arXiv subjects

Runze Zhang

Publications and source records attributed to Runze Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Large Material Gaussian Model for Relightable 3D Generation

The increasing demand for 3D assets across various industries necessitates efficient and automated methods for 3D content creation. Leveraging 3D Gaussian Splatting, recent large reconstruction models (LRMs) have demonstrated the ability to efficiently achieve high-quality 3D rendering by integrating multiview diffusion for generation and scalable transformers for reconstruction. However, existing models fail to produce the material properties of assets, which is crucial for realistic rendering in diverse lighting environments. In this paper, we introduce the Large Material Gaussian Model (MGM), a novel framework designed to generate high-quality 3D content with Physically Based Rendering (PBR) materials, ie, albedo, roughness, and metallic properties, rather than merely producing RGB textures with uncontrolled light baking. Specifically, we first fine-tune a new multiview material diffusion model conditioned on input depth and normal maps. Utilizing the generated multiview PBR images, we explore a Gaussian material representation that not only aligns with 2D Gaussian Splatting but also models each channel of the PBR materials. The reconstructed point clouds can then be rendered to acquire PBR attributes, enabling dynamic relighting by applying various ambient light maps. Extensive experiments demonstrate that the materials produced by our method not only exhibit greater visual appeal compared to baseline methods but also enhance material modeling, thereby enabling practical downstream rendering applications.

cs.CV↗

arXiv2025

On extension of closed complex (basic) differential forms: (basic) Hodge numbers and (transversely) $p$-Kähler structures

Inspired by a recent work of D. Wei--S. Zhu on the extension of closed complex differential forms and Voisin's usage of the $\partial\bar{\partial}$-lemma, we obtain several new theorems of deformation invariance of Hodge numbers and reprove the local stabilities of $p$-Kähler structures with the $\partial\bar{\partial}$-property. Our approach is more concerned with the $d$-closed extension by means of the exponential operator $e^{ι_φ}$. Furthermore, we prove the local stabilities of transversely $p$-Kähler structures with mild $\partial\bar{\partial}$-property by adapting the power series method to the foliated case, which strengthens the works of A. El Kacimi Alaoui--B. Gmira and P. Raźny on that of the transversely Kähler foliations with homologically orientability. We observe that a transversely Kähler foliation, even without homologically orientability, also satisfies the $\partial\bar{\partial}$-property. So even when $p=1$ (transversely Kähler), our results are new as we can drop the assumption in question on the initial foliation. Several theorems on the deformation invariance of basic Hodge/Bott--Chern numbers with mild $\partial\bar{\partial}$-properties are also presented.

math.CV↗

arXiv2025

Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation

Scaling laws have validated the success and promise of large-data-trained models in creative generation across text, image, and video domains. However, this paradigm faces data scarcity in the 3D domain, as there is far less of it available on the internet compared to the aforementioned modalities. Fortunately, there exist adequate videos that inherently contain commonsense priors, offering an alternative supervisory signal to mitigate the generalization bottleneck caused by limited native 3D data. On the one hand, videos capturing multiple views of an object or scene provide a spatial consistency prior for 3D generation. On the other hand, the rich semantic information contained within the videos enables the generated content to be more faithful to the text prompts and semantically plausible. This paper explores how to apply the video modality in 3D asset generation, spanning datasets to models. We introduce Droplet3D-4M, the first large-scale video dataset with multi-view level annotations, and train Droplet3D, a generative model supporting both image and dense text input. Extensive experiments validate the effectiveness of our approach, demonstrating its ability to produce spatially consistent and semantically plausible content. Moreover, in contrast to the prevailing 3D solutions, our approach exhibits the potential for extension to scene-level applications. This indicates that the commonsense priors from the videos significantly facilitate 3D creation. We have open-sourced all resources including the dataset, code, technical framework, and model weights: https://dropletx.github.io/.

cs.CV↗

arXiv2025

Parabolic Implosion in the Parameter Space of Cubic Polynomials

Parabolic implosion describes the enrichment of Julia sets when a parabolic fixed point is perturbed. It is also natural to study parabolic implosion in parameter spaces. In particular, when one perturbs properly the family of cubic polynomials having a stable parabolic fixed point into nearby families, the enrichment of the bifurcation loci occurs. We investigate the topology of such enrichment in the parameter space of cubic polynomials and relate it to the corresponding enrichment of Julia sets of quadratic polynomials, the latter of which has been studied systematically by P. Lavaurs in the 80s.

math.DS↗

arXiv2025

Efficient Algorithms for Relevant Quantities of Friedkin-Johnsen Opinion Dynamics Model

Online social networks have become an integral part of modern society, profoundly influencing how individuals form and exchange opinions across diverse domains ranging from politics to public health. The Friedkin-Johnsen model serves as a foundational framework for modeling opinion formation dynamics in such networks. In this paper, we address the computational task of efficiently determining the equilibrium opinion vector and associated metrics including polarization and disagreement, applicable to both directed and undirected social networks. We propose a deterministic local algorithm with relative error guarantees, scaling to networks exceeding ten million nodes. Further acceleration is achieved through integration with successive over-relaxation techniques, where a relaxation factor optimizes convergence rates. Extensive experiments on diverse real-world networks validate the practical effectiveness of our approaches, demonstrating significant improvements in computational efficiency and scalability compared to conventional methods.

cs.SI↗

arXiv2025

UAV-Based Remote Sensing of Soil Moisture Across Diverse Land Covers: Validation and Bayesian Uncertainty Characterization

High-resolution soil moisture (SM) observations are critical for agricultural monitoring, forestry management, and hazard prediction, yet current satellite passive microwave missions cannot directly provide retrievals at tens-of-meter spatial scales. Unmanned aerial vehicle (UAV) mounted microwave radiometry presents a promising alternative, but most evaluations to date have focused on agricultural settings, with limited exploration across other land covers and few efforts to quantify retrieval uncertainty. This study addresses both gaps by evaluating SM retrievals from a drone-based Portable L-band Radiometer (PoLRa) across shrubland, bare soil, and forest strips in Central Illinois, U.S., using a 10-day field campaign in 2024. Controlled UAV flights at altitudes of 10 m, 20 m, and 30 m were performed to generate brightness temperatures (TB) at spatial resolutions of 7 m, 14 m, and 21 m. SM retrievals were carried out using multiple tau-omega-based algorithms, including the single channel algorithm (SCA), dual channel algorithm (DCA), and multi-temporal dual channel algorithm (MTDCA). A Bayesian inference framework was then applied to provide probabilistic uncertainty characterization for both SM and vegetation optical depth (VOD). Results show that the gridded TB distributions consistently capture dry-wet gradients associated with vegetation density variations, and spatial correlations between polarized observations are largely maintained across scales. Validation against in situ measurements indicates that PoLRa derived SM retrievals from the SCAV and MTDCA algorithms achieve unbiased root-mean-square errors (ubRMSE) generally below 0.04 m3/m3 across different land covers. Bayesian posterior analyses confirm that reference SM values largely fall within the derived uncertainty intervals, with mean uncertainty ranges around 0.02 m3/m3 and 0.11 m3/m3 for SCA and DCA related retrievals.

eess.SP↗

arXiv2025

Building LOD Representation for 3D Urban Scenes

The advances in 3D reconstruction technology, such as photogrammetry and LiDAR scanning, have made it easier to reconstruct accurate and detailed 3D models for urban scenes. Nevertheless, these reconstructed models often contain a large number of geometry primitives, making interactive manipulation and rendering challenging, especially on resource-constrained devices like virtual reality platforms. Therefore, the generation of appropriate levels-of-detail (LOD) representations for these models is crucial. Additionally, automatically reconstructed 3D models tend to suffer from noise and lack semantic information. Dealing with these issues and creating LOD representations that are robust against noise while capturing the semantic meaning present significant challenges. In this paper, we propose a novel algorithm to address these challenges. We begin by analysing the properties of planar primitives detected from the input and group these primitives into multiple level sets by forming meaningful 3D structures. These level sets form the nodes of our innovative LOD-Tree. By selecting nodes at appropriate depths within the LOD-Tree, different LOD representations can be generated. Experimental results on real and complex urban scenes demonstrate the merits of our approach in generating clean, accurate, and semantically meaningful LOD representations.

cs.GR↗

arXiv2025

MuMA: 3D PBR Texturing via Multi-Channel Multi-View Generation and Agentic Post-Processing

Current methods for 3D generation still fall short in physically based rendering (PBR) texturing, primarily due to limited data and challenges in modeling multi-channel materials. In this work, we propose MuMA, a method for 3D PBR texturing through Multi-channel Multi-view generation and Agentic post-processing. Our approach features two key innovations: 1) We opt to model shaded and albedo appearance channels, where the shaded channels enables the integration intrinsic decomposition modules for material properties. 2) Leveraging multimodal large language models, we emulate artists' techniques for material assessment and selection. Experiments demonstrate that MuMA achieves superior results in visual quality and material fidelity compared to existing methods.

cs.CV↗

arXiv2025

DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation

Spatio-temporal consistency is a critical research topic in video generation. A qualified generated video segment must ensure plot plausibility and coherence while maintaining visual consistency of objects and scenes across varying viewpoints. Prior research, especially in open-source projects, primarily focuses on either temporal or spatial consistency, or their basic combination, such as appending a description of a camera movement after a prompt without constraining the outcomes of this movement. However, camera movement may introduce new objects to the scene or eliminate existing ones, thereby overlaying and affecting the preceding narrative. Especially in videos with numerous camera movements, the interplay between multiple plots becomes increasingly complex. This paper introduces and examines integral spatio-temporal consistency, considering the synergy between plot progression and camera techniques, and the long-term impact of prior content on subsequent generation. Our research encompasses dataset construction through to the development of the model. Initially, we constructed a DropletVideo-10M dataset, which comprises 10 million videos featuring dynamic camera motion and object actions. Each video is annotated with an average caption of 206 words, detailing various camera movements and plot developments. Following this, we developed and trained the DropletVideo model, which excels in preserving spatio-temporal coherence during video generation. The DropletVideo dataset and model are accessible at https://dropletx.github.io.

cs.CV↗

arXiv2025

ArcPro: Architectural Programs for Structured 3D Abstraction of Sparse Points

We introduce ArcPro, a novel learning framework built on architectural programs to recover structured 3D abstractions from highly sparse and low-quality point clouds. Specifically, we design a domain-specific language (DSL) to hierarchically represent building structures as a program, which can be efficiently converted into a mesh. We bridge feedforward and inverse procedural modeling by using a feedforward process for training data synthesis, allowing the network to make reverse predictions. We train an encoder-decoder on the points-program pairs to establish a mapping from unstructured point clouds to architectural programs, where a 3D convolutional encoder extracts point cloud features and a transformer decoder autoregressively predicts the programs in a tokenized form. Inference by our method is highly efficient and produces plausible and faithful 3D abstractions. Comprehensive experiments demonstrate that ArcPro outperforms both traditional architectural proxy reconstruction and learning-based abstraction methods. We further explore its potential to work with multi-view image and natural language inputs.

cs.GR↗

arXiv2024

Sub-Meter Remote Sensing of Soil Moisture Using Portable L-band Microwave Radiometer

Spaceborne microwave passive soil moisture products are known for their accuracy but are often limited by coarse spatial resolutions. This limits their ability to capture finer soil moisture gradients and hinders their applications. The Portable L band radiometer (PoLRa) offers soil moisture measurements from submeter to tens of meters depending on the altitude of measurement. Given that the assessments of soil moisture derived from this sensor are notably lacking, this study aims to evaluate the performance of submeter soil moisture retrieved from PoLRa mounted on poles at four different locations in central Illinois, USA. The evaluation focuses on the consistency of PoLRa measured brightness temperatures from different directions relative to the same area, and the accuracy of PoLRa derived soil moisture. As PoLRa shares many aspects of the L band radiometer onboard the NASA Soil Moisture Active Passive (SMAP) mission, two SMAP operational algorithms and the conventional dual channel algorithm were applied to calculate soil moisture from the measured brightness temperatures. The vertically polarized brightness temperatures from the PoLRa are typically more stable than their horizontally polarized counterparts. In each test period, the standard deviations of observed dual polarization brightness temperatures are generally less than 5 K. By comparing PoLRa based soil moisture retrievals against the moisture values obtained by handheld time domain reflectometry, the unbiased root mean square error and the Pearson correlation coefficient are mostly below 0.04 and above 0.75, confirming the high accuracy of PoLRa derived soil moisture retrievals and the feasibility of utilizing SMAP algorithms for PoLRa data. These findings highlight the significant potential of ground or drone based PoLRa measurements as a standalone reference for future spaceborne L band sensors.

eess.SP↗

arXiv2024

Architectural Co-LOD Generation

Managing the level-of-detail (LOD) in architectural models is crucial yet challenging, particularly for effective representation and visualization of buildings. Traditional approaches often fail to deliver controllable detail alongside semantic consistency, especially when dealing with noisy and inconsistent inputs. We address these limitations with \emph{Co-LOD}, a new approach specifically designed for effective LOD management in architectural modeling. Co-LOD employs shape co-analysis to standardize geometric structures across multiple buildings, facilitating the progressive and consistent generation of LODs. This method allows for precise detailing in both individual models and model collections, ensuring semantic integrity. Extensive experiments demonstrate that Co-LOD effectively applies accurate LOD across a variety of architectural inputs, consistently delivering superior detail and quality in LOD representations.

cs.GR↗

arXiv2024

Rigidity of bounded type cubic Siegel polynomials

We prove that if two non-renormalizable cubic Siegel polynomials with bounded type rotation numbers are combinatorially equivalent, then they are also conformally equivalent. As a consequence, we show that in the one-parameter slice of cubic Siegel polynomials considered by Zakeri [Za2], the locus of non-renormalizable maps is homeomorphic to a double-copy of a quadratic Siegel filled Julia set (minus the Siegel disk) glued along the Siegel boundary. This verifies the the conjecture of Blokh-Oversteegen-Ptacek-Timorin [BlOvPtTi] for bounded type rotation numbers.

math.DS↗

arXiv2024

An Assessment of Commonly Used Equivalent Circuit Models for Corrosion Analysis: A Bayesian Approach to Electrochemical Impedance Spectroscopy

Electrochemical Impedance Spectroscopy (EIS) is a crucial technique for assessing corrosion of a metallic materials. The analysis of EIS hinges on the selection of an appropriate equivalent circuit model (ECM) that accurately characterizes the system under study. In this work, we systematically examined the applicability of three commonly used ECMs across several typical material degradation scenarios. By applying Bayesian Inference to simulated corrosion EIS data, we assessed the suitability of these ECMs under different corrosion conditions and identified regions where the EIS data lacks sufficient information to statistically substantiate the ECM structure. Additionally, we posit that the traditional approach to EIS analysis, which often requires measurements to very low frequencies, might not be always necessary to correctly model the appropriate ECM. Our study assesses the impact of omitting data from low to medium-frequency ranges on inference results and reveals that a significant portion of low-frequency measurements can be excluded without substantially compromising the accuracy of extracting system parameters. Further, we propose simple checks to the posterior distributions of the ECM components and posterior predictions, which can be used to quantitatively evaluate the suitability of a particular ECM and the minimum frequency required to be measured. This framework points to a pathway for expediting EIS acquisition by intelligently reducing low-frequency data collection and permitting on-the-fly EIS measurements

cond-mat.mtrl-sci↗

arXiv2024

DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion Models

2D diffusion model, which often contains unwanted baked-in shading effects and results in unrealistic rendering effects in the downstream applications. Generating Physically Based Rendering (PBR) materials instead of just RGB textures would be a promising solution. However, directly distilling the PBR material parameters from 2D diffusion models still suffers from incorrect material decomposition, such as baked-in shading effects in albedo. We introduce DreamMat, an innovative approach to resolve the aforementioned problem, to generate high-quality PBR materials from text descriptions. We find out that the main reason for the incorrect material distillation is that large-scale 2D diffusion models are only trained to generate final shading colors, resulting in insufficient constraints on material decomposition during distillation. To tackle this problem, we first finetune a new light-aware 2D diffusion model to condition on a given lighting environment and generate the shading results on this specific lighting condition. Then, by applying the same environment lights in the material distillation, DreamMat can generate high-quality PBR materials that are not only consistent with the given geometry but also free from any baked-in shading effects in albedo. Extensive experiments demonstrate that the materials produced through our methods exhibit greater visual appeal to users and achieve significantly superior rendering quality compared to baseline methods, which are preferable for downstream tasks such as game and film production.

cs.GR↗

arXiv2023

Image Content Generation with Causal Reasoning

The emergence of ChatGPT has once again sparked research in generative artificial intelligence (GAI). While people have been amazed by the generated results, they have also noticed the reasoning potential reflected in the generated textual content. However, this current ability for causal reasoning is primarily limited to the domain of language generation, such as in models like GPT-3. In visual modality, there is currently no equivalent research. Considering causal reasoning in visual content generation is significant. This is because visual information contains infinite granularity. Particularly, images can provide more intuitive and specific demonstrations for certain reasoning tasks, especially when compared to coarse-grained text. Hence, we propose a new image generation task called visual question answering with image (VQAI) and establish a dataset of the same name based on the classic \textit{Tom and Jerry} animated series. Additionally, we develop a new paradigm for image generation to tackle the challenges of this task. Finally, we perform extensive experiments and analyses, including visualizations of the generated content and discussions on the potentials and limitations. The code and data are publicly available under the license of CC BY-NC-SA 4.0 for academic and non-commercial usage. The code and dataset are publicly available at: https://github.com/IEIT-AGI/MIX-Shannon/blob/main/projects/VQAI/lgd_vqai.md.

cs.CV↗

arXiv2023

AutoEIS: automated Bayesian model selection and analysis for electrochemical impedance spectroscopy

Electrochemical Impedance Spectroscopy (EIS) is a powerful tool for electrochemical analysis; however, its data can be challenging to interpret. Here, we introduce a new open-source tool named AutoEIS that assists EIS analysis by automatically proposing statistically plausible equivalent circuit models (ECMs). AutoEIS does this without requiring an exhaustive mechanistic understanding of the electrochemical systems. We demonstrate the generalizability of AutoEIS by using it to analyze EIS datasets from three distinct electrochemical systems, including thin-film oxygen evolution reaction (OER) electrocatalysis, corrosion of self-healing multi-principal components alloys, and a carbon dioxide reduction electrolyzer device. In each case, AutoEIS identified competitive or in some cases superior ECMs to those recommended by experts and provided statistical indicators of the preferred solution. The results demonstrated AutoEIS's capability to facilitate EIS analysis without expert labels while diminishing user bias in a high-throughput manner. AutoEIS provides a generalized automated approach to facilitate EIS analysis spanning a broad suite of electrochemical applications with minimal prior knowledge of the system required. This tool holds great potential in improving the efficiency, accuracy, and ease of EIS analysis and thus creates an avenue to the widespread use of EIS in accelerating the development of new electrochemical materials and devices.

cond-mat.mtrl-sci↗

arXiv2023

On Dynamical Parameter Space of Cubic Polynomials with a Parabolic Fixed Point

This article focus on the connected locus of the cubic polynomial slice $Per_1(λ)$ with a parabolic fixed point of multiplier $λ=e^{2πi\frac{p}{q}}$. We first show that any parabolic component, which is a parallel notion of hyperbolic component, is a Jordan domain. Moreover, a continuum $\mathcal{K}_λ$ called the central part in the connected locus is defined. This is the natural analogue to the closure of the main hyperbolic component of $Per_1(0)$. We prove that $\mathcal{K}_λ$ is almost a double covering of the filled-in Julia set of the quadratic polynomial $P_λ(z) = λz+z^2$.

math.DS↗