arXiv subjects

Tingting Shen

Publications and source records attributed to Tingting Shen.

9 recordsLinked to original sources

arXiv2025

HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation

Recent advances in generative models have achieved high-fidelity in 3D human reconstruction, yet their utility for specific tasks (e.g., human 3D segmentation) remains constrained. We propose HumanCrafter, a unified framework that enables the joint modeling of appearance and human-part semantics from a single image in a feed-forward manner. Specifically, we integrate human geometric priors in the reconstruction stage and self-supervised semantic priors in the segmentation stage. To address labeled 3D human datasets scarcity, we further develop an interactive annotation procedure for generating high-quality data-label pairs. Our pixel-aligned aggregation enables cross-task synergy, while the multi-task objective simultaneously optimizes texture modeling fidelity and semantic consistency. Extensive experiments demonstrate that HumanCrafter surpasses existing state-of-the-art methods in both 3D human-part segmentation and 3D human reconstruction from a single image.

cs.CV↗

arXiv2025

ID-Crafter: VLM-Grounded Online RL for Compositional Multi-Subject Video Generation

Significant progress has been achieved in high-fidelity video synthesis, yet current paradigms often fall short in effectively integrating identity information from multiple subjects. This leads to semantic conflicts and suboptimal performance in preserving identities and interactions, limiting controllability and applicability. To tackle this issue, we introduce ID-Crafter, a framework for multi-subject video generation that achieves superior identity preservation and semantic coherence. ID-Crafter integrates three key components: (i) a hierarchical identity-preserving attention mechanism that progressively aggregates features at intra-subject, inter-subject, and cross-modal levels; (ii) a semantic understanding module powered by a pretrained Vision-Language Model (VLM) to provide fine-grained guidance and capture complex inter-subject relationships; and (iii) an online reinforcement learning phase to further refine the model for critical concepts. Furthermore, we construct a new dataset to facilitate robust training and evaluation. Extensive experiments demonstrate that ID-Crafter establishes new state-of-the-art performance on multi-subject video generation benchmarks, excelling in identity preservation, temporal consistency, and overall video quality. Project page: https://angericky.github.io/ID-Crafter

cs.CV↗

arXiv2024

HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors

Despite recent advancements in high-fidelity human reconstruction techniques, the requirements for densely captured images or time-consuming per-instance optimization significantly hinder their applications in broader scenarios. To tackle these issues, we present HumanSplat which predicts the 3D Gaussian Splatting properties of any human from a single input image in a generalizable manner. In particular, HumanSplat comprises a 2D multi-view diffusion model and a latent reconstruction transformer with human structure priors that adeptly integrate geometric priors and semantic features within a unified framework. A hierarchical loss that incorporates human semantic information is further designed to achieve high-fidelity texture modeling and better constrain the estimated multiple views. Comprehensive experiments on standard benchmarks and in-the-wild images demonstrate that HumanSplat surpasses existing state-of-the-art methods in achieving photorealistic novel-view synthesis.

cs.CV↗

arXiv2023

A Magnetoelectric Memory Device Based on Pseudo-Magnetization

We propose a new type of magnetoelectric memory device that stores magnetic easy-axis information or pseudo-magnetization, rather than a definite magnetization direction, in piezoelectric/ferromagnetic (PE/FM) heterostructures. Theoretically, we show how a PE/FM combination can lead to non-volatility in pseudo-magnetization exhibiting ferroelectric-like behavior. The pseudo-magnetization can be manipulated by extremely low voltages especially when the FM is a low-barrier nanomagnet. Using a circuit model benchmarked against experiments, we determine the switching energy, delay, switching probability and retention time of the envisioned 1T/1C memory device in terms of magnetic and circuit parameters and discuss its thermal stability in terms of a key parameter called back-voltage vm which is an electrical measure of the strain-induced magnetic field. Taking advantage of ferromagnetic resonance (FMR) measurements, we experimentally extract values for vm in CoFeB films and circular nano-magnets deposited on Pb(Mg1/3Nb2/3)0.7Ti0.3O3 (PMN-PT) which agree well with the theoretical values. Our experimental findings indeed indicate the feasibility of the proposed novel device and confirm the assumed parameters in our modeling effort.

physics.app-ph↗

arXiv2022

Adaptive Weighted Nonnegative Matrix Factorization for Robust Feature Representation

Nonnegative matrix factorization (NMF) has been widely used to dimensionality reduction in machine learning. However, the traditional NMF does not properly handle outliers, so that it is sensitive to noise. In order to improve the robustness of NMF, this paper proposes an adaptive weighted NMF, which introduces weights to emphasize the different importance of each data point, thus the algorithmic sensitivity to noisy data is decreased. It is very different from the existing robust NMFs that use a slow growth similarity measure. Specifically, two strategies are proposed to achieve this: fuzzier weighted technique and entropy weighted regularized technique, and both of them lead to an iterative solution with a simple form. Experimental results showed that new methods have more robust feature representation on several real datasets with noise than exsiting methods.

cs.LG↗

arXiv2022

Subspace Nonnegative Matrix Factorization for Feature Representation

Traditional nonnegative matrix factorization (NMF) learns a new feature representation on the whole data space, which means treating all features equally. However, a subspace is often sufficient for accurate representation in practical applications, and redundant features can be invalid or even harmful. For example, if a camera has some sensors destroyed, then the corresponding pixels in the photos from this camera are not helpful to identify the content, which means only the subspace consisting of remaining pixels is worthy of attention. This paper proposes a new NMF method by introducing adaptive weights to identify key features in the original space so that only a subspace involves generating the new representation. Two strategies are proposed to achieve this: the fuzzier weighted technique and entropy regularized weighted technique, both of which result in an iterative solution with a simple form. Experimental results on several real-world datasets demonstrated that the proposed methods can generate a more accurate feature representation than existing methods. The code developed in this study is available at https://github.com/WNMF1/FWNMF-ERWNMF.

cs.CV↗

arXiv2021

Electric field control of interaction between magnons and quantum spin defects

Hybrid systems coupling quantum spin defects (QSD) and magnons can enable unique spintronic device functionalities and probes for magnetism. Here, we add electric field control of magnon-QSD coupling to such systems by integrating ferromagnet-ferroelectric multiferroic with nitrogen-vacancy (NV) center spins. Combining quantum relaxometry with ferromagnetic resonance measurements and analytical modeling, we reveal that the observed electric-field tuning results from ferroelectric polarization control of the magnon-generated fields at the NV. Exploiting the demonstrated control, we also propose magnon-enhanced hybrid electric field sensors with improved sensitivity.

cond-mat.mes-hall↗

arXiv2019

Demonstration of a strain-mediated magnetoelectric write and read unit in a Co60Fe20B20/ Pb(Mg1/3Nb2/3)0.7Ti0.3O3 heterostructure

Taking advantage of the Magnetoelectric (ME) and its inverse effect, this article demonstrates strain-mediated magnetoelectric write and read operations simultaneously in Co60Fe20B20/ Pb(Mg1/3Nb2/3)0.7Ti0.3O3 heterostructures without using any symmetry breaking magnetic field at room temperature. By applying an external DC-voltage across a (011)-cut PMN-PT substrate, the ferroelectric polarization is re-oriented, which results in an anisotropic in-plane strain that transfers to the CoFeB thin film and changes its magnetic anisotropy Hk. The change in Hk in-turn results in a 90o rotation of the magnetic easy axis for sufficiently high voltages. Simultaneously, the inverse effect is employed to read changes of the magnetic properties. Because the Piezoelectric (PE)/FerroMagnetic (FM) system is fully coupled, the change of magnetization in FM induces an elastic stress in the PE layer, which generates a piezoelectric potential in the system that can be used to readout the magnetic state of the FM layer. Our experimental results are in excellent qualitative agreement with a recently proposed, experimentally benchmarked equivalent circuit model that considers how magnetic properties are electrically controlled in such ME/PE heterostructure and how a back-voltage is generated due to changing magnetic properties in a self-consistent model.

physics.app-ph↗

arXiv2018

Studies of two-dimensional MoS2 on enhancing the electrical performance of ultrathin copper films

Copper nanowires are widely used as on-chip interconnects due to superior conductivity. However, with aggressive Cu interconnect scaling, the diffusive surface scattering of electrons drastically increases the electrical resistivity. In this work, we studied the electrical performance of Cu thin films on different materials. By comparing the thickness dependence of Cu films resistivity on MoS2 and SiO2, we demonstrated that two-dimensional MoS2 can be used to enhance the electrical performance of ultrathin Cu films due to a partial specular surface scattering. By fitting the experimental data with the theoretical Fuchs Sondheimer model, we obtained the specularity parameter at the Cu MoS2 interface in the temperature range 2K to 300K. Furthermore, first principle calculations based on the density functional theory indicates that there are more localized states at the Cu amorphous SiO2 interface than the Cu MoS2 interface which is responsible for the higher resistivity in the Cu SiO2 heterostructure due to more severe electron scattering. Our results suggest that Cu MoS2 hybrid is a promising candidate structure for the future generations of CMOS interconnects.

physics.app-ph↗