arXiv subjects

Changjian Li

Publications and source records attributed to Changjian Li.

At least 37 records · Page 2Linked to original sources

arXiv2025

DepthCues: Evaluating Monocular Depth Perception in Large Vision Models

Large-scale pre-trained vision models are becoming increasingly prevalent, offering expressive and generalizable visual representations that benefit various downstream tasks. Recent studies on the emergent properties of these models have revealed their high-level geometric understanding, in particular in the context of depth perception. However, it remains unclear how depth perception arises in these models without explicit depth supervision provided during pre-training. To investigate this, we examine whether the monocular depth cues, similar to those used by the human visual system, emerge in these models. We introduce a new benchmark, DepthCues, designed to evaluate depth cue understanding, and present findings across 20 diverse and representative pre-trained vision models. Our analysis shows that human-like depth cues emerge in more recent larger models. We also explore enhancing depth perception in large vision models by fine-tuning on DepthCues, and find that even without dense depth supervision, this improves depth estimation. To support further research, our benchmark and evaluation code will be made publicly available for studying depth perception in vision models.

cs.CV↗

arXiv2024

SpecSAR-Former: A Lightweight Transformer-based Network for Global LULC Mapping Using Integrated Sentinel-1 and Sentinel-2

Recent approaches in remote sensing have increasingly focused on multimodal data, driven by the growing availability of diverse earth observation datasets. Integrating complementary information from different modalities has shown substantial potential in enhancing semantic understanding. However, existing global multimodal datasets often lack the inclusion of Synthetic Aperture Radar (SAR) data, which excels at capturing texture and structural details. SAR, as a complementary perspective to other modalities, facilitates the utilization of spatial information for global land use and land cover (LULC). To address this gap, we introduce the Dynamic World+ dataset, expanding the current authoritative multispectral dataset, Dynamic World, with aligned SAR data. Additionally, to facilitate the combination of multispectral and SAR data, we propose a lightweight transformer architecture termed SpecSAR-Former. It incorporates two innovative modules, Dual Modal Enhancement Module (DMEM) and Mutual Modal Aggregation Module (MMAM), designed to exploit cross-information between the two modalities in a split-fusion manner. These modules enhance the model's ability to integrate spectral and spatial information, thereby improving the overall performance of global LULC semantic segmentation. Furthermore, we adopt an imbalanced parameter allocation strategy that assigns parameters to different modalities based on their importance and information density. Extensive experiments demonstrate that our network outperforms existing transformer and CNN-based models, achieving a mean Intersection over Union (mIoU) of 59.58%, an Overall Accuracy (OA) of 79.48%, and an F1 Score of 71.68% with only 26.70M parameters. The code will be available at https://github.com/Reagan1311/LULC_segmentation.

eess.IV↗

arXiv2024

Geometry-Aware Attenuation Learning for Sparse-View CBCT Reconstruction

Cone Beam Computed Tomography (CBCT) plays a vital role in clinical imaging. Traditional methods typically require hundreds of 2D X-ray projections to reconstruct a high-quality 3D CBCT image, leading to considerable radiation exposure. This has led to a growing interest in sparse-view CBCT reconstruction to reduce radiation doses. While recent advances, including deep learning and neural rendering algorithms, have made strides in this area, these methods either produce unsatisfactory results or suffer from time inefficiency of individual optimization. In this paper, we introduce a novel geometry-aware encoder-decoder framework to solve this problem. Our framework starts by encoding multi-view 2D features from various 2D X-ray projections with a 2D CNN encoder. Leveraging the geometry of CBCT scanning, it then back-projects the multi-view 2D features into the 3D space to formulate a comprehensive volumetric feature map, followed by a 3D CNN decoder to recover 3D CBCT image. Importantly, our approach respects the geometric relationship between 3D CBCT image and its 2D X-ray projections during feature back projection stage, and enjoys the prior knowledge learned from the data population. This ensures its adaptability in dealing with extremly sparse view inputs without individual training, such as scenarios with only 5 or 10 X-ray projections. Extensive evaluations on two simulated datasets and one real-world dataset demonstrate exceptional reconstruction quality and time efficiency of our method.

eess.IV↗

arXiv2024

DiffCSG: Differentiable CSG via Rasterization

Differentiable rendering is a key ingredient for inverse rendering and machine learning, as it allows to optimize scene parameters (shape, materials, lighting) to best fit target images. Differentiable rendering requires that each scene parameter relates to pixel values through differentiable operations. While 3D mesh rendering algorithms have been implemented in a differentiable way, these algorithms do not directly extend to Constructive-Solid-Geometry (CSG), a popular parametric representation of shapes, because the underlying boolean operations are typically performed with complex black-box mesh-processing libraries. We present an algorithm, DiffCSG, to render CSG models in a differentiable manner. Our algorithm builds upon CSG rasterization, which displays the result of boolean operations between primitives without explicitly computing the resulting mesh and, as such, bypasses black-box mesh processing. We describe how to implement CSG rasterization within a differentiable rendering pipeline, taking special care to apply antialiasing along primitive intersections to obtain gradients in such critical areas. Our algorithm is simple and fast, can be easily incorporated into modern machine learning setups, and enables a range of applications for computer-aided design, including direct and image-based editing of CSG primitives. Code and data: https://yyyyyhc.github.io/DiffCSG/.

cs.GR↗

arXiv2024

High quality epitaxial piezoelectric and ferroelectric wurtzite Al$_{1-x}$Sc$_x$N thin films

Piezoelectric and ferroelectric wurtzite are promising to reshape modern microelectronics because they can be easily integrated with mainstream semiconductor technology. Sc doped AlN (Al$_{1-x}$Sc$_x$N) has attracted much attention for its enhanced piezoelectric and emerging ferroelectric properties, yet the commonly used sputtering results in polycrystalline Al$_{1-x}$Sc$_x$N films with high leakage current. Here we report the pulsed laser deposition of single crystalline epitaxial Al$_{1-x}$Sc$_x$N thin films on sapphire and 4H-SiC substrates. Pure wurtzite phase is maintained up to $x = 0.3$ with minimal oxygen contamination. Polarization is estimated to be 140 $μ$C/cm$^2$ via atomic scale microscopy imaging and found to be switchable via a scanning probe. The piezoelectric coefficient is found to be 5 times of undoped one when $x = 0.3$, making it desirable for high frequency radiofrequency (RF) filters and three-dimensional nonvolatile memories.

physics.app-ph↗

arXiv2024

Looking 3D: Anomaly Detection with 2D-3D Alignment

Automatic anomaly detection based on visual cues holds practical significance in various domains, such as manufacturing and product quality assessment. This paper introduces a new conditional anomaly detection problem, which involves identifying anomalies in a query image by comparing it to a reference shape. To address this challenge, we have created a large dataset, BrokenChairs-180K, consisting of around 180K images, with diverse anomalies, geometries, and textures paired with 8,143 reference 3D shapes. To tackle this task, we have proposed a novel transformer-based approach that explicitly learns the correspondence between the query image and reference 3D shape via feature alignment and leverages a customized attention mechanism for anomaly detection. Our approach has been rigorously evaluated through comprehensive experiments, serving as a benchmark for future research in this domain.

cs.CV↗

arXiv2024

ContextSeg: Sketch Semantic Segmentation by Querying the Context with Attention

Sketch semantic segmentation is a well-explored and pivotal problem in computer vision involving the assignment of pre-defined part labels to individual strokes. This paper presents ContextSeg - a simple yet highly effective approach to tackling this problem with two stages. In the first stage, to better encode the shape and positional information of strokes, we propose to predict an extra dense distance field in an autoencoder network to reinforce structural information learning. In the second stage, we treat an entire stroke as a single entity and label a group of strokes within the same semantic part using an auto-regressive Transformer with the default attention mechanism. By group-based labeling, our method can fully leverage the context information when making decisions for the remaining groups of strokes. Our method achieves the best segmentation accuracy compared with state-of-the-art approaches on two representative datasets and has been extensively evaluated demonstrating its superior performance. Additionally, we offer insights into solving part imbalance in training data and the preliminary experiment on cross-category training, which can inspire future research in this field.

cs.CV↗

arXiv2024

CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programs

CAD programs are a popular way to compactly encode shapes as a sequence of operations that are easy to parametrically modify. However, without sufficient semantic comments and structure, such programs can be challenging to understand, let alone modify. We introduce the problem of semantic commenting CAD programs, wherein the goal is to segment the input program into code blocks corresponding to semantically meaningful shape parts and assign a semantic label to each block. We solve the problem by combining program parsing with visual-semantic analysis afforded by recent advances in foundational language and vision models. Specifically, by executing the input programs, we create shapes, which we use to generate conditional photorealistic images to make use of semantic annotators for such images. We then distill the information across the images and link back to the original programs to semantically comment on them. Additionally, we collected and annotated a benchmark dataset, CADTalk, consisting of 5,288 machine-made programs and 45 human-made programs with ground truth semantic comments. We extensively evaluated our approach, compared it to a GPT-based baseline, and an open-set shape segmentation baseline, and reported an 83.24% accuracy on the new CADTalk dataset. Code and data: https://enigma-li.github.io/CADTalk/.

cs.CV↗

arXiv2024

On the origin of topotactic reduction effect for superconductivity in infinite-layer nickelates

Topotactic reduction utilizing metal hydrides as reagents emerges as an effective approach to achieve exceptionally low oxidization states of metal ions and unconventional coordination networks. This method opens avenues to the development of entirely new functional materials, with one notable example being the infinite-layer nickelate superconductors. However, the reduction effect on the atomic reconstruction and electronic structures -- crucial for superconductivity -- remains largely unresolved. We design two sets of control Nd$_{0.8}$Sr$_{0.2}$NiO$_2$ thin films and implement secondary ion mass spectroscopy to highlight the absence of reduction-induced hydrogen intercalation. X-ray absorption spectroscopy shows a significant linear dichroism with dominant Ni 3d$_{x2{-}y2}$ orbitals on superconducting samples, indicating a Ni single-band nature of infinite-layer nickelates. Consistent with the superconducting $T_c$, the Ni 3d orbitals asymmetry manifests a dome-like reduction duration dependence. Our results unveil the critical role of reduction in modulating the Ni-3d orbital polarization and its impact on the superconducting properties.

cond-mat.supr-con↗

arXiv2023

iPUNet:Iterative Cross Field Guided Point Cloud Upsampling

Point clouds acquired by 3D scanning devices are often sparse, noisy, and non-uniform, causing a loss of geometric features. To facilitate the usability of point clouds in downstream applications, given such input, we present a learning-based point upsampling method, i.e., iPUNet, which generates dense and uniform points at arbitrary ratios and better captures sharp features. To generate feature-aware points, we introduce cross fields that are aligned to sharp geometric features by self-supervision to guide point generation. Given cross field defined frames, we enable arbitrary ratio upsampling by learning at each input point a local parameterized surface. The learned surface consumes the neighboring points and 2D tangent plane coordinates as input, and maps onto a continuous surface in 3D where arbitrary ratios of output points can be sampled. To solve the non-uniformity of input points, on top of the cross field guided upsampling, we further introduce an iterative strategy that refines the point distribution by moving sparse points onto the desired continuous 3D surface in each iteration. Within only a few iterations, the sparse points are evenly distributed and their corresponding dense samples are more uniform and better capture geometric features. Through extensive evaluations on diverse scans of objects and scenes, we demonstrate that iPUNet is robust to handle noisy and non-uniformly distributed inputs, and outperforms state-of-the-art point cloud upsampling methods.

cs.CV↗

arXiv2023

Self-passivated freestanding superconducting oxide film for flexible electronics

The integration of high-temperature superconducting YBa2Cu3O6+x (YBCO) into flexible electronic devices has the potential to revolutionize the technology industry. The effective preparation of high-quality flexible YBCO films therefore plays a key role in this development. We present a novel approach for transferring water-sensitive YBCO films onto flexible substrates without any buffer layer. Freestanding YBCO film on a polydimethylsiloxane substrate is extracted by etching the Sr3Al2O6 sacrificial layer from the LaAlO3 substrate. In addition to the obtained freestanding YBCO thin film having a Tc of 89.1 K, the freestanding YBCO thin films under inward and outward bending conditions have Tc of 89.6 K and 88.9 K, respectively. A comprehensive characterization involving multiple experimental techniques including high-resolution transmission electron microscopy, scanning electron microscopy, Raman and X-ray Absorption Spectroscopy is conducted to investigate the morphology, structural and electronic properties of the YBCO film before and after the extraction process where it shows the preservation of the structural and superconductive properties of the freestanding YBCO virtually in its pristine state. Further investigation reveals the formation of a YBCO passivated layer serves as a protective layer which effectively preserves the inner section of the freestanding YBCO during the etching process. This work plays a key role in actualizing the fabrication of flexible oxide thin films and opens up new possibilities for a diverse range of device applications involving thin-films and low-dimensional materials.

cond-mat.supr-con↗

arXiv2023

A Robust High-temperature Multiferroic Device with Tunable Topological Hall Effect

We fabricated Pt/La0.5Ba0.5MnO3 ultrathin films with integration to the PbZr0.2Ti0.8O3 ferroelectric. Strong Topological Hall Effect can be measured across a wide temperature range, which can be turned on and off corresponding to the ferroelectric polarization switching driven by short voltage pulses, indicating creation and annihilation of magnetic Skyrmions. However, its magnetoelectric coupling polarity was found to be opposite to the earlier consensus, which involves a phase transition between ferromagnetic and A-type antiferromagnetic in manganites due to electrostatic doping into the eg-orbitals by the ferroelectric bound charges. In our case, we propose a novel yet complementary picture where the transition occurs between C-type antiferromagnetic and ferromagnetic. The distinction between the earlier consensus and our picture lies at the tetragonal distortion of the manganite unit cell, resulting in an opposite magnetoelectric coupling polarity. We support the perceived relationship between the phase transition and tuning of Topological Hall Effect by micromagnetic simulations.

cond-mat.mtrl-sci↗

arXiv2023

Dimensionality control and rotational symmetry breaking superconductivity in square-planar layered nickelates

The interplay between dimensionality and various phases of matter is a central inquiry in condensed matter physics. New phases are often discovered through spontaneously broken symmetry. Understanding the dimensionality of superconductivity in the high-temperature cuprate analogue $-$ layered nickelates and revealing a new symmetry-breaking state are the keys to deciphering the underlying pairing mechanism. Here, we demonstrate the highly-tunable dimensionality and a broken rotational symmetry state in the superconductivity of square-planar layered nickelates. The superconducting state, probed by superconducting critical current and magnetoresistance within superconducting transition under direction-dependent in-plane magnetic fields, exhibits a $C_2$ rotational symmetry which breaks the $C_4$ rotational symmetry of the square-planar lattice. Furthermore, by performing detailed examination of the angular dependent upper critical fields at temperatures down to 0.5 K with high-magnetic pulsed-fields, we observe a crossover from two-dimensional to three-dimensional superconducting states which can be manipulated by the ionic size fluctuations in the rare-earth spacer layer. Such a large degree of controllability is desired for tailoring strongly two/three-dimensional superconductors and navigating various pairing landscapes for a better understanding of the correlation between reduced dimensionality and unconventional pairing. These results illuminate new directions to unravel the high-temperature superconducting pairing mechanism.

cond-mat.supr-con↗

arXiv2022

SNAF: Sparse-view CBCT Reconstruction with Neural Attenuation Fields

Cone beam computed tomography (CBCT) has been widely used in clinical practice, especially in dental clinics, while the radiation dose of X-rays when capturing has been a long concern in CBCT imaging. Several research works have been proposed to reconstruct high-quality CBCT images from sparse-view 2D projections, but the current state-of-the-arts suffer from artifacts and the lack of fine details. In this paper, we propose SNAF for sparse-view CBCT reconstruction by learning the neural attenuation fields, where we have invented a novel view augmentation strategy to overcome the challenges introduced by insufficient data from sparse input views. Our approach achieves superior performance in terms of high reconstruction quality (30+ PSNR) with only 20 input views (25 times fewer than clinical collections), which outperforms the state-of-the-arts. We have further conducted comprehensive experiments and ablation analysis to validate the effectiveness of our approach.

eess.IV↗

arXiv2022

ToothInpaintor: Tooth Inpainting from Partial 3D Dental Model and 2D Panoramic Image

In orthodontic treatment, a full tooth model consisting of both the crown and root is indispensable in making the treatment plan. However, acquiring tooth root information to obtain the full tooth model from CBCT images is sometimes restricted due to the massive radiation of CBCT scanning. Thus, reconstructing the full tooth shape from the ready-to-use input, e.g., the partial intra-oral scan and the 2D panoramic image, is an applicable and valuable solution. In this paper, we propose a neural network, called ToothInpaintor, that takes as input a partial 3D dental model and a 2D panoramic image and reconstructs the full tooth model with high-quality root(s). Technically, we utilize the implicit representation for both the 3D and 2D inputs, and learn a latent space of the full tooth shapes. At test time, given an input, we successfully project it to the learned latent space via neural optimization to obtain the full tooth model conditioned on the input. To help find the robust projection, a novel adversarial learning module is exploited in our pipeline. We extensively evaluate our method on a dataset collected from real-world clinics. The evaluation, comparison, and comprehensive ablation studies demonstrate that our approach produces accurate complete tooth models robustly and outperforms the state-of-the-art methods.

cs.CV↗

arXiv2021

Reversible modulation of metal-insulator transition in VO2 via chemically-induced oxygen migration

Metal-insulator transitions (MIT),an intriguing correlated phenomenon induced by the subtle competition of the electrons' repulsive Coulomb interaction and kinetic energy, is of great potential use for electronic applications due to the dramatic change in resistivity. Here, we demonstrate a reversible control of MIT in VO2 films via oxygen stoichiometry engineering. By facilely depositing and dissolving a water-soluble yet oxygen-active Sr3Al2O6 capping layer atop the VO2 at room temperature, oxygen ions can reversibly migrate between VO2 and Sr3Al2O6, resulting in a gradual suppression and a complete recovery of MIT in VO2. The migration of the oxygen ions is evidenced in a combination of transport measurement, structural characterization and first-principles calculations. This approach of chemically-induced oxygen migration using a water-dissolvable adjacent layer could be useful for advanced electronic and iontronic devices and studying oxygen stoichiometry effects on the MIT.

cond-mat.mtrl-sci↗

arXiv2021

Bipolar conduction and giant positive magnetoresistance in doped metallic titanium oxide heterostructures

Empowering conventional materials with unexpected magnetoelectric properties is appealing to the multi-functionalization of existing devices and the exploration of future electronics. Recently, owing to its unique effect in modulating a matter's properties, ultra-small dopants, e.g. H, D, and Li, attract enormous attention in creating emergent functionalities, such as superconductivity, and metal-insulator transition. Here, we report an observation of bipolar conduction accompanied by a giant positive magnetoresistance in D-doped metallic Ti oxide (TiOxDy) films. To overcome the challenges in intercalating the D into a crystalline oxide, a series of TiOxDy were formed by sequentially doping Ti with D and surface/interface oxidation. Intriguingly, while the electron mobility of the TiOxDy increases by an order of magnitude larger after doping, the emergent holes also exhibit high mobility. Moreover, the bipolar conduction induces a giant magnetoresistance up to 900% at 6 T, which is ~6 times higher than its conventional phase. Our study paves a way to empower conventional materials in existing electronics and induce novel electronic phases.

cond-mat.mtrl-sci↗

arXiv2021

Point2Skeleton: Learning Skeletal Representations from Point Clouds

We introduce Point2Skeleton, an unsupervised method to learn skeletal representations from point clouds. Existing skeletonization methods are limited to tubular shapes and the stringent requirement of watertight input, while our method aims to produce more generalized skeletal representations for complex structures and handle point clouds. Our key idea is to use the insights of the medial axis transform (MAT) to capture the intrinsic geometric and topological natures of the original input points. We first predict a set of skeletal points by learning a geometric transformation, and then analyze the connectivity of the skeletal points to form skeletal mesh structures. Extensive evaluations and comparisons show our method has superior performance and robustness. The learned skeletal representation will benefit several unsupervised tasks for point clouds, such as surface reconstruction and segmentation.

cs.CV↗