arXiv subjects

Jing Tian

Publications and source records attributed to Jing Tian.

At least 19 recordsLinked to original sources

arXiv2026

UNICA: A Unified Neural Framework for Controllable 3D Avatars

Controllable 3D human avatars have found widespread applications in 3D games, the metaverse, and AR/VR scenarios. The conventional approach to creating such a 3D avatar requires a lengthy, intricate pipeline encompassing appearance modeling, motion planning, rigging, and physical simulation. In this paper, we introduce UNICA (UNIfied neural Controllable Avatar), a skeleton-free generative model that unifies all avatar control components into a single neural framework. Given keyboard inputs akin to video game controls, UNICA generates the next frame of a 3D avatar's geometry through an action-conditioned diffusion model operating on 2D position maps. A point transformer then maps the resulting geometry to 3D Gaussian Splatting for high-fidelity free-view rendering. Our approach naturally captures hair and loose clothing dynamics without manually designed physical simulation, and supports extra-long autoregressive generation. To the best of our knowledge, UNICA is the first model to unify the workflow of "motion planning, rigging, physical simulation, and rendering". Code is released at https://github.com/zjh21/UNICA.

cs.CV↗

arXiv2026

CrowdGaussian: Reconstructing High-Fidelity 3D Gaussians for Human Crowd from a Single Image

Single-view 3D human reconstruction has garnered significant attention in recent years. Despite numerous advancements, prior research has concentrated on reconstructing 3D models from clear, close-up images of individual subjects, often yielding subpar results in the more prevalent multi-person scenarios. Reconstructing 3D human crowd models is a highly intricate task, laden with challenges such as: 1) extensive occlusions, 2) low clarity, and 3) numerous and various appearances. To address this task, we propose CrowdGaussian, a unified framework that directly reconstructs multi-person 3D Gaussian Splatting (3DGS) representations from single-image inputs. To handle occlusions, we devise a self-supervised adaptation pipeline that enables the pretrained large human model to reconstruct complete 3D humans with plausible geometry and appearance from heavily occluded inputs. Furthermore, we introduce Self-Calibrated Learning (SCL). This training strategy enables single-step diffusion models to adaptively refine coarse renderings to optimal quality by blending identity-preserving samples with clean/corrupted image pairs. The outputs can be distilled back to enhance the quality of multi-person 3DGS representations. Extensive experiments demonstrate that CrowdGaussian generates photorealistic, geometrically coherent reconstructions of multi-person scenes.

cs.CV↗

arXiv2026

Independent mutual-visibility sets and distance edge-critical graphs

In this paper, connections between independent sets and the variety of mutual-visibility sets are studied. It is proved that every outer mutual-visibility set of a graph is independent if and only if the graph is distance edge-critical. Several constructions yielding distance edge-critical graphs are given. Graphs in which every independent set is a total mutual-visibility or a dual mutual-visibility set are characterized, as well as graphs in which every total mutual-visibility set is independent. Along the way the total mutual-visibility number of some graphs derived from fullerenes is determined. Graphs in which every independent set is a mutual-visibility set are discussed and characterized over diameter four graphs. It is proved that determining the maximum cardinality of an independent mutual-visibility set and deciding whether it equals the independence number of a graph are NP-hard problems, and the same is true for independent total, outer and dual mutual-visibility sets.

math.CO↗

arXiv2025

Recovering the Parameter $\alpha$ in the Simplified Bardina Model through Continuous Data Assimilation

In this study, we develop a continuous data assimilation algorithm to recover the parameter $\alpha$ in the simplified Bardina model. Our method utilizes the observations of finitely many Fourier modes by using a nudging framework that involves recursive parameter updates. We provide a rigorous convergence analysis, showing that the approximate parameter approaches the true value under suitable conditions, while the approximate solution also converges to the true solution.

math.DS↗

arXiv2025

On the variety of general position problems under vertex and edge removal

Let ${\rm gp}_{\rm t}(G)$, ${\rm gp}_{\rm o}(G)$, and ${\rm gp}_{\rm d}(G)$ be the total, the outer, and the dual general position number of a graph $G$, respectively. This paper investigates how removing a vertex or removing an edge affects these graph invariants. It is proved that if $x$ is not a cut vertex, then ${\rm gp}_{\rm t}(G) -1 \le {\rm gp}_{\rm t}(G-x) \le {\rm gp}_{\rm t}(G) + {\rm deg}_G(x)$. On the other hand, ${\rm gp}_{\rm o}(G-x)$ and ${\rm gp}_{\rm d}(G-x)$ can be respectively arbitrarily larger/smaller than ${\rm gp}_{\rm o}(G)$ and ${\rm gp}_{\rm d}(G)$. On the positive side, it is proved that if $x$ lies in some ${\rm gp}_{\rm o}$-set, then ${\rm gp}_{\rm o}(G)-1 \le {\rm gp}_{\rm o}(G-x)$, and that if $x$ is not a cut vertex and lies in some ${\rm gp}_{\rm d}$-set of $G$, then $ {\rm gp}_{\rm d}(G)-1 \le {\rm gp}_{\rm d}(G-x)$. For the edge removal, it is proved that (i) ${\rm gp}_{\rm t}(G) -|S(G)_{e}| \le {\rm gp}_{\rm t}(G-e) \le {\rm gp}_{\rm t}(G) +2$, where $S(G)_{e}$ is the set of simplicial vertices adjacent to both endvertices of $e$, (ii) ${\rm gp}_{\rm o}(G)/2\le {\rm gp}_{\rm o}(G-e)\leq\ 2{\rm gp}_{\rm o}(G)$, and (iii) that ${\rm gp}_{\rm d}(G) - {\rm gp}_{\rm d}(G-e)$ can be arbitrarily large. All bounds are demonstrated to be sharp.

math.CO↗

arXiv2025

ArtVIP: Articulated Digital Assets of Visual Realism, Modular Interaction, and Physical Fidelity for Robot Learning

Robot learning increasingly relies on simulation to advance complex ability such as dexterous manipulations and precise interactions, necessitating high-quality digital assets to bridge the sim-to-real gap. However, existing open-source articulated-object datasets for simulation are limited by insufficient visual realism and low physical fidelity, which hinder their utility for training models mastering robotic tasks in real world. To address these challenges, we introduce ArtVIP, a comprehensive open-source dataset comprising high-quality digital-twin articulated objects, accompanied by indoor-scene assets. Crafted by professional 3D modelers adhering to unified standards, ArtVIP ensures visual realism through precise geometric meshes and high-resolution textures, while physical fidelity is achieved via fine-tuned dynamic parameters. Meanwhile, the dataset pioneers embedded modular interaction behaviors within assets and pixel-level affordance annotations. Feature-map visualization and optical motion capture are employed to quantitatively demonstrate ArtVIP's visual and physical fidelity, with its applicability validated across imitation learning and reinforcement learning experiments. Provided in USD format with detailed production guidelines, ArtVIP is fully open-source, benefiting the research community and advancing robot learning research. Our project is at https://x-humanoid-artvip.github.io/ .

cs.RO↗

arXiv2025

Varieties of mutual-visibility and general position on Sierpi\'nski graphs

The variety of mutual-visibility problems contains four members, as does the variety of general position problems. The basic problem is to determine the cardinality of the largest such sets. In this paper, these eight invariants are investigated on Sierpi\'nski graphs $S_p^n$. They are determined for the Sierpi\'nski graphs $S_p^2$, $p\ge 3$. All, but the outer mutual-visibility number and the outer general position number, are also determined for $S_3^n$, $n\ge 3$. In many of the cases the corresponding extremal sets are enumerated.

math.CO↗

arXiv2024

Visibility polynomials, dual visibility spectrum, and characterization of total mutual-visibility sets

Mutual-visibility sets were motivated by visibility in distributed systems and social networks, and intertwine with several classical mathematical areas. Monotone properties of the variety of mutual-visibility sets, and restrictions of such sets to convex and isometric subgraphs are studied. Dual mutual-visibility sets are shown to be intrinsically different from other types of mutual-visibility sets. It is proved that for every finite subset $Z$ of positive integers there exists a graph $G$ that has a dual mutual-visibility set of size $i$ if and only if $i\in Z\cup \{0\}$, while for the other types of mutual-visibility such a set consists of consecutive integers. Visibility polynomials are introduced and their properties derived. As a surprise, every polynomial with nonnegative integer coefficients and with a constant term $1$ is a dual visibility polynomial of some graph. Characterizations are given for total mutual-visibility sets, for graphs with total mutual-visibility number $1$, and for sets which are not total mutual-visibility sets, yet every proper subset is such. Along the way an earlier result from the literature is corrected.

math.CO↗

arXiv2024

Parameter Error Analysis for the 3D Modified Leray-alpha Model: Analytical and Numerical Approaches

In this study, we conduct a parameter error analysis for the 3D modified Leray-$\alpha$ model using both analytical and numerical approaches. We first prove the global well-posedness and continuous dependence of initial data for the assimilated system. Furthermore, given sufficient conditions on the physical parameters and norms of the true solution, we demonstrate that the true solution can be recovered from the approximation solution, with an error determined by the discrepancy between the true and approximating parameters. Numerical simulations are provided to validate the convergence criteria.

math.NA↗

arXiv2024

Conjugate-dual clusters

Discovery of clusters with high symmetrical geometry, such as C60 fullerene, always attract lots of interest because of their diverse nature. However, most of such interesting cluster were sporadically discovered, is there any systematic method to explore all possible high symmetrical clusters? Herein, we propose an idea to systematically construct high symmetrical structures based on novel conjugate-dual (co-dual) concept. A co-dual structure would be constructed by conjugately combining one high symmetrical polyhedron and its corresponding dual. In such co-dual structures, the symmetry of the original polyhedron could be kept or even promoted in some special cases. This provides a way to explore high symmetrical polyhedra and leads to a new cluster family, co-dual clusters. In this paper, we have systematically studied the spherical co-dual clusters with one- or two-element shells, and found a series of stable cage-like and core-shell clusters. The co-dual structures would be a new treasure box for hunting novel clusters.

cond-mat.mtrl-sci↗

arXiv2024

HCDN: A Change Detection Network for Construction Housekeeping Using Feature Fusion and Large Vision Models

Workplace safety has received increasing attention as millions of workers worldwide suffer from work-related accidents. Despite poor housekeeping is a significant contributor to construction accidents, there remains a significant lack of technological research focused on improving housekeeping practices in construction sites. Recognizing and locating poor housekeeping in a dynamic construction site is an important task that can be improved through computer vision approaches. Despite advances in AI and computer vision, existing methods for detecting poor housekeeping conditions face many challenges, including limited explanations, lack of locating of poor housekeeping, and lack of annotated datasets. On the other hand, change detection which aims to detect the changed environmental conditions (e.g., changing from good to poor housekeeping) and 'where' the change has occurred (e.g., location of objects causing poor housekeeping), has not been explored to the problem of housekeeping management. To address these challenges, we propose the Housekeeping Change Detection Network (HCDN), an advanced change detection neural network that integrates a feature fusion module and a large vision model, achieving state-of-the-art performance. Additionally, we introduce the approach to establish a novel change detection dataset (named Housekeeping-CCD) focused on housekeeping in construction sites, along with a housekeeping segmentation dataset. Our contributions include significant performance improvements compared to existing methods, providing an effective tool for enhancing construction housekeeping and safety. To promote further development, we share our source code and trained models for global researchers: https://github.com/NUS-DBE/Housekeeping-CD.

cs.CV↗

arXiv2024

An Image-Guided Robotic System for Transcranial Magnetic Stimulation: System Development and Experimental Evaluation

Transcranial magnetic stimulation (TMS) is a noninvasive medical procedure that can modulate brain activity, and it is widely used in neuroscience and neurology research. Compared to manual operators, robots may improve the outcome of TMS due to their superior accuracy and repeatability. However, there has not been a widely accepted standard protocol for performing robotic TMS using fine-segmented brain images, resulting in arbitrary planned angles with respect to the true boundaries of the modulated cortex. Given that the recent study in TMS simulation suggests a noticeable difference in outcomes when using different anatomical details, cortical shape should play a more significant role in deciding the optimal TMS coil pose. In this work, we introduce an image-guided robotic system for TMS that focuses on (1) establishing standardized planning methods and heuristics to define a reference (true zero) for the coil poses and (2) solving the issue that the manual coil placement requires expert hand-eye coordination which often leading to low repeatability of the experiments. To validate the design of our robotic system, a phantom study and a preliminary human subject study were performed. Our results show that the robotic method can half the positional error and improve the rotational accuracy by up to two orders of magnitude. The accuracy is proven to be repeatable because the standard deviation of multiple trials is lowered by an order of magnitude. The improved actuation accuracy successfully translates to the TMS application, with a higher and more stable induced voltage in magnetic field sensors.

cs.RO↗

arXiv2024

Parameter Analysis in Continuous Data Assimilation for Various Turbulence Models

In this study, we conduct parameter estimation analysis on a data assimilation algorithm for two turbulence models: the simplified Bardina model and the Navier-Stokes-{\alpha} model. Our approach involves creating an approximate solution for the turbulence models by employing an interpolant operator based on the observational data of the systems. The estimation depends on the parameter alpha in the models. Additionally, numerical simulations are presented to validate our theoretical results

physics.flu-dyn↗

arXiv2024

General position problems in strong and lexicographic products of graphs

Outer, dual, and total general position sets are studied on strong and lexicographic products of graphs. Sharp lower and upper bounds are proved for the outer and the dual general position number of strong products and several exact values are obtained. For the lexicographic product, the outer general position number is determined in all the cases, and the dual general position number in many cases. The total general position number is determined for both products. Along the way some results on outer general position sets are also derived.

math.CO↗

arXiv2024

An Improved Two-Step Attack on Lattice-Based Cryptography: A Case Study of Kyber

After three rounds of post-quantum cryptography (PQC) strict evaluations conducted by NIST, CRYSTALS-Kyber was successfully selected in July 2022 and standardized in August 2024. It becomes urgent to further evaluate Kyber's physical security for the upcoming deployment phase. In this brief, we present an improved two-step attack on Kyber to quickly recover the full secret key, s, by using much fewer power traces and less time. In the first step, we use the correlation power analysis (CPA) to obtain a portion of guess values of s with a small number of power traces. The CPA is enhanced by utilizing both Pearson and Kendall's rank correlation coefficients and modifying the leakage model to improve the accuracy. In the second step, we adopt the lattice attack to recover s based on the results of CPA. The success rate is largely built up by constructing a trial-and-error method. We deploy the reference implementations of Kyber-512, -768, and -1024 on an ARM Cortex-M4 target board and successfully recover s in approximately 9~10 minutes with at most 15 power traces, using a Xeon Gold 6342-equipped machine for the attack.

cs.CR↗

arXiv2024

A Hardware-Friendly Shuffling Countermeasure Against Side-Channel Attacks for Kyber

CRYSTALS-Kyber has been standardized as the only key-encapsulation mechanism (KEM) scheme by NIST to withstand attacks by large-scale quantum computers. However, the side-channel attacks (SCAs) on its implementation are still needed to be well considered for the upcoming migration. In this brief, we propose a secure and efficient hardware implementation for Kyber by incorporating a novel compact shuffling architecture. First of all, we modify the Fisher-Yates shuffle to make it more hardware-friendly. We then design an optimized shuffling architecture for the well-known open-source Kyber hardware implementation to enhance the security of all known and potential side-channel leakage points. Finally, we implement the modified Kyber design on FPGA and evaluate its security and performance. The security is verified by conducting correlation power analysis (CPA) and test vector leakage assessment (TVLA) on the hardware. Meanwhile, FPGA place-and-route results show that the proposed design reports only 8.7% degradation on the hardware efficiency compared with the original unprotected version, much better than existing hardware hiding schemes.

cs.CR↗

arXiv2024

UVCPNet: A UAV-Vehicle Collaborative Perception Network for 3D Object Detection

With the advancement of collaborative perception, the role of aerial-ground collaborative perception, a crucial component, is becoming increasingly important. The demand for collaborative perception across different perspectives to construct more comprehensive perceptual information is growing. However, challenges arise due to the disparities in the field of view between cross-domain agents and their varying sensitivity to information in images. Additionally, when we transform image features into Bird's Eye View (BEV) features for collaboration, we need accurate depth information. To address these issues, we propose a framework specifically designed for aerial-ground collaboration. First, to mitigate the lack of datasets for aerial-ground collaboration, we develop a virtual dataset named V2U-COO for our research. Second, we design a Cross-Domain Cross-Adaptation (CDCA) module to align the target information obtained from different domains, thereby achieving more accurate perception results. Finally, we introduce a Collaborative Depth Optimization (CDO) module to obtain more precise depth estimation results, leading to more accurate perception outcomes. We conduct extensive experiments on both our virtual dataset and a public dataset to validate the effectiveness of our framework. Our experiments on the V2U-COO dataset and the DAIR-V2X dataset demonstrate that our method improves detection accuracy by 6.1% and 2.7%, respectively.

cs.CV↗

arXiv2024

The general position number under vertex and edge removal

Let ${\rm gp}(G)$ be the general position number of a graph $G$. It is proved that ${\rm gp}(G-x)\leq 2{\rm gp}(G)$ holds for any vertex $x$ of a connected graph $G$ and that if $x$ lies in some ${\rm gp}$-set of $G$, then ${\rm gp}(G) - 1 \le {\rm gp}(G-x)$. Constructions are given which show that ${\rm gp}(G-x)$ can be much larger than ${\rm gp}(G)$ also when $G-x$ is connected. For diameter $2$ graphs it is proved that ${\rm gp}(G-x) \le {\rm gp}(G)$, and that ${\rm gp}(G-x) \ge {\rm gp}(G) - 1$ when the diameter of $G-x$ remains $2$. It is demonstrated that ${\rm gp}(G)/2\le {\rm gp}(G-e)\leq 2{\rm gp}(G)$ holds for any edge $e$ of a graph $G$. For diameter $2$ graphs these results can be improved to ${\rm gp}(G)-1\le {\rm gp}(G-e)\leq\ {\rm gp}(G) + 1$. All these bounds are proved to be sharp.

math.CO↗