arXiv subjects

Chun Xie

Publications and source records attributed to Chun Xie.

13 recordsLinked to original sources

arXiv2026

MetaSSP: Enhancing Semi-supervised Implicit 3D Reconstruction through Meta-adaptive EMA and SDF-aware Pseudo-label Evaluation

Implicit SDF-based methods for single-view 3D reconstruction achieve high-quality surfaces but require large labeled datasets, limiting their scalability. We propose MetaSSP, a novel semi-supervised framework that exploits abundant unlabeled images. Our approach introduces gradient-based parameter importance estimation to regularize adaptive EMA updates and an SDF-aware pseudo-label weighting mechanism combining augmentation consistency with SDF variance. Beginning with a 10% supervised warm-up, the unified pipeline jointly refines labeled and unlabeled data. On the Pix3D benchmark, our method reduces Chamfer Distance by approximately 20.61% and increases IoU by around 24.09% compared to existing semi-supervised baselines, setting a new state of the art.

cs.CV↗

arXiv2026

MGP-KAD: Multimodal Geometric Priors and Kolmogorov-Arnold Decoder for Single-View 3D Reconstruction in Complex Scenes

Single-view 3D reconstruction in complex real-world scenes is challenging due to noise, object diversity, and limited dataset availability. To address these challenges, we propose MGP-KAD, a novel multimodal feature fusion framework that integrates RGB and geometric prior to enhance reconstruction accuracy. The geometric prior is generated by sampling and clustering ground-truth object data, producing class-level features that dynamically adjust during training to improve geometric understanding. Additionally, we introduce a hybrid decoder based on Kolmogorov-Arnold Networks (KAN) to overcome the limitations of traditional linear decoders in processing complex multimodal inputs. Extensive experiments on the Pix3D dataset demonstrate that MGP-KAD achieves state-of-the-art (SOTA) performance, significantly improving geometric integrity, smoothness, and detail preservation. Our work provides a robust and effective solution for advancing single-view 3D reconstruction in complex scenes.

cs.CV↗

arXiv2025

SV-DRR: High-Fidelity Novel View X-Ray Synthesis Using Diffusion Model

X-ray imaging is a rapid and cost-effective tool for visualizing internal human anatomy. While multi-view X-ray imaging provides complementary information that enhances diagnosis, intervention, and education, acquiring images from multiple angles increases radiation exposure and complicates clinical workflows. To address these challenges, we propose a novel view-conditioned diffusion model for synthesizing multi-view X-ray images from a single view. Unlike prior methods, which are limited in angular range, resolution, and image quality, our approach leverages the Diffusion Transformer to preserve fine details and employs a weak-to-strong training strategy for stable high-resolution image generation. Experimental results demonstrate that our method generates higher-resolution outputs with improved control over viewing angles. This capability has significant implications not only for clinical applications but also for medical education and data extension, enabling the creation of diverse, high-quality datasets for training and analysis. Our code is available at https://github.com/xiechun298/SV-DRR.

eess.IV↗

arXiv2025

Observation of Momentum-Band Topology in PT-Symmetric acoustic Floquet Lattices

Momentum-band topology, which transcends conventional topological band theory, unlocks new topological phases that host fascinating temporal interface states. However, direct bulk experimental evidence of such emerging band topology is still lacking due to the great challenges in resolving eigenstates and topological invariants of time-varying systems. Here, we present a comprehensive study on the momentum-band topology in a PT-symmetric Floquet lattice, where the drive-induced momentum gap can be characterized by a quantized Berry phase in the energy Brillouin zone. Experimentally, we synthesize the Floquet lattice model using an acoustic cavity-tube structure coupled to custom-designed external circuits. By reconstructing the effective Hamiltonian, we extract the system's eigenstates and provide the first bulk evidence of momentum-band topology from the perspectives of band inversion and topological invariants. This is accompanied by an unambiguous observation of time-localized interface states in real physical time, thereby providing the boundary signature of the bulk topology. Our work paves the way for further experimental studies on the burgeoning momentum-gap physics.

cond-mat.mtrl-sci↗

arXiv2024

M3D: Dual-Stream Selective State Spaces and Depth-Driven Framework for High-Fidelity Single-View 3D Reconstruction

The precise reconstruction of 3D objects from a single RGB image in complex scenes presents a critical challenge in virtual reality, autonomous driving, and robotics. Existing neural implicit 3D representation methods face significant difficulties in balancing the extraction of global and local features, particularly in diverse and complex environments, leading to insufficient reconstruction precision and quality. We propose M3D, a novel single-view 3D reconstruction framework, to tackle these challenges. This framework adopts a dual-stream feature extraction strategy based on Selective State Spaces to effectively balance the extraction of global and local features, thereby improving scene comprehension and representation precision. Additionally, a parallel branch extracts depth information, effectively integrating visual and geometric features to enhance reconstruction quality and preserve intricate details. Experimental results indicate that the fusion of multi-scale features with depth information via the dual-branch feature extraction significantly boosts geometric consistency and fidelity, achieving state-of-the-art reconstruction performance.

cs.CV↗

arXiv2024

RayEmb: Arbitrary Landmark Detection in X-Ray Images Using Ray Embedding Subspace

Intra-operative 2D-3D registration of X-ray images with pre-operatively acquired CT scans is a crucial procedure in orthopedic surgeries. Anatomical landmarks pre-annotated in the CT volume can be detected in X-ray images to establish 2D-3D correspondences, which are then utilized for registration. However, registration often fails in certain view angles due to poor landmark visibility. We propose a novel method to address this issue by detecting arbitrary landmark points in X-ray images. Our approach represents 3D points as distinct subspaces, formed by feature vectors (referred to as ray embeddings) corresponding to intersecting rays. Establishing 2D-3D correspondences then becomes a task of finding ray embeddings that are close to a given subspace, essentially performing an intersection test. Unlike conventional methods for landmark estimation, our approach eliminates the need for manually annotating fixed landmarks. We trained our model using the synthetic images generated from CTPelvic1K CLINIC dataset, which contains 103 CT volumes, and evaluated it on the DeepFluoro dataset, comprising real X-ray images. Experimental results demonstrate the superiority of our method over conventional methods. The code is available at https://github.com/Pragyanstha/rayemb.

cs.CV↗

arXiv2023

X-Ray to CT Rigid Registration Using Scene Coordinate Regression

Intraoperative fluoroscopy is a frequently used modality in minimally invasive orthopedic surgeries. Aligning the intraoperatively acquired X-ray image with the preoperatively acquired 3D model of a computed tomography (CT) scan reduces the mental burden on surgeons induced by the overlapping anatomical structures in the acquired images. This paper proposes a fully automatic registration method that is robust to extreme viewpoints and does not require manual annotation of landmark points during training. It is based on a fully convolutional neural network (CNN) that regresses the scene coordinates for a given X-ray image. The scene coordinates are defined as the intersection of the back-projected rays from a pixel toward the 3D model. Training data for a patient-specific model were generated through a realistic simulation of a C-arm device using preoperative CT scans. In contrast, intraoperative registration was achieved by solving the perspective-n-point (PnP) problem with a random sample and consensus (RANSAC) algorithm. Experiments were conducted using a pelvic CT dataset that included several real fluoroscopic (X-ray) images with ground truth annotations. The proposed method achieved an average mean target registration error (mTRE) of 3.79 mm in the 50th percentile of the simulated test dataset and projected mTRE of 9.65 mm in the 50th percentile of real fluoroscopic images for pelvis registration.

cs.CV↗

arXiv2023

Rate-Induced Tipping: Thresholds, Edge States and Connecting Orbits

Rate-induced tipping (R-tipping) occurs when time-variation of input parameters of a dynamical system interacts with system timescales to give genuine nonautonomous instabilities. Such instabilities appear as the input varies at some critical rates and cannot, in general, be understood in terms of autonomous bifurcations in the frozen system with a fixed-in-time input. This paper develops an accessible mathematical framework for R-tipping in multidimensional nonautonomous dynamical systems with an autonomous future limit. We focus on R-tipping via loss of tracking of base attractors that are equilibria in the frozen system, due to crossing what we call regular thresholds. These thresholds are associated with regular edge states: compact hyperbolic invariant sets with one unstable direction and orientable stable manifold, that lie on a basin boundary in the frozen system. We define R-tipping and critical rates for the nonautonomous system in terms of special solutions that limit to a compact invariant set of the future limit system that is not an attractor. We focus on the case when the limit set is a regular edge state, which we call the regular R-tipping edge state that anchors the associated regular R-tipping threshold at infinity. We introduce the concept of edge tails to rigorously classify R-tipping into reversible, irreversible, and degenerate cases. The main idea is to compactify the problem and use regular edge states of the future limit system to analyse R-tipping in the nonautonomous system. This allows us to give sufficient conditions for the occurrence of R-tipping in terms of easily testable properties of the frozen system and input variation, and necessary and sufficient conditions for the occurrence of reversible and irreversible R-tipping in terms of computationally verifiable (heteroclinic) connections to regular R-tipping edge states in the compactified system.

math.DS↗

arXiv2022

OmniVoxel: A Fast and Precise Reconstruction Method of Omnidirectional Neural Radiance Field

This paper proposes a method to reconstruct the neural radiance field with equirectangular omnidirectional images. Implicit neural scene representation with a radiance field can reconstruct the 3D shape of a scene continuously within a limited spatial area. However, training a fully implicit representation on commercial PC hardware requires a lot of time and computing resources (15 $\sim$ 20 hours per scene). Therefore, we propose a method to accelerate this process significantly (20 $\sim$ 40 minutes per scene). Instead of using a fully implicit representation of rays for radiance field reconstruction, we adopt feature voxels that contain density and color features in tensors. Considering omnidirectional equirectangular input and the camera layout, we use spherical voxelization for representation instead of cubic representation. Our voxelization method could balance the reconstruction quality of the inner scene and outer scene. In addition, we adopt the axis-aligned positional encoding method on the color features to increase the total image quality. Our method achieves satisfying empirical performance on synthetic datasets with random camera poses. Moreover, we test our method with real scenes which contain complex geometries and also achieve state-of-the-art performance. Our code and complete dataset will be released at the same time as the paper publication.

cs.CV↗

arXiv2020

Compactification for Asymptotically Autonomous Dynamical Systems: Theory, Applications and Invariant Manifolds

We develop a general compactification framework to facilitate analysis of nonlinear nonautonomous ODEs where nonautonomous terms decay asymptotically. The strategy is to compactify the problem: the phase space is augmented with a bounded but open dimension and then extended at one or both ends by gluing in flow-invariant subspaces that carry autonomous dynamics of the limit systems from infinity. We derive the weakest decay conditions possible for the compactified system to be continuously differentiable on the extended phase space. This enables us to use equilibria and other compact invariant sets of the limit systems from infinity to analyse the original nonautonomous problem in the spirit of dynamical systems theory. Specifically, we prove that solutions of interest are contained in unique invariant manifolds of saddles for the limit systems when embedded in the extended phase space. The uniqueness holds in the general case, that is even if the compactification gives rise to a centre direction and the manifolds become centre or centre-stable manifolds. A wide range of problems including pullback attractors, rate-induced critical transitions (R-tipping) and nonlinear wave solutions fit naturally into our framework.

math.DS↗

arXiv2019

Calibration of X-ray telescope prototypes at PANTER

We report a ground X-ray calibration of two X-ray telescope prototypes at the PANTER X-ray Test Facility, of the Max-Planck-Institute for Extraterrestrial Physics, in Neuried, Germany. The X-ray telescope prototypes were developed by the Institute of Precision Optical Engineering (IPOE) of Tongji University, in a conical Wolter-I configuration, using thermal glass slumping technology. Prototype #1 with 3 layers and Prototype #2 with 21 layers were tested to assess the prototypes' on-axis imaging performance. The measurement of Prototype #1 indicates a Half Power Diameter (HPD) of 82" at 1.49 keV. As for Prototype #2, we performed more comprehensive measurements of on-axis angular resolution and effective area at several energies ranging from 0.5-10 keV. The HPD and effective area are 111" and 39 cm^2 at 1.49 keV, respectively, at which energy the on-axis performance of the prototypes is our greatest concern.

astro-ph.IM↗

arXiv2018

Flow-induced Density Fluctuation assisted Nucleation in Polyethylene

The nucleation process of polyethylene under quiescent and shear flow conditions are comparatively studied with all_atom molecular dynamical simulations. At both conditions, nucleation are demonstrated to be two_step processes, which, however, proceed via different intermediate orders. Quiescent nucleation is assisted by local structure order coupling conformational and local rotational symmetric orderings, while flow_induced nucleation is promoted by density fluctuation, which is a coupling effect of conformational and orientation orderings. Flow drives the transformation from flexible chains to rigid conformational ordered segments and circumvents the entropic penalty, which is the most peculiar and rate_limited step in polymer crystallization. Current work suggests that flow accelerates nucleation in orders of magnitude is not simply due to flow_induced entropic reduction of melt as early models proposed, which is mainly attributed to the different kinetic pathway via conformational/orientational ordering_density fluctuation_nucleation.

cond-mat.soft↗

arXiv2017

Local Structure Order Assisted Two-step Crystal Nucleation in Polyethylene

Homogeneous nucleation process of polyethylene (PE) is studied with full-atom molecular dynamic simulation. To account the complex shape with low symmetry and the peculiar intra-chain conformational order of polymer, we introduce a shape descriptor OCB coupling conformational order and inter-chain rotational symmetry, which is able to differentiate hexagonal and orthorhombic clusters from melt. With the shape descriptor OCB, we find that coupling between conformational and inter-chain rotational orderings results in the formation of hexagonal clusters first, which is dynamic in nature. Whilst nucleation of orthorhombic structure occurs inside of hexagonal clusters later, which proceeds via the coalescence of neighboring hexagonal clusters rather than standard stepwise growth process. This demonstrates that nucleation of PE crystal is a two-step process with the assistance of OCB order, which is different from early models for polymer crystallization but similar with that proposed for spherical 'atoms' like colloid and metal.

cond-mat.soft↗