounding for Vision Language Navigation

Vision Language Navigation (VLN) typically requires agents to navigate to specified objects or remote regions in unknown scenes by obeying linguistic commands. Such tasks require organizing historical visual observations for linguistic grounding, which is critical for long-sequence navigational decisions. However, current agents suffer from overly detailed scene representation and ambiguous vision-language alignment, which weaken their comprehension of navigation-friendly high-level scene priors and easily lead to behaviors that violate linguistic commands. To tackle these issues, we propose a navigation policy by recursively summarizing along-the-way visual perceptions, which are adaptively aligned with commands to enhance linguistic grounding. In particular, by structurally modeling historical trajectories as compact neural grids, several Recursive Visual Imagination (RVI) techniques are proposed to motivate agents to focus on the regularity of visual transitions and semantic scene layouts, instead of dealing with misleading geometric details. Then, an Adaptive Linguistic Grounding (ALG) technique is proposed to align the learned situational memories with different linguistic components purposefully. Such fine-grained semantic matching facilitates the accurate anticipation of navigation actions and progress. Our navigation policy outperforms the state-of-the-art methods on the challenging VLN-CE and ObjectNav tasks, showing the superiority of our RVI and ALG techniques for VLN.

cs.CV↗

arXiv2025

ATR-UMMIM: A Benchmark Dataset for UAV-Based Multimodal Image Registration under Complex Imaging Conditions

Multimodal fusion has become a key enabler for UAV-based object detection, as each modality provides complementary cues for robust feature extraction. However, due to significant differences in resolution, field of view, and sensing characteristics across modalities, accurate registration is a prerequisite before fusion. Despite its importance, there is currently no publicly available benchmark specifically designed for multimodal registration in UAV-based aerial scenarios, which severely limits the development and evaluation of advanced registration methods under real-world conditions. To bridge this gap, we present ATR-UMMIM, the first benchmark dataset specifically tailored for multimodal image registration in UAV-based applications. This dataset includes 7,969 triplets of raw visible, infrared, and precisely registered visible images captured covers diverse scenarios including flight altitudes from 80m to 300m, camera angles from 0{\deg} to 75{\deg}, and all-day, all-year temporal variations under rich weather and illumination conditions. To ensure high registration quality, we design a semi-automated annotation pipeline to introduce reliable pixel-level ground truth to each triplet. In addition, each triplet is annotated with six imaging condition attributes, enabling benchmarking of registration robustness under real-world deployment settings. To further support downstream tasks, we provide object-level annotations on all registered images, covering 11 object categories with 77,753 visible and 78,409 infrared bounding boxes. We believe ATR-UMMIM will serve as a foundational benchmark for advancing multimodal registration, fusion, and perception in real-world UAV scenarios. The datatset can be download from https://github.com/supercpy/ATR-UMMIM

cs.CV↗

arXiv2025

Perspective from a Higher Dimension: Can 3D Geometric Priors Help Visual Floorplan Localization?

Since a building's floorplans are easily accessible, consistent over time, and inherently robust to changes in visual appearance, self-localization within the floorplan has attracted researchers' interest. However, since floorplans are minimalist representations of a building's structure, modal and geometric differences between visual perceptions and floorplans pose challenges to this task. While existing methods cleverly utilize 2D geometric features and pose filters to achieve promising performance, they fail to address the localization errors caused by frequent visual changes and view occlusions due to variously shaped 3D objects. To tackle these issues, this paper views the 2D Floorplan Localization (FLoc) problem from a higher dimension by injecting 3D geometric priors into the visual FLoc algorithm. For the 3D geometric prior modeling, we first model geometrically aware view invariance using multi-view constraints, i.e., leveraging imaging geometric principles to provide matching constraints between multiple images that see the same points. Then, we further model the view-scene aligned geometric priors, enhancing the cross-modal geometry-color correspondences by associating the scene's surface reconstruction with the RGB frames of the sequence. Both 3D priors are modeled through self-supervised contrastive learning, thus no additional geometric or semantic annotations are required. These 3D priors summarized in extensive realistic scenes bridge the modal gap while improving localization success without increasing the computational burden on the FLoc algorithm. Sufficient comparative studies demonstrate that our method significantly outperforms state-of-the-art methods and substantially boosts the FLoc accuracy. All data and code will be released after the anonymous review.

cs.CV↗

arXiv2025

Nearshore Underwater Target Detection Meets UAV-borne Hyperspectral Remote Sensing: A Novel Hybrid-level Contrastive Learning Framework and Benchmark Dataset

UAV-borne hyperspectral remote sensing has emerged as a promising approach for underwater target detection (UTD). However, its effectiveness is hindered by spectral distortions in nearshore environments, which compromise the accuracy of traditional hyperspectral UTD (HUTD) methods that rely on bathymetric model. These distortions lead to significant uncertainty in target and background spectra, challenging the detection process. To address this, we propose the Hyperspectral Underwater Contrastive Learning Network (HUCLNet), a novel framework that integrates contrastive learning with a self-paced learning paradigm for robust HUTD in nearshore regions. HUCLNet extracts discriminative features from distorted hyperspectral data through contrastive learning, while the self-paced learning strategy selectively prioritizes the most informative samples. Additionally, a reliability-guided clustering strategy enhances the robustness of learned representations.To evaluate the method effectiveness, we conduct a novel nearshore HUTD benchmark dataset, ATR2-HUTD, covering three diverse scenarios with varying water types and turbidity, and target types. Extensive experiments demonstrate that HUCLNet significantly outperforms state-of-the-art methods. The dataset and code will be publicly available at: https://github.com/qjh1996/HUTD

cs.CV↗

arXiv2025

Outlier eigenvalues for full rank deformed single ring random matrices

Let $A_n$ be an $n \times n$ deterministic matrix and $\Sigma_n$ be a deterministic non-negative matrix such that $A_n$ and $\Sigma_n$ converge in $*$-moments to operators $a$ and $\Sigma$ respectively in some $W^*$-probability space. We consider the full rank deformed model $A_n + U_n \Sigma_n V_n,$ where $U_n$ and $V_n$ are independent Haar-distributed random unitary matrices. In this paper, we investigate the eigenvalues of $A_n + U_n\Sigma_n V_n$ in two domains that are outside the support of the Brown measure of $a +u \Sigma$. We give a sufficient condition to guarantee that outliers are stable in one domain, and we also prove that there are no outliers in the other domain. When $A_n$ has a bounded rank, the first domain is exactly the one outside the outer boundary of the single ring, and the second domain is the inner disk of the single ring. Our results generalize the results of Benaych-Georges and Rochet (Probab. Theory Relat. Fields, 2016).

math.PR↗

arXiv2025

Environment-Driven Online LiDAR-Camera Extrinsic Calibration

LiDAR-camera extrinsic calibration (LCEC) is crucial for multi-modal data fusion in autonomous robotic systems. Existing methods, whether target-based or target-free, typically rely on customized calibration targets or fixed scene types, which limit their applicability in real-world scenarios. To address these challenges, we present EdO-LCEC, the first environment-driven online calibration approach. Unlike traditional target-free methods, EdO-LCEC employs a generalizable scene discriminator to estimate the feature density of the application environment. Guided by this feature density, EdO-LCEC extracts LiDAR intensity and depth features from varying perspectives to achieve higher calibration accuracy. To overcome the challenges of cross-modal feature matching between LiDAR and camera, we introduce dual-path correspondence matching (DPCM), which leverages both structural and textural consistency for reliable 3D-2D correspondences. Furthermore, we formulate the calibration process as a joint optimization problem that integrates global constraints across multiple views and scenes, thereby enhancing overall accuracy. Extensive experiments on real-world datasets demonstrate that EdO-LCEC outperforms state-of-the-art methods, particularly in scenarios involving sparse point clouds or partially overlapping sensor views.

cs.CV↗

arXiv2024

Lighten CARAFE: Dynamic Lightweight Upsampling with Guided Reassemble Kernels

As a fundamental operation in modern machine vision models, feature upsampling has been widely used and investigated in the literatures. An ideal upsampling operation should be lightweight, with low computational complexity. That is, it can not only improve the overall performance but also not affect the model complexity. Content-aware Reassembly of Features (CARAFE) is a well-designed learnable operation to achieve feature upsampling. Albeit encouraging performance achieved, this method requires generating large-scale kernels, which brings a mass of extra redundant parameters, and inherently has limited scalability. To this end, we propose a lightweight upsampling operation, termed Dynamic Lightweight Upsampling (DLU) in this paper. In particular, it first constructs a small-scale source kernel space, and then samples the large-scale kernels from the kernel space by introducing learnable guidance offsets, hence avoiding introducing a large collection of trainable parameters in upsampling. Experiments on several mainstream vision tasks show that our DLU achieves comparable and even better performance to the original CARAFE, but with much lower complexity, e.g., DLU requires 91% fewer parameters and at least 63% fewer FLOPs (Floating Point Operations) than CARAFE in the case of 16x upsampling, but outperforms the CARAFE by 0.3% mAP in object detection. Code is available at https://github.com/Fu0511/Dynamic-Lightweight-Upsampling.

cs.CV↗