Search

We introduce Crowd-Sourced Splatting (CSS), a novel 3D Gaussian Splatting (3DGS) pipeline designed to overcome the challenges of pose-free scene reconstruction using crowd-sourced imagery. The dream of reconstructing historically significant but inaccessible scenes from collections of photographs has long captivated researchers. However, traditional 3D techniques struggle with missing camera poses, limited viewpoints, and inconsistent lighting. CSS addresses these challenges through robust geometric priors and advanced illumination modeling, enabling high-quality novel view synthesis under complex, real-world conditions. Our method demonstrates clear improvements over existing approaches, paving the way for more accurate and flexible applications in AR, VR, and large-scale 3D reconstruction.

Map-free relocalization technology is crucial for applications in autonomous navigation and augmented reality, but relying on pre-built maps is often impractical. It faces significant challenges due to limitations in matching methods and the inherent lack of scale in monocular images. These issues lead to substantial rotational and metric errors and even localization failures in real-world scenarios. Large matching errors significantly impact the overall relocalization process, affecting both rotational and translational accuracy. Due to the inherent limitations of the camera itself, recovering the metric scale from a single image is crucial, as this significantly impacts the translation error. To address these challenges, we propose a map-free relocalization method enhanced by instance knowledge and depth knowledge. By leveraging instance-based matching information to improve global matching results, our method significantly reduces the possibility of mismatching across different objects. The robustness of instance knowledge across the scene helps the feature point matching model focus on relevant regions and enhance matching accuracy. Additionally, we use estimated metric depth from a single image to reduce metric errors and improve scale recovery accuracy. By integrating methods dedicated to mitigating large translational and rotational errors, our approach demonstrates superior performance in map-free relocalization techniques., Comment: 17 pages,6 figures

Group-V materials such as niobium and tantalum have become popular choices for extending the performance of circuit quantum electrodynamics (cQED) platforms allowing for quantum processors and memories with reduced error rates and more modes. The complex surface chemistry of niobium however makes identifying the main modes of decoherence difficult at millikelvin temperatures and single-photon powers. We use niobium coaxial quarter-wave cavities to study the impact of etch chemistry, prolonged atmospheric exposure, and the significance of cavity conditions prior to and during cooldown, in particular niobium hydride evolution, on single-photon coherence. We demonstrate cavities with quality factors of $Q_{\rm int}\gtrsim 1.4\times10^{9}$ in the single-photon regime, a $15$ fold improvement over aluminum cavities of the same geometry. We rigorously quantify the sensitivity of our fabrication process to various loss mechanisms and demonstrate a $2-4\times$ reduction in the two-level system (TLS) loss tangent and a $3-5\times$ improvement in the residual resistivity over traditional BCP etching techniques. Finally, we demonstrate transmon integration and coherent cavity control while maintaining a cavity coherence of \SI{11.3}{ms}. The accessibility of our method, which can easily be replicated in academic-lab settings, and the demonstration of its performance mark an advancement in 3D cQED., Comment: 14 pages, 10 figures

Quantum technologies based on quantum point defects in crystals require control over the defect charge state. Here we tune the charge state of shallow nitrogen-vacancy and silicon-vacancy centers by locally oxidizing a hydrogenated surface with moderate optical excitation and simultaneous spectral monitoring. The loss of conductivity and change in work function due to oxidation are measured in atmosphere using conductive atomic force microscopy (C-AFM) and Kelvin probe force microscopy (KPFM). We correlate these scanning probe measurements with optical spectroscopy of the nitrogen-vacancy and silicon-vacancy centers created via implantation and annealing 15-25 nm beneath the diamond surface. The observed charge state of the defects as a function of optical exposure demonstrates that laser oxidation provides a way to precisely tune the Fermi level over a range of at least 2.00 eV. We also observe a significantly larger oxidation rate for implanted surfaces compared to unimplanted surfaces under ambient conditions. Combined with knowledge of the electron affinity of a surface, these results suggest KPFM is a powerful, high-spatial resolution technique to advance surface Fermi level engineering for charge stabilization of quantum defects.

Visual-based 3D semantic occupancy perception is a key technology for robotics, including autonomous vehicles, offering an enhanced understanding of the environment by 3D. This approach, however, typically requires more computational resources than BEV or 2D methods. We propose a novel 3D semantic occupancy perception method, OccupancyDETR, which utilizes a DETR-like object detection, a mixed dense-sparse 3D occupancy decoder. Our approach distinguishes between foreground and background within a scene. Initially, foreground objects are detected using the DETR-like object detection. Subsequently, queries for both foreground and background objects are fed into the mixed dense-sparse 3D occupancy decoder, performing upsampling in dense and sparse methods, respectively. Finally, a MaskFormer is utilized to infer the semantics of the background voxels. Our approach strikes a balance between efficiency and accuracy, achieving faster inference times, lower resource consumption, and improved performance for small object detection. We demonstrate the effectiveness of our proposed method on the SemanticKITTI dataset, showcasing an mIoU of 14 and a processing speed of 10 FPS, thereby presenting a promising solution for real-time 3D semantic occupancy perception.

Accurate depth estimation under out-of-distribution (OoD) scenarios, such as adverse weather conditions, sensor failure, and noise contamination, is desirable for safety-critical applications. Existing depth estimation systems, however, suffer inevitably from real-world corruptions and perturbations and are struggled to provide reliable depth predictions under such cases. In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation. This challenge was developed based on the newly established KITTI-C and NYUDepth2-C benchmarks. We hosted two stand-alone tracks, with an emphasis on robust self-supervised and robust fully-supervised depth estimation, respectively. Out of more than two hundred participants, nine unique and top-performing solutions have appeared, with novel designs ranging from the following aspects: spatial- and frequency-domain augmentations, masked image modeling, image restoration and super-resolution, adversarial training, diffusion-based noise suppression, vision-language pre-training, learned model ensembling, and hierarchical feature enhancement. Extensive experimental analyses along with insightful observations are drawn to better understand the rationale behind each design. We hope this challenge could lay a solid foundation for future research on robust and reliable depth estimation and beyond. The datasets, competition toolkit, workshop recordings, and source code from the winning teams are publicly available on the challenge website., Comment: Technical Report; 65 pages, 34 figures, 24 tables; Code at https://github.com/ldkong1205/RoboDepth

Niobium offers the benefit of increased operating temperatures and frequencies for Josephson junctions, which are the core component of superconducting devices. However existing niobium processes are limited by more complicated fabrication methods and higher losses than now-standard aluminum junctions. Combining recent trilayer fabrication advancements, methods to remove lossy dielectrics and modern superconducting qubit design, we revisit niobium trilayer junctions and fabricate all-niobium transmons using only optical lithography. We characterize devices in the microwave domain, measuring coherence times up to $62~\mu$s and an average qubit quality factor above $10^5$: much closer to state-of-the-art aluminum-junction devices. We find the higher superconducting gap energy also results in reduced quasiparticle sensitivity above $0.16~$K, where aluminum junction performance deteriorates. Our junction process is readily applied to standard optical-based foundry processes, opening new avenues for direct integration and scalability, and paves the way for higher-temperature and higher-frequency quantum devices.

This paper proposes an anchor-based deformation model, namely AnchorDEF, to predict 3D garment animation from a body motion sequence. It deforms a garment mesh template by a mixture of rigid transformations with extra nonlinear displacements. A set of anchors around the mesh surface is introduced to guide the learning of rigid transformation matrices. Once the anchor transformations are found, per-vertex nonlinear displacements of the garment template can be regressed in a canonical space, which reduces the complexity of deformation space learning. By explicitly constraining the transformed anchors to satisfy the consistencies of position, normal and direction, the physical meaning of learned anchor transformations in space is guaranteed for better generalization. Furthermore, an adaptive anchor updating is proposed to optimize the anchor position by being aware of local mesh topology for learning representative anchor transformations. Qualitative and quantitative experiments on different types of garments demonstrate that AnchorDEF achieves the state-of-the-art performance on 3D garment deformation prediction in motion, especially for loose-fitting garments., Comment: Accepted to CVPR 2023. Project page: https://semanticdh.github.io/AnchorDEF

We present a simple yet effective method for skeleton-free motion retargeting. Previous methods transfer motion between high-resolution meshes, failing to preserve the inherent local-part motions in the mesh. Addressing this issue, our proposed method learns the correspondence in a coarse-to-fine fashion by integrating the retargeting process with a mesh-coarsening pipeline. First, we propose a mesh-coarsening module that coarsens the mesh representations for better motion transfer. This module improves the ability to handle small-part motion and preserves the local motion interdependence between neighboring mesh vertices. Furthermore, we leverage a hierarchical refinement procedure to complement missing mesh details by gradually improving the low-resolution mesh output with a higher-resolution one. We evaluate our method on several well-known 3D character datasets, and it yields an average improvement of 25% on point-wise mesh euclidean distance (PMD) against the start-of-art method. Moreover, our qualitative results show that our method is significantly helpful in preserving the moving consistency of different body parts on the target character due to disentangling body-part structures and mesh details in a hierarchical way.

A good motion retargeting cannot be reached without reasonable consideration of source-target differences on both the skeleton and shape geometry levels. In this work, we propose a novel Residual RETargeting network (R2ET) structure, which relies on two neural modification modules, to adjust the source motions to fit the target skeletons and shapes progressively. In particular, a skeleton-aware module is introduced to preserve the source motion semantics. A shape-aware module is designed to perceive the geometries of target characters to reduce interpenetration and contact-missing. Driven by our explored distance-based losses that explicitly model the motion semantics and geometry, these two modules can learn residual motion modifications on the source motion to generate plausible retargeted motion in a single inference without post-processing. To balance these two modifications, we further present a balancing gate to conduct linear interpolation between them. Extensive experiments on the public dataset Mixamo demonstrate that our R2ET achieves the state-of-the-art performance, and provides a good balance between the preservation of motion semantics as well as the attenuation of interpenetration and contact-missing. Code is available at https://github.com/Kebii/R2ET., Comment: CVPR 2023