Searcharxiv⌕ Search

arXiv subjects

Qianli Ma

Publications and source records attributed to Qianli Ma.

123 records · Page 7Linked to original sources
arXiv2021

SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements

Learning to model and reconstruct humans in clothing is challenging due to articulation, non-rigid deformation, and varying clothing types and topologies. To enable learning, the choice of representation is the key. Recent work uses neural networks to parameterize local surface elements. This approach captures locally coherent geometry and non-planar details, can deal with varying topology, and does not require registered training data. However, naively using such methods to model 3D clothed humans fails to capture fine-grained local deformations and generalizes poorly. To address this, we present three key innovations: First, we deform surface elements based on a human body model such that large-scale deformations caused by articulation are explicitly separated from topological changes and local clothing deformations. Second, we address the limitations of existing neural surface elements by regressing local geometry from local features, significantly improving the expressiveness. Third, we learn a pose embedding on a 2D parameterization space that encodes posed body geometry, improving generalization to unseen poses by reducing non-local spurious correlations. We demonstrate the efficacy of our surface representation by learning models of complex clothing from point clouds. The clothing can change topology and deviate from the topology of the body. Once learned, we can animate previously unseen motions, producing high-quality point clouds, from which we generate realistic images with neural rendering. We assess the importance of each technical contribution and show that our approach outperforms the state-of-the-art methods in terms of reconstruction accuracy and inference time. The code is available for research purposes at https://qianlim.github.io/SCALE .

cs.CV↗
arXiv2021

SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks

We present SCANimate, an end-to-end trainable framework that takes raw 3D scans of a clothed human and turns them into an animatable avatar. These avatars are driven by pose parameters and have realistic clothing that moves and deforms naturally. SCANimate does not rely on a customized mesh template or surface mesh registration. We observe that fitting a parametric 3D body model, like SMPL, to a clothed human scan is tractable while surface registration of the body topology to the scan is often not, because clothing can deviate significantly from the body shape. We also observe that articulated transformations are invertible, resulting in geometric cycle consistency in the posed and unposed shapes. These observations lead us to a weakly supervised learning method that aligns scans into a canonical pose by disentangling articulated deformations without template-based surface registration. Furthermore, to complete missing regions in the aligned scans while modeling pose-dependent deformations, we introduce a locally pose-aware implicit function that learns to complete and model geometry with learned pose correctives. In contrast to commonly used global pose embeddings, our local pose conditioning significantly reduces long-range spurious correlations and improves generalization to unseen poses, especially when training data is limited. Our method can be applied to pose-aware appearance modeling to generate a fully textured avatar. We demonstrate our approach on various clothing types with different amounts of training data, outperforming existing solutions and other variants in terms of fidelity and generality in every setting. The code is available at https://scanimate.is.tue.mpg.de.

cs.CV↗
arXiv2020

PLACE: Proximity Learning of Articulation and Contact in 3D Environments

High fidelity digital 3D environments have been proposed in recent years, however, it remains extremely challenging to automatically equip such environment with realistic human bodies. Existing work utilizes images, depth or semantic maps to represent the scene, and parametric human models to represent 3D bodies. While being straightforward, their generated human-scene interactions are often lack of naturalness and physical plausibility. Our key observation is that humans interact with the world through body-scene contact. To synthesize realistic human-scene interactions, it is essential to effectively represent the physical contact and proximity between the body and the world. To that end, we propose a novel interaction generation method, named PLACE (Proximity Learning of Articulation and Contact in 3D Environments), which explicitly models the proximity between the human body and the 3D scene around it. Specifically, given a set of basis points on a scene mesh, we leverage a conditional variational autoencoder to synthesize the minimum distances from the basis points to the human body surface. The generated proximal relationship exhibits which region of the scene is in contact with the person. Furthermore, based on such synthesized proximity, we are able to effectively obtain expressive 3D human bodies that interact with the 3D scene naturally. Our perceptual study shows that PLACE significantly improves the state-of-the-art method, approaching the realism of real human-scene interaction. We believe our method makes an important step towards the fully automatic synthesis of realistic 3D human bodies in 3D scenes. The code and model are available for research at https://sanweiliti.github.io/PLACE/PLACE.html.

cs.CV↗
arXiv2020

Parallel Spin Stripes and Their Coexistance with Superconducting Ground States at Optimal and High Doping in La$_{1.6-x}$Nd$_{0.4}$Sr$_x$CuO$_4$

Quasi-two dimensional quantum magnetism is clearly highly correlated with superconducting ground states in cuprate-based High T$_c$ superconductivity. Three dimensional, commensurate long range magnetic order in La$_2$CuO$_4$ quickly evolves to quasi-two dimensional, incommensurate correlations on doping with mobile holes, and superconducting ground states follow for x as small as 0.05 in the La$_{2-x}$Sr$_x$/Ba$_x$CuO$_4$ family of superconductors. It has long been known that the onset of superconducting ground states in these systems is coincident with a remarkable rotation of the incommensurate spin order from "diagonal stripes" below x = 0.05, to "parallel stripes" above. However, little is known about the spin correlations at optimal and high doping levels, where the dome of superconductivity draws to an end. Here we present new elastic and inelastic neutron scattering measurements on single crystals of La$_{1.6-x}$Nd$_{0.4}$Sr$_x$CuO$_4$ with x = 0.125, 0.19, 0.24 and 0.26, and show that two dimensional, quasi-static, parallel spin stripes are observed to onset at temperatures such that the parallel spin stripe phase envelopes all superconducting ground states in this system. Parallel spin stripes stretch across 0.05 < < 0.26, with rapidly decreasing moment size and onset temperatures for x > 0.125. We also show that the low energy, parallel spin stripe fluctuations for optimally doped x = 0.19 display dynamic spectral weight which grows with decreasing temperature and saturates below its superconducting T$_c$. The elastic order parameter for x = 0.19 also shows plateau behavior coincident with the onset of superconductivity. This set of observations assert the foundational role played by two dimensional parallel spin stripe order and fluctuations in High T$_c$ cuprate superconductivity.

cond-mat.supr-con↗
arXiv2020

Materials preparation, single crystal growth, and the phase diagram of the cuprate high temperature superconductor La1.6-xNd0.4SrxCuO4

One branch of the La-214 family of cuprate superconductors, La1.6-xNd0.4SrxCuO4 (Nd-LSCO), has been of significant and sustained interest, in large part because it displays the full complexity of the phase diagram for canonical hole-doped, high Tc superconductivity, while also displaying relatively low superconducting critical temperatures. The low superconducting Tc's imply that experimentally accessible magnetic fields can suppress the superconductivity to zero temperature. In particular, this has enabled various transport and thermodynamic studies of the T = 0 ground state in Nd-LSCO, free of superconductivity, across the critical doping p* = 0.23 where the pseudogap phase ends. The strong dependence of its superconducting properties on its crystal symmetry has itself motivated careful studies of the Nd-LSCO structural phase diagram. This paper provides a systematic study and summary of the materials preparation and characterization of both single crystal and polycrystalline samples of Nd-LSCO. Single-phase polycrystalline samples with x spanning the range from 0.01 to 0.40 have been synthesized, and large single crystals of Nd-LSCO for select x across the region (0.07, 0.12, 0.17, 0.19, 0.225, 0.24, and 0.26) were grown by the optical floating zone method. Systematic neutron and X-ray diffraction studies on these samples were performed at both low and room temperatures, 10 K and 300 K, respectively. These studies allowed us to follow the various structural phase transitions and propose an updated structural phase diagram for Nd-LSCO. In particular, we found that the low-temperature tetragonal (LTT) phase ends at a critical doping pLTT = 0.255(5), clearly separated from p*.

cond-mat.supr-con↗
arXiv2020

Learning to Dress 3D People in Generative Clothing

Three-dimensional human body models are widely used in the analysis of human pose and motion. Existing models, however, are learned from minimally-clothed 3D scans and thus do not generalize to the complexity of dressed people in common images and videos. Additionally, current models lack the expressive power needed to represent the complex non-linear geometry of pose-dependent clothing shapes. To address this, we learn a generative 3D mesh model of clothed people from 3D scans with varying pose and clothing. Specifically, we train a conditional Mesh-VAE-GAN to learn the clothing deformation from the SMPL body model, making clothing an additional term in SMPL. Our model is conditioned on both pose and clothing type, giving the ability to draw samples of clothing to dress different body shapes in a variety of styles and poses. To preserve wrinkle detail, our Mesh-VAE-GAN extends patchwise discriminators to 3D meshes. Our model, named CAPE, represents global shape and fine local structure, effectively extending the SMPL body model to clothing. To our knowledge, this is the first generative model that directly dresses 3D human body meshes and generalizes to different poses. The model, code and data are available for research purposes at https://cape.is.tue.mpg.de.

cs.CV↗
arXiv2020

Frontal Low-rank Random Tensors for Fine-grained Action Segmentation

Fine-grained action segmentation in long untrimmed videos is an important task for many applications such as surveillance, robotics, and human-computer interaction. To understand subtle and precise actions within a long time period, second-order information (e.g. feature covariance) or higher is reported to be effective in the literature. However, extracting such high-order information is considerably non-trivial. In particular, the dimensionality increases exponentially with the information order, and hence gaining more representation power also increases the computational cost and the risk of overfitting. In this paper, we propose an approach to representing high-order information for temporal action segmentation via a simple yet effective bilinear form. Specifically, our contributions are: (1) From the multilinear perspective, we derive a bilinear form of low complexity, assuming that the three-way tensor has low-rank frontal slices. (2) Rather than learning the tensor entries from data, we sample the entries from different underlying distributions, and prove that the underlying distribution influences the information order. (3) We employed our bilinear form as an intermediate layer in state-of-the-art deep neural networks, enabling to represent high-order information in complex deep models effectively and efficiently. Our experimental results demonstrate that the proposed bilinear form outperforms the previous state-of-the-art methods on the challenging temporal action segmentation task. One can see our project page for data, model and code: \url{https://vlg.inf.ethz.ch/projects/BilinearTCN/}.

cs.LG↗
arXiv2019

Unified Attentional Generative Adversarial Network for Brain Tumor Segmentation From Multimodal Unpaired Images

In medical applications, the same anatomical structures may be observed in multiple modalities despite the different image characteristics. Currently, most deep models for multimodal segmentation rely on paired registered images. However, multimodal paired registered images are difficult to obtain in many cases. Therefore, developing a model that can segment the target objects from different modalities with unpaired images is significant for many clinical applications. In this work, we propose a novel two-stream translation and segmentation unified attentional generative adversarial network (UAGAN), which can perform any-to-any image modality translation and segment the target objects simultaneously in the case where two or more modalities are available. The translation stream is used to capture modality-invariant features of the target anatomical structures. In addition, to focus on segmentation-related features, we add attentional blocks to extract valuable features from the translation stream. Experiments on three-modality brain tumor segmentation indicate that UAGAN outperforms the existing methods in most cases.

cs.CV↗
arXiv2019

Identifying the magnetospheric driver of STEVE

For the first time, we identify the magnetospheric driver of STEVE, east-west aligned narrow emissions in the subauroral region. In the ionosphere, STEVE is associated with subauroral ion drift (SAID) features of high electron temperature peak, density gradient, and strong westward ion flow. In this study, we present STEVE's magnetospheric driver region at a sharp plasmapause containing: strong tailward quasi-static electric field, kinetic Alfven waves, parallel electron acceleration, perpendicular ion drift. The observed continuous emissions of STEVE are possibly caused by ionospheric electron heating due to heat conduction and/or auroral acceleration process powered by Alfven waves, both driven by the observed equatorial magnetospheric processes. The observed green emissions are likely optical manifestations of electron precipitations associated with wave structures traveling along the plasmapause. The observed SAR arc at lower latitudes likely corresponds to the formation of low-energy plasma inside the plasmapause by Coulomb collisions between ring current ions and plasmaspheric plasma.

physics.space-ph↗
arXiv2018

Classification of lung nodules in CT images based on Wasserstein distance in differential geometry

Lung nodules are commonly detected in screening for patients with a risk for lung cancer. Though the status of large nodules can be easily diagnosed by fine needle biopsy or bronchoscopy, small nodules are often difficult to classify on computed tomography (CT). Recent works have shown that shape analysis of lung nodules can be used to differentiate benign lesions from malignant ones, though existing methods are limited in their sensitivity and specificity. In this work we introduced a new 3D shape analysis within the framework of differential geometry to calculate the Wasserstein distance between benign and malignant lung nodules to derive an accurate classification scheme. The Wasserstein distance between the nodules is calculated based on our new spherical optimal mass transport, this new algorithm works directly on sphere by using spherical metric, which is much more accurate and efficient than previous methods. In the process of deformation, the area-distortion factor gives a probability measure on the unit sphere, which forms the Wasserstein space. From known cases of benign and malignant lung nodules, we can calculate a unique optimal mass transport map between their correspondingly deformed Wasserstein spaces. This transportation cost defines the Wasserstein distance between them and can be used to classify new lung nodules into either the benign or malignant class. To the best of our knowledge, this is the first work that utilizes Wasserstein distance for lung nodule classification. The advantages of Wasserstein distance are it is invariant under rigid motions and scalings, thus it intrinsically measures shape distance even when the underlying shapes are of high complexity, making it well suited to classify lung nodules as they have different sizes, orientations, and appearances.

q-bio.QM↗
arXiv2017

Deep-ESN: A Multiple Projection-encoding Hierarchical Reservoir Computing Framework

As an efficient recurrent neural network (RNN) model, reservoir computing (RC) models, such as Echo State Networks, have attracted widespread attention in the last decade. However, while they have had great success with time series data [1], [2], many time series have a multiscale structure, which a single-hidden-layer RC model may have difficulty capturing. In this paper, we propose a novel hierarchical reservoir computing framework we call Deep Echo State Networks (Deep-ESNs). The most distinctive feature of a Deep-ESN is its ability to deal with time series through hierarchical projections. Specifically, when an input time series is projected into the high-dimensional echo-state space of a reservoir, a subsequent encoding layer (e.g., a PCA, autoencoder, or a random projection) can project the echo-state representations into a lower-dimensional space. These low-dimensional representations can then be processed by another ESN. By using projection layers and encoding layers alternately in the hierarchical framework, a Deep-ESN can not only attenuate the effects of the collinearity problem in ESNs, but also fully take advantage of the temporal kernel property of ESNs to explore multiscale dynamics of time series. To fuse the multiscale representations obtained by each reservoir, we add connections from each encoding layer to the last output layer. Theoretical analyses prove that stability of a Deep-ESN is guaranteed by the echo state property (ESP), and the time complexity is equivalent to a conventional ESN. Experimental results on some artificial and real world time series demonstrate that Deep-ESNs can capture multiscale dynamics, and outperform both standard ESNs and previous hierarchical ESN-based models.

cs.LG↗
arXiv2016

Theano: A Python framework for fast computation of mathematical expressions

Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements. Theano is being actively and continuously developed since 2008, multiple frameworks have been built on top of it and it has been used to produce many state-of-the-art machine learning models. The present article is structured as follows. Section I provides an overview of the Theano software and its community. Section II presents the principal features of Theano and how to use them, and compares them with other similar projects. Section III focuses on recently-introduced functionalities and improvements. Section IV compares the performance of Theano against Torch7 and TensorFlow on several machine learning models. Section V discusses current limitations of Theano and potential ways of improving it.

cs.SC↗
arXiv2012

Resonances in rotationally inelastic scattering of OH($X^2Π$) with helium and neon

We present detailed calculations on resonances in rotationally and spin-orbit inelastic scattering of OH ($X\,^2Π, j=3/2, F_1, f$) radicals with He and Ne atoms. We calculate new \emph{ab initio} potential energy surfaces for OH-He, and the cross sections derived from these surfaces compare favorably with the recent crossed beam scattering experiment of Kirste \emph{et al.} [Phys. Rev. A \textbf{82}, 042717 (2010)]. We identify both shape and Feshbach resonances in the integral and differential state-to-state scattering cross sections, and we discuss the prospects for experimentally observing scattering resonances using Stark decelerated beams of OH radicals.

physics.atom-ph↗
arXiv2007

Manipulation of the quantum state by Majorana transition in spinor Bose-Einstein condensates

Manipulation of the quantum state by the Majorana transition in spinor BEC system has been realized by altering the rotation frequency of the magnetic field's direction. This kind of manipulation method has no limitation on the transition speed in principle and the system is well closed, which provides a new and superior tool to manipulate quantum states. Using this methord on pulsed atom laser, multicomponent spinor atom laser is generated. We demonstrate that the experiment results are agreed with the theoretical predication.

quant-ph↗