arXiv subjects

Feng Qiao

Publications and source records attributed to Feng Qiao.

At least 19 recordsLinked to original sources

arXiv2026

Behavior-Skill: A Fine-Grained Benchmark for Evaluating Vision-Language-Action Policies in Long-Horizon Tasks

Reliable execution of long-horizon mobile manipulation tasks remains challenging because overall task success depends on the successful completion of multiple constituent skills. Existing benchmarks, however, still rely primarily on full-task rollouts and aggregate task-level metrics, making intermediate failures difficult to observe and analyze. We present Behavior-Skill, a benchmark that reformulates the learning and evaluation of long-horizon tasks around executable constituent skills. It contains 235,492 skill instances from 10,000 demonstrations across 50 household tasks and 34 semantic skill categories. Each instance pairs a skill instruction with an aligned observation-action segment, and is further associated with a restorable intermediate state and a skill success condition to enable independent evaluation under valid preconditions. We further introduce trajectory-level and skill-level metrics to characterize policy capability beyond aggregate task success. Extensive experiments across representative VLA policies including pi0.5 and GR00T on the complete 50-task benchmark show that failures are highly non-uniform across skills, with contact-rich manipulation skills forming persistent bottlenecks. These results demonstrate that Behavior-Skill complements full-task evaluation by exposing intermediate capability profiles for analyzing and improving long-horizon VLA policies. Behavior-Skill is publicly available at https://github.com/nubot-nudt/Behavior-Skill.

cs.RO↗

arXiv2026

Track2View: 4D-Consistent Camera-Controlled Video Generation via Paired 3D Point Tracks

Re-rendering an existing video from a novel camera viewpoint requires the output to follow the prescribed camera trajectory while preserving the appearance and dynamics of the original scene across every frame. Existing methods rely on per-frame pose embeddings, noisy point-cloud renderings, or implicit learned correspondences, none of which provides an explicit, temporally continuous link between source and target pixels. We propose Track2View, which conditions a video diffusion transformer on paired 3D point tracks: sparse trajectories of scene points projected into both the source and target camera views. These tracks provide explicit spatiotemporal correspondences that are temporally continuous by construction, encoding what content should appear where and when. At the core of Track2View is a dual-view track conditioner that transfers visual context from source to target view through parameter-free geometric operations and learned temporal aggregation, ensuring generalization to arbitrary camera trajectories without memorizing specific motions. We further introduce a data curation pipeline that extracts one-to-one track correspondences by running a 3D point tracker on temporally concatenated multi-camera view pairs. On a 400-video benchmark spanning static and dynamic scenes, Track2View achieves state-of-the-art results across visual quality, view synchronization, and camera accuracy, reducing rotation error by 30-65% and translation error by 61-72% relative to leading baselines. Project page is available at this https URL: https://qjizhi.github.io/track2view

cs.CV↗

arXiv2026

StereoGenBench: A Synthetic Multi-Camera Benchmark for Stereo Generation under Controlled Baseline Regimes

Stereo image and video generation, stereo geometry estimation, and condition-controlled view synthesis require paired data in which the variables that determine binocular geometry -- camera baseline, intrinsics, scene depth, and camera motion -- are known and controllable. Existing stereo resources provide subsets of these variables, but resources commonly used for stereo generation evaluation do not, to our knowledge, provide scene-paired, calibrated multi-baseline right-view ground truth with jointly recorded intrinsics, dense metric depth, and per-frame poses in a single controlled source. We introduce StereoGenBench, a synthetic Unreal Engine benchmark designed to make baseline-regime sensitivity and target-camera consistency measurable under matched scene content. Each scene is rendered with a rigid six-camera lateral array, yielding up to 15 calibrated view pairs; adjacent baselines are sampled from inter-pupillary to wide-baseline regimes; focal length is sampled independently; and every view is released with RGB, metric depth, intrinsics, per-pair baselines, and per-frame poses. The splits include two evaluation families for narrow and wide baseline regimes and a train-only family for broader all-pairs coverage. We release the dataset, evaluation code, reference results, Croissant metadata, and generation code/configuration for extension with compatible assets. The dataset is available at https://huggingface.co/datasets/stereo-dataset/stereo-dataset

cs.CV↗

arXiv2026

Generation of magnonic squeezed state and its superposition in a hybrid qubit-magnon system

We propose a protocol for generating magnonic squeezed states (MSS) and their superpositions (SMSS) in a hybrid system comprising a superconducting flux qubit magnetically coupled to the Kittel mode of a yttrium iron garnet (YIG) sphere. The flux qubit provides an intrinsic longitudinal interaction with the magnon mode, which, under resonant microwave driving, gives rise to an effective qubit-state-dependent squeezing Hamiltonian. Numerical simulations incorporating realistic dissipation demonstrate that magnon quadrature noise reduction exceeding $8~\mathrm{dB}$ is achievable with experimentally accessible parameters.~By preparing the qubit in a superposition state followed by projective measurement, we further obtain symmetric and antisymmetric superpositions of orthogonally squeezed magnon states exhibiting clear phase-space interference fringes.~We discuss how the fourfold rotational symmetry of these states supports a bosonic logical encoding with potential for protecting against dominant error channels in magnonic platforms.

quant-ph↗

arXiv2026

GenOpticalFlow: A Generative Approach to Unsupervised Optical Flow Learning

Optical flow estimation is a fundamental problem in computer vision, yet the reliance on expensive ground-truth annotations limits the scalability of supervised approaches. Although unsupervised and semi-supervised methods alleviate this issue, they often suffer from unreliable supervision signals based on brightness constancy and smoothness assumptions, leading to inaccurate motion estimation in complex real-world scenarios. To overcome these limitations, we introduce \textbf{\modelname}, a novel framework that synthesizes large-scale, perfectly aligned frame--flow data pairs for supervised optical flow training without human annotations. Specifically, our method leverages a pre-trained depth estimation network to generate pseudo optical flows, which serve as conditioning inputs for a next-frame generation model trained to produce high-fidelity, pixel-aligned subsequent frames. This process enables the creation of abundant, high-quality synthetic data with precise motion correspondence. Furthermore, we propose an \textit{inconsistent pixel filtering} strategy that identifies and removes unreliable pixels in generated frames, effectively enhancing fine-tuning performance on real-world datasets. Extensive experiments on KITTI2012, KITTI2015, and Sintel demonstrate that \textbf{\modelname} achieves competitive or superior results compared to existing unsupervised and semi-supervised approaches, highlighting its potential as a scalable and annotation-free solution for optical flow learning. We will release our code upon acceptance.

cs.CV↗

arXiv2026

Video Understanding: From Geometry and Semantics to Unified Models

Video understanding aims to enable models to perceive, reason about, and interact with the dynamic visual world. In contrast to image understanding, video understanding inherently requires modeling temporal dynamics and evolving visual context, placing stronger demands on spatiotemporal reasoning and making it a foundational problem in computer vision. In this survey, we present a structured overview of video understanding by organizing the literature into three complementary perspectives: low-level video geometry understanding, high-level semantic understanding, and unified video understanding models. We further highlight a broader shift from isolated, task-specific pipelines toward unified modeling paradigms that can be adapted to diverse downstream objectives, enabling a more systematic view of recent progress. By consolidating these perspectives, this survey provides a coherent map of the evolving video understanding landscape, summarizes key modeling trends and design principles, and outlines open challenges toward building robust, scalable, and unified video foundation models.

cs.CV↗

arXiv2026

PhysAlign: Physics-Coherent Image-to-Video Generation through Feature and 3D Representation Alignment

Video Diffusion Models (VDMs) offer a promising approach for simulating dynamic scenes and environments, with broad applications in robotics and media generation. However, existing models often generate temporally incoherent content that violates basic physical intuition, significantly limiting their practical applicability. We propose PhysAlign, an efficient framework for physics-coherent image-to-video (I2V) generation that explicitly addresses this limitation. To overcome the critical scarcity of physics-annotated videos, we first construct a fully controllable synthetic data generation pipeline based on rigid-body simulation, yielding a highly-curated dataset with accurate, fine-grained physics and 3D annotations. Leveraging this data, PhysAlign constructs a unified physical latent space by coupling explicit 3D geometry constraints with a Gram-based spatio-temporal relational alignment that extracts kinematic priors from video foundation models. Extensive experiments demonstrate that PhysAlign significantly outperforms existing VDMs on tasks requiring complex physical reasoning and temporal stability, without compromising zero-shot visual quality. PhysAlign shows the potential to bridge the gap between raw visual synthesis and rigid-body kinematics, establishing a practical paradigm for genuinely physics-grounded video generation. The project page is available at https://physalign.github.io/PhysAlign.

cs.CV↗

arXiv2025

Asymmetric polaron picture for the quantum Rabi model

The experimental access to ultra-strong couplings in light-matter interactions has made the quantum phase transition (QPT) in the quantum Rabi model practically relevant, while the physics of the QPT has not yet been fully explored. The polaron picture is a method capable of analyzing in the entire coupling regime and extracting the essential physics behind the QPT. However, the asymmetric deformation of polarons is missing in the current polaron picture. In the present work we propose an improved variational method in asymmetric polaron picture (APP). Our APP not only increases the method accuracy but also reveals more underlying physics concerning the QPT. We find that in the ground state both the polarons and antipolarons are asymmetrically deformed to a large extent, which leads to a richer phase diagram. We also analyze the first excited state in which we unveil an asymmetry direction reversal for the polarons and an attraction/replusion transition differently from the ground state. Finally, we apply the APP in quantum Fisher information analysis and critical coupling extraction, the improvements indicate that the polaron asymmetry makes a considerable contribution to the quantum resource in quantum metrology and plays an unnegligible role in the QPT. Our results and mechanism clarifications expose more subtle energy competitions and abundant physics, and the method potentially might have broader applications in light-matter interactions.

quant-ph↗

arXiv2025

Globalized critical quantum metrology in dynamics of quantum Rabi model by auxiliary nonlinear term

Quantum Rabi model (QRM) is a fundamental model for light-matter interactions, the finite-component quantum phase transition (QPT) in the QRM has established a paradigmatic application for critical quantum metrology (CQM). However, such a paradigmatic application is restricted to a local regime of the QPT which has only a single critical point. In this work we propose a globalized CQM in the QRM by introducing an auxiliary nonlinear term which is realizable and can extend the critical point to a continuous critical regime. As a consequence, a high measurement precision is globally available over the entire coupling regime from the original critical point of the QRM down to the weak-coupling limit, as demonstrated by the globally accessible diverging quantum Fisher information in dynamics. We illustrate a measurement scheme by quadrature dynamics, with globally criticality-enhanced inverted variance as well as the scaling relation with respect to finite frequencies. In particular, we find that the globally high measurement precisions still survive in the presence of decoherence. Our proposal paves a way to break the local limitation of QPT of the QRM in CQM and enables a broader application, with implications of applicability in realistic situation.

quant-ph↗

arXiv2025

Phonon-induced two-axis spin squeezing with decoherence reduction in hybrid spin-optomechanical system

We propose a scheme to implement Heisenberg-limited spin squeezing in a hybrid cavity optomechanical-spin system. In our system, $N$ two-level systems are coupled via Tavis-Cummings interactions to a mechanical resonator (MR) in a standard optomechanical setup. Within the dispersive coupling regime, adiabatic elimination of the optical mode induces a squeezing effect on the MR, which, in the squeezed representation, effectively transforms the collective spin operators into a Bogoliubov form. Under large detuning conditions, the phonon mode mediates interactions among the Bogoliubov collective spins, thereby enabling a two-axis twisting squeezing protocol through appropriate parameter tuning. Both theoretical analysis and numerical simulations show that in the presence of dephasing and phonon dissipation, the maximum squeezing degree asymptotically converges to a constant as $N$ increases, which implies the metrological precision asymptotically approaches the standard quantum limit without parameter optimization. Nevertheless, in parameter optimization we extract a scaling relation of the optimal squeezing which surpasses existing schemes in the literature. Moreover, the optimization also leads to a considerable reduction of the preparation time for the optimal squeezing. Our work may provide insights into dissipation effects in spin squeezing and offer a potential route for high-precision quantum metrology in many-body systems.

quant-ph↗

arXiv2025

Towards Open-World Generation of Stereo Images and Unsupervised Matching

Stereo images are fundamental to numerous applications, including extended reality (XR) devices, autonomous driving, and robotics. Unfortunately, acquiring high-quality stereo images remains challenging due to the precise calibration requirements of dual-camera setups and the complexity of obtaining accurate, dense disparity maps. Existing stereo image generation methods typically focus on either visual quality for viewing or geometric accuracy for matching, but not both. We introduce GenStereo, a diffusion-based approach, to bridge this gap. The method includes two primary innovations (1) conditioning the diffusion process on a disparity-aware coordinate embedding and a warped input image, allowing for more precise stereo alignment than previous methods, and (2) an adaptive fusion mechanism that intelligently combines the diffusion-generated image with a warped image, improving both realism and disparity consistency. Through extensive training on 11 diverse stereo datasets, GenStereo demonstrates strong generalization ability. GenStereo achieves state-of-the-art performance in both stereo image generation and unsupervised stereo matching tasks. Project page is available at https://qjizhi.github.io/genstereo.

cs.CV↗

arXiv2024

Learning to Adapt SAM for Segmenting Cross-domain Point Clouds

Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable challenge, primarily stemming from the sparse and unordered nature of point cloud data. Especially for LiDAR point clouds, the domain discrepancy becomes obvious across varying capture scenes, fluctuating weather conditions, and the diverse array of LiDAR devices in use. While previous UDA methodologies have often sought to mitigate this gap by aligning features between source and target domains, this approach falls short when applied to 3D segmentation due to the substantial domain variations. Inspired by the remarkable generalization capabilities exhibited by the vision foundation model, SAM, in the realm of image segmentation, our approach leverages the wealth of general knowledge embedded within SAM to unify feature representations across diverse 3D domains and further solves the 3D domain adaptation problem. Specifically, we harness the corresponding images associated with point clouds to facilitate knowledge transfer and propose an innovative hybrid feature augmentation methodology, which significantly enhances the alignment between the 3D feature space and SAM's feature space, operating at both the scene and instance levels. Our method is evaluated on many widely-recognized datasets and achieves state-of-the-art performance.

cs.CV↗

arXiv2024

UniMSF: A Unified Multi-Sensor Fusion Framework for Intelligent Transportation System Global Localization

Intelligent transportation systems (ITS) localization is of significant importance as it provides fundamental position and orientation for autonomous operations like intelligent vehicles. Integrating diverse and complementary sensors such as global navigation satellite system (GNSS) and 4D-radar can provide scalable and reliable global localization. Nevertheless, multi-sensor fusion encounters challenges including heterogeneity and time-varying uncertainty in measurements. Consequently, developing a reliable and unified multi-sensor framework remains challenging. In this paper, we introduce UniMSF, a comprehensive multi-sensor fusion localization framework for ITS, utilizing factor graphs. By integrating a multi-sensor fusion front-end, alongside outlier detection\&noise model estimation, and a factor graph optimization back-end, this framework accomplishes efficient fusion and ensures accurate localization for ITS. Specifically, in the multi-sensor fusion front-end module, we tackle the measurement heterogeneity among different modality sensors and establish effective measurement models. Reliable outlier detection and data-driven online noise estimation methods ensure that back-end optimization is immune to interference from outlier measurements. In addition, integrating multi-sensor observations via factor graph optimization offers the advantage of \enquote{plug and play}. Notably, our framework features high modularity and is seamlessly adapted to various sensor configurations. We demonstrate the effectiveness of the proposed framework through real vehicle tests by tightly integrating GNSS pseudorange and carrier phase information with IMU, and 4D-radar.

cs.RO↗

arXiv2024

MCPDepth: Omnidirectional Depth Estimation via Stereo Matching from Multi-Cylindrical Panoramas

Omnidirectional depth estimation presents a significant challenge due to the inherent distortions in panoramic images. Despite notable advancements, the impact of projection methods remains underexplored. We introduce Multi-Cylindrical Panoramic Depth Estimation (MCPDepth), a novel two-stage framework designed to enhance omnidirectional depth estimation through stereo matching across multiple cylindrical panoramas. MCPDepth initially performs stereo matching using cylindrical panoramas, followed by a robust fusion of the resulting depth maps from different views. Unlike existing methods that rely on customized kernels to address distortions, MCPDepth utilizes standard network components, facilitating seamless deployment on embedded devices while delivering exceptional performance. To effectively address vertical distortions in cylindrical panoramas, MCPDepth incorporates a circular attention module, significantly expanding the receptive field beyond traditional convolutions. We provide a comprehensive theoretical and experimental analysis of common panoramic projections-spherical, cylindrical, and cubic-demonstrating the superior efficacy of cylindrical projection. Our method improves the mean absolute error (MAE) by 18.8% on the outdoor dataset Deep360 and by 19.9% on the real dataset 3D60. This work offers practical insights for other tasks and real-world applications, establishing a new paradigm in omnidirectional depth estimation. The code is available at https://github.com/Qjizhi/MCPDepth.

cs.CV↗

arXiv2023

StereoFlowGAN: Co-training for Stereo and Flow with Unsupervised Domain Adaptation

We introduce a novel training strategy for stereo matching and optical flow estimation that utilizes image-to-image translation between synthetic and real image domains. Our approach enables the training of models that excel in real image scenarios while relying solely on ground-truth information from synthetic images. To facilitate task-agnostic domain adaptation and the training of task-specific components, we introduce a bidirectional feature warping module that handles both left-right and forward-backward directions. Experimental results show competitive performance over previous domain translation-based methods, which substantiate the efficacy of our proposed framework, effectively leveraging the benefits of unsupervised domain adaptation, stereo matching, and optical flow estimation.

cs.CV↗

arXiv2023

DUFormer: Solving Power Line Detection Task in Aerial Images using Semantic Segmentation

Unmanned aerial vehicles (UAVs) are frequently used for inspecting power lines and capturing high-resolution aerial images. However, detecting power lines in aerial images is difficult,as the foreground data(i.e, power lines) is small and the background information is abundant.To tackle this problem, we introduce DUFormer, a semantic segmentation algorithm explicitly designed to detect power lines in aerial images. We presuppose that it is advantageous to train an efficient Transformer model with sufficient feature extraction using a convolutional neural network(CNN) with a strong inductive bias.With this goal in mind, we introduce a heavy token encoder that performs overlapping feature remodeling and tokenization. The encoder comprises a pyramid CNN feature extraction module and a power line feature enhancement module.After successful local feature extraction for power lines, feature fusion is conducted.Then,the Transformer block is used for global modeling. The final segmentation result is achieved by amalgamating local and global features in the decode head.Moreover, we demonstrate the importance of the joint multi-weight loss function in power line segmentation. Our experimental results show that our proposed method outperforms all state-of-the-art methods in power line segmentation on the publicly accessible TTPLA dataset.

cs.CV↗

arXiv2022

QuadFormer: Quadruple Transformer for Unsupervised Domain Adaptation in Power Line Segmentation of Aerial Images

Accurate segmentation of power lines in aerial images is essential to ensure the flight safety of aerial vehicles. Acquiring high-quality ground truth annotations for training a deep learning model is a laborious process. Therefore, developing algorithms that can leverage knowledge from labelled synthetic data to unlabelled real images is highly demanded. This process is studied in Unsupervised domain adaptation (UDA). Recent approaches to self-training have achieved remarkable performance in UDA for semantic segmentation, which trains a model with pseudo labels on the target domain. However, the pseudo labels are noisy due to a discrepancy in the two data distributions. We identify that context dependency is important for bridging this domain gap. Motivated by this, we propose QuadFormer, a novel framework designed for domain adaptive semantic segmentation. The hierarchical quadruple transformer combines cross-attention and self-attention mechanisms to adapt transferable context. Based on cross-attentive and self-attentive feature representations, we introduce a pseudo label correction scheme to online denoise the pseudo labels and reduce the domain gap. Additionally, we present two datasets - ARPLSyn and ARPLReal to further advance research in unsupervised domain adaptive powerline segmentation. Finally, experimental results indicate that our method achieves state-of-the-art performance for the domain adaptive power line segmentation on ARPLSyn$\rightarrow$TTTPLA and ARPLSyn$\rightarrow$ARPLReal.

cs.CV↗

arXiv2022

STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes

Accurately detecting and tracking pedestrians in 3D space is challenging due to large variations in rotations, poses and scales. The situation becomes even worse for dense crowds with severe occlusions. However, existing benchmarks either only provide 2D annotations, or have limited 3D annotations with low-density pedestrian distribution, making it difficult to build a reliable pedestrian perception system especially in crowded scenes. To better evaluate pedestrian perception algorithms in crowded scenarios, we introduce a large-scale multimodal dataset,STCrowd. Specifically, in STCrowd, there are a total of 219 K pedestrian instances and 20 persons per frame on average, with various levels of occlusion. We provide synchronized LiDAR point clouds and camera images as well as their corresponding 3D labels and joint IDs. STCrowd can be used for various tasks, including LiDAR-only, image-only, and sensor-fusion based pedestrian detection and tracking. We provide baselines for most of the tasks. In addition, considering the property of sparse global distribution and density-varying local distribution of pedestrians, we further propose a novel method, Density-aware Hierarchical heatmap Aggregation (DHA), to enhance pedestrian perception in crowded scenes. Extensive experiments show that our new method achieves state-of-the-art performance for pedestrian detection on various datasets.

cs.CV↗