arXiv subjects

Xiaoyang Huang

Publications and source records attributed to Xiaoyang Huang.

At least 19 recordsLinked to original sources

arXiv2026

Scenix: Sparse-View 3D Scene Reconstruction via Executable Scene Programs

Synthesizing a structured and editable 3D indoor scene from a few uncalibrated RGB views requires more than generating high-quality individual assets: a system must infer the room structure, associate objects across incomplete observations, and recover a globally consistent spatial configuration. Previous methods mainly focus on 3D scene generation with text input or require continuous visual inputs with additional priors, \ e.g., human-annotated masks or accurate 3D layouts, which makes these methods labor demanding and hard to apply in general cases. We present \textsc{Scenix}, a sparse-view 3D scene reconstruction framework via executable scene programs, a structured representation that can be directly instantiated into editable 3D scenes. Given sparse views, \textsc{Scenix} predicts executable scene programs through perception-grounded asset instantiation and closed-loop spatial refinement. % We present \method, a framework that predicts an executable scene representation from sparse views and realizes it through perception-grounded asset instantiation and closed-loop spatial refinement. To support this task, we construct \dataset, a dataset of approximately 110,000 synthetic and real indoor scenes with multiview imagery, room structures, object-centric descriptions, and metric spatial annotations. We further introduce observation-consistent supervision that aligns each target scene with the visual evidence available in its input views. Experiments on held-out \textsc{XScene} scenes, real indoor images, and out-of-distribution SpatialGen cases evaluate structured scene prediction, object grounding, and spatial refinement.

cs.CV↗

arXiv2026

Quantum geometry from the Moyal product: quantum kinetic equation and non-linear response

We systematically derive the dissipationless quantum kinetic equation for a multi-band free fermionic system with U(1) symmetry. Using the Moyal product formalism, we fully band-diagonalize the dynamics. Expanding to the second order in gradients, which is beyond the semiclassical limit, we give a complete analysis of the band-resolved thermodynamics and transport properties, especially those arising from the quantum geometric tensor. We apply our framework to a Bloch band theory under electric fields near equilibrium and find the linear and nonlinear transport coefficients. We also obtain the dynamical density-density response functions in the metallic case, including quantum metric corrections. Our results and approach can be applied very generally to multi-band problems even in situations with spatially varying Hamiltonians and distributions.

cond-mat.mes-hall↗

arXiv2026

Minimal Models of Entropic Order

Due to entropic effects, it is possible that generic high-energy states of a quantum or classical system are ordered. This leads to spontaneous symmetry breaking at arbitrarily high temperatures. We present minimal models of entropic order that arise from very simple interactions. Our main examples are the Arithmetic Ising Model (AIM) and its quantum analogue, where usual Ising spins are replaced by non-negative integers. Using a large-flavor expansion together with numerical simulations, we find that the high-temperature phase is ordered in the classical and quantum models. We also introduce classical gas models whose interactions drive the system to a crystal at high temperatures.

cond-mat.stat-mech↗

arXiv2025

Generating Human-AI Collaborative Design Sequence for 3D Assets via Differentiable Operation Graph

The emergence of 3D artificial intelligence-generated content (3D-AIGC) has enabled rapid synthesis of intricate geometries. However, a fundamental disconnect persists between AI-generated content and human-centric design paradigms, rooted in representational incompatibilities: conventional AI frameworks predominantly manipulate meshes or neural representations (\emph{e.g.}, NeRF, Gaussian Splatting), while designers operate within parametric modeling tools. This disconnection diminishes the practical value of AI for 3D industry, undermining the efficiency of human-AI collaboration. To resolve this disparity, we focus on generating design operation sequences, which are structured modeling histories that comprehensively capture the step-by-step construction process of 3D assets and align with designers' typical workflows in modern 3D software. We first reformulate fundamental modeling operations (\emph{e.g.}, \emph{Extrude}, \emph{Boolean}) into differentiable units, enabling joint optimization of continuous (\emph{e.g.}, \emph{Extrude} height) and discrete (\emph{e.g.}, \emph{Boolean} type) parameters via gradient-based learning. Based on these differentiable operations, a hierarchical graph with gating mechanism is constructed and optimized end-to-end by minimizing Chamfer Distance to target geometries. Multi-stage sequence length constraint and domain rule penalties enable unsupervised learning of compact design sequences without ground-truth sequence supervision. Extensive validation demonstrates that the generated operation sequences achieve high geometric fidelity, smooth mesh wiring, rational step composition and flexible editing capacity, with full compatibility within design industry.

cs.GR↗

arXiv2025

InstantSticker: Realistic Decal Blending via Disentangled Object Reconstruction

We present InstantSticker, a disentangled reconstruction pipeline based on Image-Based Lighting (IBL), which focuses on highly realistic decal blending, simulates stickers attached to the reconstructed surface, and allows for instant editing and real-time rendering. To achieve stereoscopic impression of the decal, we introduce shadow factor into IBL, which can be adaptively optimized during training. This allows the shadow brightness of surfaces to be accurately decomposed rather than baked into the diffuse color, ensuring that the edited texture exhibits authentic shading. To address the issues of warping and blurriness in previous methods, we apply As-Rigid-As-Possible (ARAP) parameterization to pre-unfold a specified area of the mesh and use the local UV mapping combined with a neural texture map to enhance the ability to express high-frequency details in that area. For instant editing, we utilize the Disney BRDF model, explicitly defining material colors with 3-channel diffuse albedo. This enables instant replacement of albedo RGB values during the editing process, avoiding the prolonged optimization required in previous approaches. In our experiment, we introduce the Ratio Variance Warping (RVW) metric to evaluate the local geometric warping of the decal area. Extensive experimental results demonstrate that our method surpasses previous decal blending methods in terms of editing quality, editing speed and rendering speed, achieving the state-of-the-art.

cs.CV↗

arXiv2025

Entropic Order

Ordered phases of matter, such as solids, ferromagnets, superfluids, or quantum topological order, typically only exist at low temperatures. Despite this conventional wisdom, we present explicit local models in which all such phases persist to arbitrarily high temperature. This is possible since order in one degree of freedom can enable other degrees of freedom to strongly fluctuate, leading to "entropic order", whereby typical high energy states are ordered. Our construction, which utilizes interacting bosons, avoids existing no-go theorems on long-range order or entanglement at high temperature. We propose a simple model for high-temperature superconductivity using these general principles.

cond-mat.stat-mech↗

arXiv2025

Hydrodynamics as the effective field theory of strong-to-weak spontaneous symmetry breaking

Inspired by the hunt for new phases of matter in quantum mixed states, it has recently been proposed that the equivalence of microcanonical and canonical ensembles in statistical mechanics is a manifestation of strong-to-weak spontaneous symmetry breaking (SWSSB) in an underlying many-body quantum description. Here, we build an effective field theory for SWSSB of a global U(1) symmetry; the answer exactly reproduces the Schwinger-Keldysh effective field theory of diffusion for the conserved charge. We conclude that hydrodynamics can be understood as a theory of "superfluidity" for the broken strong symmetry: a non-vanishing susceptibility is a measurable order parameter for SWSSB, the diffusion mode is the Goldstone boson of the spontaneously broken continuous symmetry, and a generalization of Goldstone's Theorem implies that the diffusion mode is always long-lived. This perspective provides a transparent physical explanation for the unusual "reparameterization" symmetries which are a necessary ingredient of Schwinger-Keldysh effective field theories for "normal fluids".

cond-mat.str-el↗

arXiv2024

Breakdown of hydrodynamics in a Galilean quantum Hall crystal

We construct a nonlinear fluctuating hydrodynamic effective field theory for Galilean-invariant quantum Hall systems with spontaneously broken translational symmetry. Neglecting the role of energy conservation in a low-temperature regime, the hydrodynamic mode is a magnetophonon with quartic attenuation: $ω\sim \pm k^2-\mathrm{i} k^z$ with $z=4$. However, this linear response theory is unstable, and flows to a non-trivial dynamical universality class with $z\approx 3$. We observe this scaling in numerical simulations of many-body classical Hamiltonian dynamics, in a model of an electronic crystal in the lowest Landau level. Observing this magnetophonon decay rate in a quantum Hall crystal represents a promising setting to detect an analogue of a "fractonic dynamical universality class" in a solid-state system, e.g. using microwave impedance microscopy.

cond-mat.mes-hall↗

arXiv2024

Effective field theory of Berry Fermi liquid from the coadjoint orbit method

We construct an effective field theory for an interacting Fermi liquid with nonzero Berry curvature at zero temperature, called the Berry Fermi liquid. We start with the extended phase space formalism, incorporating physical time into the configuration space. This approach allows us to include the time dependence of the background gauge fields ``covariantly'' into the symplectic structure. Upon restricting to the physical hypersurface, the effective action that lives on the coadjoint orbit becomes the minus free energy on the extended phase space. We also derive the action perturbatively in external fields using the canonical variables. For applications, we compute both linear and nonlinear electrical responses using the Kubo formula, and identify contributions from the electric and magnetic dipole moments, which stem from interactions breaking parity and time-reversal symmetry. The anomalous Hall effect is confirmed using the kinetic theory.

cond-mat.str-el↗

arXiv2024

Effective field theory for ersatz Fermi liquids

We apply "hydrodynamic" effective field theory techniques to an ersatz Fermi liquid. Our effective theory, which captures the correlation functions of density operators at each angle on the Fermi surface, can only deviate from conventional Fermi liquid behavior if the effective theory is non-local. Neglecting non-local effects, the ersatz Fermi liquid's effective action is the Legendre transform of the effective action for Fermi liquids, based on the coadjoint orbit method, up to irrelevant corrections.

cond-mat.str-el↗

arXiv2024

Deep Rib Fracture Instance Segmentation and Classification from CT on the RibFrac Challenge

Rib fractures are a common and potentially severe injury that can be challenging and labor-intensive to detect in CT scans. While there have been efforts to address this field, the lack of large-scale annotated datasets and evaluation benchmarks has hindered the development and validation of deep learning algorithms. To address this issue, the RibFrac Challenge was introduced, providing a benchmark dataset of over 5,000 rib fractures from 660 CT scans, with voxel-level instance mask annotations and diagnosis labels for four clinical categories (buckle, nondisplaced, displaced, or segmental). The challenge includes two tracks: a detection (instance segmentation) track evaluated by an FROC-style metric and a classification track evaluated by an F1-style metric. During the MICCAI 2020 challenge period, 243 results were evaluated, and seven teams were invited to participate in the challenge summary. The analysis revealed that several top rib fracture detection solutions achieved performance comparable or even better than human experts. Nevertheless, the current rib fracture classification solutions are hardly clinically applicable, which can be an interesting area in the future. As an active benchmark and research resource, the data and online evaluation of the RibFrac Challenge are available at the challenge website. As an independent contribution, we have also extended our previous internal baseline by incorporating recent advancements in large-scale pretrained networks and point-based rib segmentation techniques. The resulting FracNet+ demonstrates competitive performance in rib fracture detection, which lays a foundation for further research and development in AI-assisted rib fracture detection and diagnosis.

eess.IV↗

arXiv2023

Generalized time-reversal symmetry and effective theories for nonequilibrium matter

The past decade has witnessed the development of systematic effective theories for dissipative thermal systems. Here, we describe an analogous effective theory framework that applies to the classical stochastic dynamics of nonequilibrium systems. We illustrate this approach using a range of examples, including nonreciprocal (predator-prey) dynamics, dissipative and driven rigid-body motion, and active chiral fluids and solids. Many of these systems exhibit a generalized time-reversal symmetry, which plays a crucial role within our formalism, and in many cases can be implemented within the Martin-Siggia-Rose path integral. This effective theory formalism yields generalizations of the fluctuation-dissipation theorem and second law of thermodynamics valid out of equilibrium. By stipulating a stationary distribution and a set of symmetries -- rather than postulating the stochastic equations of motion directly -- this formalism provides an alternative route to building phenomenological models of driven and active matter. We hope that this approach facilitates a systematic investigation of the universality classes of active matter, and provides a common language for nonequilibrium many-body physics from high energy to condensed matter.

cond-mat.stat-mech↗

arXiv2023

A Chern-Simons theory for dipole symmetry

We present effective field theories for dipole symmetric topological matters that can be described by the Chern-Simons theory. Unlike most studies using higher-rank gauge theory, we develop a framework with both U(1) and dipole gauge fields. As a result, only the highest multipole symmetry can support the 't Hooft anomaly. We show that with appropriate point group symmetries, the dipolar Chern-Simons theory can exist in any dimension and, moreover, the bulk-edge correspondence can depend on the boundary. As two applications, we draw an analogy between the dipole anomaly and the torsional anomaly and generalize particle-vortex duality to dipole phase transitions. All of the above are in the flat spacetime limit, but our framework is able to systematically couple dipole symmetry to curved spacetime. Based on that, we give a proposal about anomalous dipole hydrodynamics. Moreover, we show that the fracton-elasticity duality arises naturally from a non-abelian Chern-Simons theory in 3D.

cond-mat.str-el↗

arXiv2023

Shifting More Attention to Breast Lesion Segmentation in Ultrasound Videos

Breast lesion segmentation in ultrasound (US) videos is essential for diagnosing and treating axillary lymph node metastasis. However, the lack of a well-established and large-scale ultrasound video dataset with high-quality annotations has posed a persistent challenge for the research community. To overcome this issue, we meticulously curated a US video breast lesion segmentation dataset comprising 572 videos and 34,300 annotated frames, covering a wide range of realistic clinical scenarios. Furthermore, we propose a novel frequency and localization feature aggregation network (FLA-Net) that learns temporal features from the frequency domain and predicts additional lesion location positions to assist with breast lesion segmentation. We also devise a localization-based contrastive loss to reduce the lesion location distance between neighboring video frames within the same video and enlarge the location distances between frames from different ultrasound videos. Our experiments on our annotated dataset and two public video polyp segmentation datasets demonstrate that our proposed FLA-Net achieves state-of-the-art performance in breast lesion segmentation in US videos and video polyp segmentation while significantly reducing time and space complexity. Our model and dataset are available at https://github.com/jhl-Det/FLA-Net.

eess.IV↗

arXiv2023

Disordered quantum critical fixed points from holography

Using holographic duality, we present an analytically controlled theory of quantum critical points without quasiparticles, at finite disorder and finite charge density. These fixed points are obtained by perturbing a disorder-free quantum critical point with relevant disorder whose operator dimension is perturbatively close to Harris marginal. We analyze these fixed points both using field theoretic arguments, and by solving the bulk equations of motion in holography. We calculate the critical exponents of the IR theory, together with thermoelectric transport coefficients. Our predictions for the critical exponents of the disordered fixed point are consistent with previous work, both in holographic and nonholograpic models.

cond-mat.str-el↗

arXiv2023

Goldstone bosons and fluctuating hydrodynamics with dipole and momentum conservation

We develop a Schwinger-Keldysh effective field theory describing the hydrodynamics of a fluid with conserved charge and dipole moments, together with conserved momentum. The resulting hydrodynamic modes are highly unusual, including sound waves with quadratic (magnon-like) dispersion relation and subdiffusive decay rate. Hydrodynamics itself is unstable below four spatial dimensions. We show that the momentum density is, at leading order, the Goldstone boson for a dipole symmetry which appears spontaneously broken at finite charge density. Unlike an ordinary fluid, the presence or absence of energy conservation qualitatively changes the decay rates of the hydrodynamic modes. This effective field theory naturally couples to curved spacetime and background gauge fields; in the flat spacetime limit, we reproduce the "mixed rank tensor fields" previously coupled to fracton matter.

hep-th↗

arXiv2023

Frequency-Modulated Point Cloud Rendering with Easy Editing

We develop an effective point cloud rendering pipeline for novel view synthesis, which enables high fidelity local detail reconstruction, real-time rendering and user-friendly editing. In the heart of our pipeline is an adaptive frequency modulation module called Adaptive Frequency Net (AFNet), which utilizes a hypernetwork to learn the local texture frequency encoding that is consecutively injected into adaptive frequency activation layers to modulate the implicit radiance signal. This mechanism improves the frequency expressive ability of the network with richer frequency basis support, only at a small computational budget. To further boost performance, a preprocessing module is also proposed for point cloud geometry optimization via point opacity estimation. In contrast to implicit rendering, our pipeline supports high-fidelity interactive editing based on point cloud manipulation. Extensive experimental results on NeRF-Synthetic, ScanNet, DTU and Tanks and Temples datasets demonstrate the superior performances achieved by our method in terms of PSNR, SSIM and LPIPS, in comparison to the state-of-the-art.

cs.CV↗

arXiv2023

AudioEar: Single-View Ear Reconstruction for Personalized Spatial Audio

Spatial audio, which focuses on immersive 3D sound rendering, is widely applied in the acoustic industry. One of the key problems of current spatial audio rendering methods is the lack of personalization based on different anatomies of individuals, which is essential to produce accurate sound source positions. In this work, we address this problem from an interdisciplinary perspective. The rendering of spatial audio is strongly correlated with the 3D shape of human bodies, particularly ears. To this end, we propose to achieve personalized spatial audio by reconstructing 3D human ears with single-view images. First, to benchmark the ear reconstruction task, we introduce AudioEar3D, a high-quality 3D ear dataset consisting of 112 point cloud ear scans with RGB images. To self-supervisedly train a reconstruction model, we further collect a 2D ear dataset composed of 2,000 images, each one with manual annotation of occlusion and 55 landmarks, named AudioEar2D. To our knowledge, both datasets have the largest scale and best quality of their kinds for public use. Further, we propose AudioEarM, a reconstruction method guided by a depth estimation network that is trained on synthetic data, with two loss functions tailored for ear data. Lastly, to fill the gap between the vision and acoustics community, we develop a pipeline to integrate the reconstructed ear mesh with an off-the-shelf 3D human body and simulate a personalized Head-Related Transfer Function (HRTF), which is the core of spatial audio rendering. Code and data are publicly available at https://github.com/seanywang0408/AudioEar.

cs.CV↗