arXiv subjects

Chi Zhang

Publications and source records attributed to Chi Zhang.

At least 595 records · Page 33Linked to original sources

arXiv2023

An SPH formulation for general plate and shell structures with finite deformation and large rotation

In this paper, we propose a reduced-dimensional smoothed particle hydrodynamics (SPH) formulation for quasi-static and dynamic analyses of plate and shell structures undergoing finite deformation and large rotation. By exploiting Uflyand-Mindlin plate theory, the present surface-particle formulation is able to resolve the thin structures by using only one layer of particles at the mid-surface. To resolve the geometric non-linearity and capture finite deformation and large rotation, two reduced-dimensional linear-reproducing correction matrices are introduced, and weighted non-singularity conversions between the rotation angle and pseudo normal are formulated. A new non-isotropic Kelvin-Voigt damping is proposed especially for the both thin and moderately thick plate and shell structures to increase the numerical stability. In addition, a shear-scaled momentum-conserving hourglass control algorithm with an adaptive limiter is introduced to suppress the mismatches between the particle position and pseudo normal and those estimated with the deformation gradient. A comprehensive set of test problems, for which the analytical or numerical results from literature or those of the volume-particle SPH model are available for quantitative and qualitative comparison, are examined to demonstrate the accuracy and stability of the present method.

math.NA↗

arXiv2023

Extended Eulerian SPH and its realization of FVM

Eulerian smoothed particle hydrodynamics (Eulerian SPH) is considered as a potential meshless alternative to a traditional Eulerian mesh-based method, i.e. finite volume method (FVM), in computational fluid dynamics (CFD). While researchers have analyzed the differences between these two methods, a rigorous comparison of their performance and computational efficiency is hindered by the constraint related to the normal direction of interfaces in pairwise particle interactions within Eulerian SPH framework. To address this constraint and improve numerical accuracy, we introduce Eulerian SPH extensions, including particle relaxation to satisfy zero-order consistency, kernel correction matrix to ensure first-order consistency and release the constraint associated with the normal direction of interfaces, as well as dissipation limiters to enhance numerical accuracy and these extensions make Eulerian SPH rigorously equivalent to FVM. Furthermore, we implement mesh-based FVM within SPHinXsys, an open-source SPH library, through developing a parser to extract necessary information from the mesh file which is exported in the MESH format using the commercial software ICEM. Therefore, these comprehensive approaches enable a rigorous comparison between these two methods.

physics.flu-dyn↗

arXiv2023

PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction

Vectorized high-definition map online construction has garnered considerable attention in the field of autonomous driving research. Most existing approaches model changeable map elements using a fixed number of points, or predict local maps in a two-stage autoregressive manner, which may miss essential details and lead to error accumulation. Towards precise map element learning, we propose a simple yet effective architecture named PivotNet, which adopts unified pivot-based map representations and is formulated as a direct set prediction paradigm. Concretely, we first propose a novel point-to-line mask module to encode both the subordinate and geometrical point-line priors in the network. Then, a well-designed pivot dynamic matching module is proposed to model the topology in dynamic point sequences by introducing the concept of sequence matching. Furthermore, to supervise the position and topology of the vectorized point predictions, we propose a dynamic vectorized sequence loss. Extensive experiments and ablations show that PivotNet is remarkably superior to other SOTAs by 5.9 mAP at least. The code will be available soon.

cs.CV↗

arXiv2023

MacFormer: Map-Agent Coupled Transformer for Real-time and Robust Trajectory Prediction

Predicting the future behavior of agents is a fundamental task in autonomous vehicle domains. Accurate prediction relies on comprehending the surrounding map, which significantly regularizes agent behaviors. However, existing methods have limitations in exploiting the map and exhibit a strong dependence on historical trajectories, which yield unsatisfactory prediction performance and robustness. Additionally, their heavy network architectures impede real-time applications. To tackle these problems, we propose Map-Agent Coupled Transformer (MacFormer) for real-time and robust trajectory prediction. Our framework explicitly incorporates map constraints into the network via two carefully designed modules named coupled map and reference extractor. A novel multi-task optimization strategy (MTOS) is presented to enhance learning of topology and rule constraints. We also devise bilateral query scheme in context fusion for a more efficient and lightweight network. We evaluated our approach on Argoverse 1, Argoverse 2, and nuScenes real-world benchmarks, where it all achieved state-of-the-art performance with the lowest inference latency and smallest model size. Experiments also demonstrate that our framework is resilient to imperfect tracklet inputs. Furthermore, we show that by combining with our proposed strategies, classical models outperform their baselines, further validating the versatility of our framework.

cs.CV↗

arXiv2023

DPF-Net: Combining Explicit Shape Priors in Deformable Primitive Field for Unsupervised Structural Reconstruction of 3D Objects

Unsupervised methods for reconstructing structures face significant challenges in capturing the geometric details with consistent structures among diverse shapes of the same category. To address this issue, we present a novel unsupervised structural reconstruction method, named DPF-Net, based on a new Deformable Primitive Field (DPF) representation, which allows for high-quality shape reconstruction using parameterized geometric primitives. We design a two-stage shape reconstruction pipeline which consists of a primitive generation module and a primitive deformation module to approximate the target shape of each part progressively. The primitive generation module estimates the explicit orientation, position, and size parameters of parameterized geometric primitives, while the primitive deformation module predicts a dense deformation field based on a parameterized primitive field to recover shape details. The strong shape prior encoded in parameterized geometric primitives enables our DPF-Net to extract high-level structures and recover fine-grained shape details consistently. The experimental results on three categories of objects in diverse shapes demonstrate the effectiveness and generalization ability of our DPF-Net on structural reconstruction and shape segmentation.

cs.CV↗

arXiv2023

IT3D: Improved Text-to-3D Generation with Explicit View Synthesis

Recent strides in Text-to-3D techniques have been propelled by distilling knowledge from powerful large text-to-image diffusion models (LDMs). Nonetheless, existing Text-to-3D approaches often grapple with challenges such as over-saturation, inadequate detailing, and unrealistic outputs. This study presents a novel strategy that leverages explicitly synthesized multi-view images to address these issues. Our approach involves the utilization of image-to-image pipelines, empowered by LDMs, to generate posed high-quality images based on the renderings of coarse 3D models. Although the generated images mostly alleviate the aforementioned issues, challenges such as view inconsistency and significant content variance persist due to the inherent generative nature of large diffusion models, posing extensive difficulties in leveraging these images effectively. To overcome this hurdle, we advocate integrating a discriminator alongside a novel Diffusion-GAN dual training strategy to guide the training of 3D models. For the incorporated discriminator, the synthesized multi-view images are considered real data, while the renderings of the optimized 3D models function as fake data. We conduct a comprehensive set of experiments that demonstrate the effectiveness of our method over baseline approaches.

cs.CV↗

arXiv2023

X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events

Intuitive physics is pivotal for human understanding of the physical world, enabling prediction and interpretation of events even in infancy. Nonetheless, replicating this level of intuitive physics in artificial intelligence (AI) remains a formidable challenge. This study introduces X-VoE, a comprehensive benchmark dataset, to assess AI agents' grasp of intuitive physics. Built on the developmental psychology-rooted Violation of Expectation (VoE) paradigm, X-VoE establishes a higher bar for the explanatory capacities of intuitive physics models. Each VoE scenario within X-VoE encompasses three distinct settings, probing models' comprehension of events and their underlying explanations. Beyond model evaluation, we present an explanation-based learning system that captures physics dynamics and infers occluded object states solely from visual sequences, without explicit occlusion labels. Experimental outcomes highlight our model's alignment with human commonsense when tested against X-VoE. A remarkable feature is our model's ability to visually expound VoE events by reconstructing concealed scenes. Concluding, we discuss the findings' implications and outline future research directions. Through X-VoE, we catalyze the advancement of AI endowed with human-like intuitive physics capabilities.

cs.AI↗

arXiv2023

KD-MVS: Knowledge Distillation Based Self-supervised Learning for Multi-view Stereo

Supervised multi-view stereo (MVS) methods have achieved remarkable progress in terms of reconstruction quality, but suffer from the challenge of collecting large-scale ground-truth depth. In this paper, we propose a novel self-supervised training pipeline for MVS based on knowledge distillation, termed KD-MVS, which mainly consists of self-supervised teacher training and distillation-based student training. Specifically, the teacher model is trained in a self-supervised fashion using both photometric and featuremetric consistency. Then we distill the knowledge of the teacher model to the student model through probabilistic knowledge transferring. With the supervision of validated knowledge, the student model is able to outperform its teacher by a large margin. Extensive experiments performed on multiple datasets show our method can even outperform supervised methods.

cs.CV↗

arXiv2023

ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution

Single hyperspectral image super-resolution (single-HSI-SR) aims to restore a high-resolution hyperspectral image from a low-resolution observation. However, the prevailing CNN-based approaches have shown limitations in building long-range dependencies and capturing interaction information between spectral features. This results in inadequate utilization of spectral information and artifacts after upsampling. To address this issue, we propose ESSAformer, an ESSA attention-embedded Transformer network for single-HSI-SR with an iterative refining structure. Specifically, we first introduce a robust and spectral-friendly similarity metric, \ie, the spectral correlation coefficient of the spectrum (SCC), to replace the original attention matrix and incorporates inductive biases into the model to facilitate training. Built upon it, we further utilize the kernelizable attention technique with theoretical support to form a novel efficient SCC-kernel-based self-attention (ESSA) and reduce attention computation to linear complexity. ESSA enlarges the receptive field for features after upsampling without bringing much computation and allows the model to effectively utilize spatial-spectral information from different scales, resulting in the generation of more natural high-resolution images. Without the need for pretraining on large-scale datasets, our experiments demonstrate ESSA's effectiveness in both visual quality and quantitative results.

cs.CV↗

arXiv2023

Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image

Reconstructing accurate 3D scenes from images is a long-standing vision task. Due to the ill-posedness of the single-image reconstruction problem, most well-established methods are built upon multi-view geometry. State-of-the-art (SOTA) monocular metric depth estimation methods can only handle a single camera model and are unable to perform mixed-data training due to the metric ambiguity. Meanwhile, SOTA monocular methods trained on large mixed datasets achieve zero-shot generalization by learning affine-invariant depths, which cannot recover real-world metrics. In this work, we show that the key to a zero-shot single-view metric depth model lies in the combination of large-scale data training and resolving the metric ambiguity from various camera models. We propose a canonical camera space transformation module, which explicitly addresses the ambiguity problems and can be effortlessly plugged into existing monocular models. Equipped with our module, monocular models can be stably trained with over 8 million images with thousands of camera models, resulting in zero-shot generalization to in-the-wild images with unseen camera settings. Experiments demonstrate SOTA performance of our method on 7 zero-shot benchmarks. Notably, our method won the championship in the 2nd Monocular Depth Estimation Challenge. Our method enables the accurate recovery of metric 3D structures on randomly collected internet images, paving the way for plausible single-image metrology. The potential benefits extend to downstream tasks, which can be significantly improved by simply plugging in our model. For example, our model relieves the scale drift issues of monocular-SLAM (Fig. 1), leading to high-quality metric scale dense mapping. The code is available at https://github.com/YvanYin/Metric3D.

cs.CV↗

arXiv2023

Quantum-Enhanced Metrology for Molecular Symmetry Violation using Decoherence-Free Subspaces

We propose a method to measure time-reversal symmetry violation in molecules that overcomes the standard quantum limit while leveraging decoherence-free subspaces to mitigate sensitivity to classical noise. The protocol does not require an external electric field, and the entangled states have no first-order sensitivity to static electromagnetic fields as they involve superpositions with zero average lab-frame projection of spins and dipoles. This protocol can be applied with trapped neutral or ionic species, and can be implemented using methods which have been demonstrated experimentally.

physics.atom-ph↗

arXiv2023

Brain in a Vat: On Missing Pieces Towards Artificial General Intelligence in Large Language Models

In this perspective paper, we first comprehensively review existing evaluations of Large Language Models (LLMs) using both standardized tests and ability-oriented benchmarks. We pinpoint several problems with current evaluation methods that tend to overstate the capabilities of LLMs. We then articulate what artificial general intelligence should encompass beyond the capabilities of LLMs. We propose four characteristics of generally intelligent agents: 1) they can perform unlimited tasks; 2) they can generate new tasks within a context; 3) they operate based on a value system that underpins task generation; and 4) they have a world model reflecting reality, which shapes their interaction with the world. Building on this viewpoint, we highlight the missing pieces in artificial general intelligence, that is, the unity of knowing and acting. We argue that active engagement with objects in the real world delivers more robust signals for forming conceptual representations. Additionally, knowledge acquisition isn't solely reliant on passive input but requires repeated trials and errors. We conclude by outlining promising future research directions in the field of artificial general intelligence.

cs.CL↗

arXiv2023

Sympathetic cooling and slowing of molecules with Rydberg atoms

We propose to sympathetically slow and cool polar molecules in a cold, low-density beam using laser-cooled Rydberg atoms. The elastic collision cross sections between molecules and Rydberg atoms are large enough to efficiently thermalize the molecules even in a low density environment. Molecules traveling at 100 m/s can be stopped in under 30 collisions with little inelastic loss. Our method does not require photon scattering from the molecules and can be generically applied to complex species for applications in precision measurement, quantum information science, and controlled chemistry.

physics.atom-ph↗

arXiv2023

Event Detection from Social Media Stream: Methods, Datasets and Opportunities

Social media streams contain large and diverse amount of information, ranging from daily-life stories to the latest global and local events and news. Twitter, especially, allows a fast spread of events happening real time, and enables individuals and organizations to stay informed of the events happening now. Event detection from social media data poses different challenges from traditional text and is a research area that has attracted much attention in recent years. In this paper, we survey a wide range of event detection methods for Twitter data stream, helping readers understand the recent development in this area. We present the datasets available to the public. Furthermore, a few research opportunities

cs.SI↗

arXiv2023

MachMap: End-to-End Vectorized Solution for Compact HD-Map Construction

This report introduces the 1st place winning solution for the Autonomous Driving Challenge 2023 - Online HD-map Construction. By delving into the vectorization pipeline, we elaborate an effective architecture, termed as MachMap, which formulates the task of HD-map construction as the point detection paradigm in the bird-eye-view space with an end-to-end manner. Firstly, we introduce a novel map-compaction scheme into our framework, leading to reducing the number of vectorized points by 93% without any expression performance degradation. Build upon the above process, we then follow the general query-based paradigm and propose a strong baseline with integrating a powerful CNN-based backbone like InternImage, a temporal-based instance decoder and a well-designed point-mask coupling head. Additionally, an extra optional ensemble stage is utilized to refine model predictions for better performance. Our MachMap-tiny with IN-1K initialization achieves a mAP of 79.1 on the Argoverse2 benchmark and the further improved MachMap-huge reaches the best mAP of 83.5, outperforming all the other online HD-map construction approaches on the final leaderboard with a distinct performance margin (> 9.8 mAP at least).

cs.CV↗

arXiv2023

End-to-End Vectorized HD-map Construction with Piecewise Bezier Curve

Vectorized high-definition map (HD-map) construction, which focuses on the perception of centimeter-level environmental information, has attracted significant research interest in the autonomous driving community. Most existing approaches first obtain rasterized map with the segmentation-based pipeline and then conduct heavy post-processing for downstream-friendly vectorization. In this paper, by delving into parameterization-based methods, we pioneer a concise and elegant scheme that adopts unified piecewise Bezier curve. In order to vectorize changeful map elements end-to-end, we elaborate a simple yet effective architecture, named Piecewise Bezier HD-map Network (BeMapNet), which is formulated as a direct set prediction paradigm and postprocessing-free. Concretely, we first introduce a novel IPM-PE Align module to inject 3D geometry prior into BEV features through common position encoding in Transformer. Then a well-designed Piecewise Bezier Head is proposed to output the details of each map element, including the coordinate of control points and the segment number of curves. In addition, based on the progressively restoration of Bezier curve, we also present an efficient Point-Curve-Region Loss for supervising more robust and precise HD-map modeling. Extensive comparisons show that our method is remarkably superior to other existing SOTAs by 18.0 mAP at least.

cs.CV↗

arXiv2023

Control of an atomic quadrupole transition in a phase-stable standing wave

Using a single calcium ion confined in a surface-electrode trap, we study the interaction of electric quadrupole transitions with a passively phase-stable optical standing wave field sourced by photonics integrated within the trap. We characterize the optical fields through spatial mapping of the Rabi frequencies of both carrier and motional sideband transitions as well as AC Stark shifts. Our measurements demonstrate the ability to engineer favorable combinations of sideband and carrier Rabi frequency as well as AC Stark shifts for specific tasks in quantum state control and metrology.

physics.atom-ph↗

arXiv2023

An Infinite Family of Elliptic Ladder Integrals

We identify two families of ten-point Feynman diagrams that generalize the elliptic double box, and show that they can be expressed in terms of the same class of elliptic multiple polylogarithms to all loop orders. Interestingly, one of these families can also be written as a dlog form. For both families of diagrams, we provide new 2l-fold integral representations that are linearly reducible in all but one variable and that make the above properties manifest. We illustrate the simplicity of this integral representation by directly integrating the three-loop representative of both families of diagrams. These families also satisfy a pair of second-order differential equations, making them ideal examples on which to develop bootstrap techniques involving elliptic symbol letters at high loop orders.

hep-th↗