Search

3D content creation has long been a complex and time-consuming process, often requiring specialized skills and resources. While recent advancements have allowed for text-guided 3D object and scene generation, they still fall short of providing sufficient control over the generation process, leading to a gap between the user's creative vision and the generated results. In this paper, we present iControl3D, a novel interactive system that empowers users to generate and render customizable 3D scenes with precise control. To this end, a 3D creator interface has been developed to provide users with fine-grained control over the creation process. Technically, we leverage 3D meshes as an intermediary proxy to iteratively merge individual 2D diffusion-generated images into a cohesive and unified 3D scene representation. To ensure seamless integration of 3D meshes, we propose to perform boundary-aware depth alignment before fusing the newly generated mesh with the existing one in 3D space. Additionally, to effectively manage depth discrepancies between remote content and foreground, we propose to model remote content separately with an environment map instead of 3D meshes. Finally, our neural rendering interface enables users to build a radiance field of their scene online and navigate the entire scene. Extensive experiments have been conducted to demonstrate the effectiveness of our system. The code will be made available at https://github.com/xingyi-li/iControl3D., Comment: Accepted by ACM MM 2024

Automatic image cropping models predict reframing boxes to enhance image aesthetics. Yet, the scarcity of labeled data hinders the progress of this task. To overcome this limitation, we explore the possibility of utilizing both labeled and unlabeled data together to expand the scale of training data for image cropping models. This idea can be implemented in a pseudo-labeling way: producing pseudo labels for unlabeled data by a teacher model and training a student model with these pseudo labels. However, the student may learn from teacher's mistakes. To address this issue, we propose the multi-policy viewfinder network (MPV-Net) that offers diverse refining policies to rectify the mistakes in original pseudo labels from the teacher. The most reliable policy is selected to generate trusted pseudo labels. The reliability of policies is evaluated via the robustness against box jittering. The efficacy of our method can be evaluated by the improvement compared to the supervised baseline which only uses labeled data. Notably, our MPV-Net outperforms off-the-shelf pseudo-labeling methods, yielding the most substantial improvement over the supervised baseline. Furthermore, our approach achieves state-of-the-art results on both the FCDB and FLMS datasets, signifying the superiority of our approach., Comment: 18 pages, 8figures

Large-scale datasets with point-wise semantic and instance labels are crucial to 3D instance segmentation but also expensive. To leverage unlabeled data, previous semi-supervised 3D instance segmentation approaches have explored self-training frameworks, which rely on high-quality pseudo labels for consistency regularization. They intuitively utilize both instance and semantic pseudo labels in a joint learning manner. However, semantic pseudo labels contain numerous noise derived from the imbalanced category distribution and natural confusion of similar but distinct categories, which leads to severe collapses in self-training. Motivated by the observation that 3D instances are non-overlapping and spatially separable, we ask whether we can solely rely on instance consistency regularization for improved semi-supervised segmentation. To this end, we propose a novel self-training network InsTeacher3D to explore and exploit pure instance knowledge from unlabeled data. We first build a parallel base 3D instance segmentation model DKNet, which distinguishes each instance from the others via discriminative instance kernels without reliance on semantic segmentation. Based on DKNet, we further design a novel instance consistency regularization framework to generate and leverage high-quality instance pseudo labels. Experimental results on multiple large-scale datasets show that the InsTeacher3D significantly outperforms prior state-of-the-art semi-supervised approaches. Code is available: https://github.com/W1zheng/InsTeacher3D., Comment: 14 pages, 10 figures

Efficient control of antiferromagnetic (AFM) domain switching in thin films is vital for advancing antiferromagnet-based memory devices. In this study, we directly observed the current-driven switching process of CoO AFM domains in the Pt/CoO(001) bilayer by the magneto-optical birefringence effect. The observed critical current density for AFM domain switching remains nearly constant across varying CoO thicknesses, associated with the consistent switching polarity n $\perp$ j, suggesting the dominance of the thermomagnetoelastic effect, where and stand for Neel vector and current density vector, respectively. Further confirmation comes from a similar switching process with n $\perp$ j observed in the Pt/Al2O3/CoO sample, excluding the contribution of spin current injection. Remarkably, it was also surprisingly observed that the Neel vector can be further switched parallel to the current direction (n//j) at higher current density. Our findings not only enhance the understanding of current-driven AFM domain switching but also present new avenues for manipulating AFM domains., Comment: 22 pages, 6 figures

The perception of motion behavior in a dynamic environment holds significant importance for autonomous driving systems, wherein class-agnostic motion prediction methods directly predict the motion of the entire point cloud. While most existing methods rely on fully-supervised learning, the manual labeling of point cloud data is laborious and time-consuming. Therefore, several annotation-efficient methods have been proposed to address this challenge. Although effective, these methods rely on weak annotations or additional multi-modal data like images, and the potential benefits inherent in the point cloud sequence are still underexplored. To this end, we explore the feasibility of self-supervised motion prediction with only unlabeled LiDAR point clouds. Initially, we employ an optimal transport solver to establish coarse correspondences between current and future point clouds as the coarse pseudo motion labels. Training models directly using such coarse labels leads to noticeable spatial and temporal prediction inconsistencies. To mitigate these issues, we introduce three simple spatial and temporal regularization losses, which facilitate the self-supervised training process effectively. Experimental results demonstrate the significant superiority of our approach over the state-of-the-art self-supervised methods., Comment: Accepted by CVPR2024

Current 3D stylization methods often assume static scenes, which violates the dynamic nature of our real world. To address this limitation, we present S-DyRF, a reference-based spatio-temporal stylization method for dynamic neural radiance fields. However, stylizing dynamic 3D scenes is inherently challenging due to the limited availability of stylized reference images along the temporal axis. Our key insight lies in introducing additional temporal cues besides the provided reference. To this end, we generate temporal pseudo-references from the given stylized reference. These pseudo-references facilitate the propagation of style information from the reference to the entire dynamic 3D scene. For coarse style transfer, we enforce novel views and times to mimic the style details present in pseudo-references at the feature level. To preserve high-frequency details, we create a collection of stylized temporal pseudo-rays from temporal pseudo-references. These pseudo-rays serve as detailed and explicit stylization guidance for achieving fine style transfer. Experiments on both synthetic and real-world datasets demonstrate that our method yields plausible stylized results of space-time view synthesis on dynamic 3D scenes., Comment: Accepted by CVPR 2024. Project page: https://xingyi-li.github.io/s-dyrf/

Class-agnostic motion prediction methods aim to comprehend motion within open-world scenarios, holding significance for autonomous driving systems. However, training a high-performance model in a fully-supervised manner always requires substantial amounts of manually annotated data, which can be both expensive and time-consuming to obtain. To address this challenge, our study explores the potential of semi-supervised learning (SSL) for class-agnostic motion prediction. Our SSL framework adopts a consistency-based self-training paradigm, enabling the model to learn from unlabeled data by generating pseudo labels through test-time inference. To improve the quality of pseudo labels, we propose a novel motion selection and re-generation module. This module effectively selects reliable pseudo labels and re-generates unreliable ones. Furthermore, we propose two data augmentation strategies: temporal sampling and BEVMix. These strategies facilitate consistency regularization in SSL. Experiments conducted on nuScenes demonstrate that our SSL method can surpass the self-supervised approach by a large margin by utilizing only a tiny fraction of labeled data. Furthermore, our method exhibits comparable performance to weakly and some fully supervised methods. These results highlight the ability of our method to strike a favorable balance between annotation costs and performance. Code will be available at https://github.com/kwwcv/SSMP., Comment: This paper is accepted by AAAI2024

Structured light, particularly in the terahertz frequency range, holds considerable potential for a diverse range of applications. However, the generation and control of structured terahertz radiation pose major challenges. In this work, we demonstrate a novel programmable spintronic emitter that can flexibly generate a variety of structured terahertz waves. This is achieved through the precise and high-resolution programming of the magnetization pattern on the emitter surface, utilizing laser-assisted local field cooling of an exchange-biased ferromagnetic heterostructure. Moreover, we outline a generic design strategy for realizing specific complex structured terahertz fields in the far field. Our device successfully demonstrates the generation of terahertz waves with diverse structured polarization states, including spatially separated circular polarizations, azimuthal or radial polarization states, and a full Poincare beam. This innovation opens a new avenue for designing and generating structured terahertz radiations, with potential applications in terahertz microscopy, communication, quantum information, and light-matter interactions.

The conventional Hall effect is linearly proportional to the field component or magnetization component perpendicular to a film. Despite the increasing theoretical proposals on the Hall effect to the in-plane field or magnetization in various special systems induced by the Berry curvature, such an unconventional Hall effect has only been experimentally reported in Weyl semimetals and in a heterodimensional superlattice. Here, we report an unambiguous experimental observation of the antisymmetric planar Hall effect (APHE) with respect to the in-plane magnetic field in centrosymmetric rutile RuO2 and IrO2 single-crystal films. The measured Hall resistivity is found to be linearly proportional to the component of the applied in-plane magnetic field along a particular crystal axis and to be independent of the current direction or temperature. Both the experimental observations and theoretical calculations confirm that the APHE in rutile oxide films is induced by the Lorentz force. Our findings can be generalized to ferromagnetic materials for the discovery of anomalous Hall effects and quantum anomalous Hall effects induced by in-plane magnetization. In addition to significantly expanding knowledge of the Hall effect, this work opens the door to explore new members in the Hall effect family.

The Segment Anything Model (SAM) has demonstrated its effectiveness in segmenting any part of 2D RGB images. However, SAM exhibits a stronger emphasis on texture information while paying less attention to geometry information when segmenting RGB images. To address this limitation, we propose the Segment Any RGBD (SAD) model, which is specifically designed to extract geometry information directly from images. Inspired by the natural ability of humans to identify objects through the visualization of depth maps, SAD utilizes SAM to segment the rendered depth map, thus providing cues with enhanced geometry information and mitigating the issue of over-segmentation. We further include the open-vocabulary semantic segmentation in our framework, so that the 3D panoptic segmentation is fulfilled. The project is available on https://github.com/Jun-CEN/SegmentAnyRGBD., Comment: Technical report of Segment Any RGBD. Project url: https://github.com/Jun-CEN/SegmentAnyRGBD

Precise and ultrafast control over photo-induced charge currents across nanoscale interfaces could lead to important applications in energy harvesting, ultrafast electronics, and coherent terahertz sources. Recent studies have shown that several relativistic mechanisms, including inverse spin-Hall effect, inverse Rashba-Edelstein effect and inverse spin-orbit-torque effect, can convert longitudinally injected spin-polarized currents from magnetic materials to transverse charge currents, thereby harnessing these currents for terahertz generation. However, these mechanisms typically require external magnetic fields and suffer from low spin-polarization rates and low efficiencies of relativistic spin-to-charge conversion. In this work, we present a novel nonrelativistic and nonmagnetic mechanism that directly utilizes the photo-excited high-density charge currents across the interface. We demonstrate that the electrical anisotropy of conductive oxides RuO2 and IrO2 can effectively deflect injected charge currents to the transverse direction, resulting in efficient and broadband terahertz radiation. Importantly, this new mechanism has the potential to offer much higher conversion efficiency compared to previous methods, as conductive materials with large electrical anisotropy are readily available, whereas further increasing the spin-Hall angle of heavy-metal materials would be challenging. Our new findings offer exciting possibilities for directly utilizing these photo-excited high-density currents across metallic interfaces for ultrafast electronics and terahertz spectroscopy.

We introduce a 3D instance representation, termed instance kernels, where instances are represented by one-dimensional vectors that encode the semantic, positional, and shape information of 3D instances. We show that instance kernels enable easy mask inference by simply scanning kernels over the entire scenes, avoiding the heavy reliance on proposals or heuristic clustering algorithms in standard 3D instance segmentation pipelines. The idea of instance kernel is inspired by recent success of dynamic convolutions in 2D/3D instance segmentation. However, we find it non-trivial to represent 3D instances due to the disordered and unstructured nature of point cloud data, e.g., poor instance localization can significantly degrade instance representation. To remedy this, we construct a novel 3D instance encoding paradigm. First, potential instance centroids are localized as candidates. Then, a candidate merging scheme is devised to simultaneously aggregate duplicated candidates and collect context around the merged centroids to form the instance kernels. Once instance kernels are available, instance masks can be reconstructed via dynamic convolutions whose weights are conditioned on instance kernels. The whole pipeline is instantiated with a dynamic kernel network (DKNet). Results show that DKNet outperforms the state of the arts on both ScanNetV2 and S3DIS datasets with better instance localization. Code is available: https://github.com/W1zheng/DKNet., Comment: Appearing in ECCV, 2022

L10-FePt distinguishes itself for its ultrahigh perpendicular magnetic anisotropy (PMA), which enables memory cells with sufficient thermal stability to scale down to 3 nm. The recently discovered "bulk" spin-orbit torques in L10-FePt provide an efficient and scalable way to manipulate the L10-FePt magnetization. However, the existence of external field during the switching limits its practical application, and therefore field-free switching of the L10-FePt is in highly demand. In this manuscript, we demonstrate the field-free switching of the L10-FePt by growing it on vicinal MgO (001) substrates. This method is different from previously established strategies, as it does not need to add other functional layers or create asymmetry in the film structure. We demonstrate the field-free switching is robust and can withstand strong field disturbance up to ~1 kOe. The dependence on vicinal angle, film thickness, and growth temperature demonstrated a wide operation window for the field-free switching of the L10-FePt. We confirmed that the physical origin of the field-free switching is the vicinal surface-induced the tilted anisotropy of L10-FePt. We quantitatively characterize the spin-orbit torques in the L10-FePt films, and found the spin-orbit torques are not significantly influenced by the lattice strain from vicinal substrates. Our results extend beyond the established strategies to realize field-free switching, and potentially could be applied to other magnetic and antiferromagnetic systems., Comment: 10 pages,4 figures

A high-sensitive DC Magneto-Optical Kerr Effect (MOKE) apparatus is described in this letter. Via detailed analysis on several dominating noise sources, we have proposed solutions that significantly lower the MOKE noise, and a sensitivity of $1.5\times10^{-7} \text{rad}/\sqrt{\text{Hz}}$ is achieved with long-term stability. The sensitivity of the apparatus is tested by measuring a wedge-shaped Ni thin film on $\text{SiO}_2$ with Ni thickness varying from 0 to 3 nm. A noise floor of $1.5\times10^{-8}$ rad is demonstrated. The possibility of further improving sensitivity to $10^{-9}$ rad via applying ac modulation is also discussed., Comment: 16 pages, 7 figures

We investigated spin wave (SW) propagation and emission in thin film systems with strong interfacial Dzyaloshinskii-Moriya interaction (DMI) utilizing micromagnetic simulation. The effect of DMI on SW propagation is analogous to the flow of magnetic medium leading to the spin Doppler effect, and a spin-polarized current can enhance or suppress it. It is demonstrated that, for a Doppler velocity exceeding a critical value, a shock-wave-like emission of SWs with a cone-shape emerges from a magnetically irregular point as the cone apex. The cone angle is quantitatively determined by the DMI-induced Doppler velocity. Combining the interfacial DMI and the spin-polarized current, a constant SW emission by a static source is demonstrated, which provides a promising route to efficiently generate SWs with tunable frequency.

The ability to manipulate the electric-field vector of broadband terahertz waves is essential for applications of terahertz technologies in many areas, and can open up new possibilities for nonlinear terahertz spectroscopy and coherent control. Here, we propose a novel laser-driven terahertz emitter, consisting of metasurface-patterned magnetic multilayer heterostructures. Such hybrid terahertz emitters can combine the advantages of spintronic emitters for being ultrabroadband, efficient and flexible, as well as those of metasurfaces for the unique capability to manipulate terahertz waves with high precision and degree of freedom. Taking a stripe-patterned metasurface as an example, we demonstrate the generation of broadband terahertz waves with tunable chirality. Based on experimental and theoretical studies, the interplay between the laser-induced spintronic-origin currents and the metasurface-induced transient charges/currents are investigated, revealing the strong influence on the device functionality originated from both the light-matter interactions in individual metasurface units and the dynamic coupling between them. Our work not only offers a flexible, reliable and cost-effective solution for chiral terahertz wave generation and manipulation, but also opens a new pathway to metasurface-tailored spintronic devices for efficient vector-control of electromagnetic waves in the terahertz regime.

The interfacial Dzyaloshinskii-Moriya interaction (DMI) is of great interest as it can stabilize chiral spin structures in thin films. Experiments verifying the orientation of the interfacial DMI vector remain rare, in part due to the difficulty of separating vector components of DMI. In this study, Fe/Ni bilayers and Co/Ni multilayers were deposited epitaxially onto Cu(001) and Pt(111) substrates, respectively. By tailoring the effective anisotropy, spin reorientation transitions (SRTs) are employed to probe the orientation of the DMI vector by measuring the spin structure of domain walls on both sides of the SRTs. The interfacial DMI is found to be sufficiently strong to stabilize chiral N\'eel walls in the out-of-plane magnetized regimes, while achiral N\'eel walls are observed in the in-plane magnetized regimes. These findings experimentally confirm that the out-of-plane component of the DMI vector is insignificant in these fcc(001) and fcc(111) oriented interfaces, even in the presence of atomic steps., Comment: 19 pages, 5 figures

Antiferromagnetic (AFM) domains in ultrathin CoO(001) films are imaged by a wide-field optical microscopy using magneto-optical birefringence effect. The magnetic origin of observed optical contrast is confirmed by the spin orientation manipulation through exchange coupling in Fe/CoO(001) bilayer. The finite size effect of ordering temperature for ultrathin single crystal CoO film is revealed by the thickness and temperature dependent measurement of birefringence contrast. The magneto-optical birefringence effect is found to strongly depend on the photon energy of incident light, and a surprising large polarization rotation angle up to 168.5 mdeg is obtained from a 4.6 nm CoO film with a blue light source, making it possible to further investigate the evolution of AFM domains in AFM ultrathin film under external field., Comment: 11 pages,5 figures

The spin- and energy-dependent interface reflectivity of a ferromagnetic (FM) film in contact with a nonmagnetic (NM) film is calculated using a first-principles transport method and incorporated into the superdiffusive spin transport model to study the femtosecond laser-induced ultrafast demagnetization of Fe|NM and Ni|NM (NM= Au, Al & Pt) bilayers. By comparing the calculated demagnetization with transparent and real interfaces, we demonstrate that the spin-dependent reflection of hot electrons has a noticeable influence on the ultrafast demagnetization and the associated terahertz electromagnetic radiation. In particular, a spin filtering effect is found at the Fe|NM interface that increases the spin current injected into the NM metal, which enhances both the resulting demagnetization and the resulting THz emission. This suggests that the THz radiation can be optimized by tailoring the interface, indicating a very large tunability., Comment: 14 pages, 16 figures

Recent demonstrations of electrical detection and manipulation of antiferromagnets (AFMs) have opened new opportunities towards robust and ultrafast spintronics devices. However, it is difficult to establish the connection between the spin-transport behavior and the microscopic AFM domain states due to the lack of the real-time AFM domain imaging technique under the electric field. Here we report a significant Voigt rotation up to 60 mdeg in thin NiO(001) films at room temperature. Such large Voigt rotation allows us to directly observe AFM domains in thin-film NiO by utilizing a wide-field optical microscope. Further complementary XMLD-PEEM measurement confirms that the Voigt contrast originates from the NiO AFM order. We examine the domain pattern evolution at a wide range of temperature and with the application of external magnetic field. Comparing to large-scale-facility techniques such as the X-ray photoemission electron microscopy, the use with a wide-field, tabletop optical imaging method enables straightforward access to domain configurations of single-layer AFMs., Comment: 17 pages , 5 figures

Tailoring Gilbert damping of metallic ferromagnetic thin films is one of the central interests in spintronics applications. Here we report a giant Gilbert damping anisotropy in epitaxial Co$_{50}$Fe$_{50}$ thin film with a maximum-minimum damping ratio of 400 \%, determined by broadband spin-torque as well as inductive ferromagnetic resonance. We conclude that the origin of this damping anisotropy is the variation of the spin orbit coupling for different magnetization orientations in the cubic lattice, which is further corroborate from the magnitude of the anisotropic magnetoresistance in Co$_{50}$Fe$_{50}$., Comment: 13 pages, 14 figures

It is a common perception that the transport of a spin current in polycrystalline metal is isotropic and independent of the polarization direction, even though spin current is a tensorlike quantity and its polarization direction is a key variable. We demonstrate surprising anisotropic spin relaxation in mesoscopic polycrystalline Cu channels in nonlocal spin valves. For directions in the substrate plane, the spin-relaxation length is longer for spins parallel to the Cu channel than for spins perpendicular to it, by as much as 9% at 10 K. Spin-orbit effects on the surfaces of Cu channels can account for this anisotropic spin relaxation. The finding suggests novel tunability of spin current, not only by its polarization direction but also by electrostatic gating., Comment: (#) C. Zhou and F. Kandaz contributed equally to this work. Main text (22 pages, 4 figures) + Supplementary material (9 pages, 3 figures)