arXiv subjects

Yi Yang

Publications and source records attributed to Yi Yang.

At least 451 records · Page 25Linked to original sources

arXiv2024

Broadband measurement of Feibelman's quantum surface response functions

The Feibelman $d$-parameter, a mesoscopic complement to the local bulk permittivity, describes quantum optical surface responses for interfaces, including nonlocality, spill-in and-out, and surface-enabled Landau damping. It has been incorporated into the macroscopic Maxwellian framework for convenient modeling and understanding of nanoscale electromagnetic phenomena, calling for the compilation of a $d$-parameter database for interfaces of interest in nano-optics. However, accurate first-principles calculations of $d$-parameters face computational challenges, whereas existing measurements of $d$-parameters are scarce and restricted to narrow spectral windows. We demonstrate a general broadband ellipsometric approach to measure $d$-parameters at a gold--air interface across the visible--ultraviolet regimes. Gold is found to spill in and spill out at different frequencies. We also observe gold's Bennett mode, a surface-dipole resonance associated with a pole of the $d$-parameter, around 2.5 eV. Our measurements give rise to and are further validated by the passivity and Kramers--Kronig causality analysis of $d$-parameters. Our work advances the understanding of quantum surface response and may enable applications like enhanced electron field emission.

physics.optics↗

arXiv2024

Aggregating Nearest Sharp Features via Hybrid Transformers for Video Deblurring

Video deblurring methods, aiming at recovering consecutive sharp frames from a given blurry video, usually assume that the input video suffers from consecutively blurry frames. However, in real-world scenarios captured by modern imaging devices, sharp frames often interspersed within the video, providing temporally nearest sharp features that can aid in the restoration of blurry frames. In this work, we propose a video deblurring method that leverages both neighboring frames and existing sharp frames using hybrid Transformers for feature aggregation. Specifically, we first train a blur-aware detector to distinguish between sharp and blurry frames. Then, a window-based local Transformer is employed for exploiting features from neighboring frames, where cross attention is beneficial for aggregating features from neighboring frames without explicit spatial alignment. To aggregate nearest sharp features from detected sharp frames, we utilize a global Transformer with multi-scale matching capability. Moreover, our method can easily be extended to event-driven video deblurring by incorporating an event fusion module into the global Transformer. Extensive experiments on benchmark datasets demonstrate that our proposed method outperforms state-of-the-art video deblurring methods as well as event-driven video deblurring methods in terms of quantitative metrics and visual quality. The source code and trained models are available at https://github.com/shangwei5/STGTN.

cs.CV↗

arXiv2024

Synthetic gain for electron-beam spectroscopy

Electron-beam microscopy and spectroscopy featuring atomic-scale spatial resolution have become essential tools used daily in almost all branches of nanoscale science and technology. As a natural supercontinuum source of light, free electrons couple with phonons, plasmons, electron-hole pairs, inter- and intra-band transitions, and inner-shell ionization. The multiple excitations, intertwined with the intricate nature of nanostructured samples, present significant challenges in isolating specific spectral characteristics amidst complex experimental backgrounds. Here we introduce the approach of synthetic complex frequency waves to mitigate these challenges in free-electron--light interaction. The complex frequency waves, created through causality-informed coherent superposition of real-frequency waves induced by free electrons, offer virtual gain to offset material losses. This amplifies and enhances spectral features, as confirmed by our electron energy loss and cathodoluminescence measurements on multi-layer membranes, suspended nanoparticles, and film-coupled nanostructures. Strikingly, we reveal that our approach can retrieve resonance excitation completely buried underneath the zero-loss peak, substantially enhance the quality of hyperspectral imaging, and resolve entangled multiple-photon-electron events in their quantum interaction. Our findings indicate the versatile utility of complex frequency waves in various electron-beam spectroscopy and their promising diagnostic capabilities in free-electron quantum optics.

physics.optics↗

arXiv2024

MaGS: Reconstructing and Simulating Dynamic 3D Objects with Mesh-adsorbed Gaussian Splatting

3D reconstruction and simulation, although interrelated, have distinct objectives: reconstruction requires a flexible 3D representation that can adapt to diverse scenes, while simulation needs a structured representation to model motion principles effectively. This paper introduces the Mesh-adsorbed Gaussian Splatting (MaGS) method to address this challenge. MaGS constrains 3D Gaussians to roam near the mesh, creating a mutually adsorbed mesh-Gaussian 3D representation. Such representation harnesses both the rendering flexibility of 3D Gaussians and the structured property of meshes. To achieve this, we introduce RMD-Net, a network that learns motion priors from video data to refine mesh deformations, alongside RGD-Net, which models the relative displacement between the mesh and Gaussians to enhance rendering fidelity under mesh constraints. To generalize to novel, user-defined deformations beyond input video without reliance on temporal data, we propose MPE-Net, which leverages inherent mesh information to bootstrap RMD-Net and RGD-Net. Due to the universality of meshes, MaGS is compatible with various deformation priors such as ARAP, SMPL, and soft physics simulation. Extensive experiments on the D-NeRF, DG-Mesh, and PeopleSnapshot datasets demonstrate that MaGS achieves state-of-the-art performance in both reconstruction and simulation.

cs.CV↗

arXiv2024

Synthetic non-Abelian Electric Fields and Spin-Orbit Coupling in Photonic Synthetic Dimensions

We theoretically propose a scheme to synthesize photonic non-Abelian electric field and spin-orbit coupling (SOC) in the synthetic frequency dimension based on a polarization-multiplexed time-modulated ring resonator. Inside the ring resonator, the cascade of polarization-dependent phase modulation, polarization rotation, and phase retardation enables a photonic realization of minimal SOC composed of equal Rashba and Dresselhaus terms. The synthetic bands and associated spin textures can be effectively probed by the continuous-wave polarization- and time-resolved band structure measurements. Meanwhile, the pulse dynamics in the frequency dimension can be manipulated by both synthetic Abelian and non-Abelian electric fields, leading to Bloch oscillation, Zitterbewegung, and their interplay dynamics. Our proposed setup can be realized with free-space optics, fibers, and integrated photonics, and provides pseudospin control knobs for large-scale synthetic lattices based on frequency combs.

physics.optics↗

arXiv2024

Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models

Diffusion models have revitalized the image generation domain, playing crucial roles in both academic research and artistic expression. With the emergence of new diffusion models, assessing the performance of text-to-image models has become increasingly important. Current metrics focus on directly matching the input text with the generated image, but due to cross-modal information asymmetry, this leads to unreliable or incomplete assessment results. Motivated by this, we introduce the Image Regeneration task in this study to assess text-to-image models by tasking the T2I model with generating an image according to the reference image. We use GPT4V to bridge the gap between the reference image and the text input for the T2I model, allowing T2I models to understand image content. This evaluation process is simplified as comparisons between the generated image and the reference image are straightforward. Two regeneration datasets spanning content-diverse and style-diverse evaluation dataset are introduced to evaluate the leading diffusion models currently available. Additionally, we present ImageRepainter framework to enhance the quality of generated images by improving content comprehension via MLLM guided iterative generation and revision. Our comprehensive experiments have showcased the effectiveness of this framework in assessing the generative capabilities of models. By leveraging MLLM, we have demonstrated that a robust T2M can produce images more closely resembling the reference image.

cs.CV↗

arXiv2024

Moving Off-the-Grid: Scene-Grounded Video Representations

Current vision models typically maintain a fixed correspondence between their representation structure and image space. Each layer comprises a set of tokens arranged "on-the-grid," which biases patches or tokens to encode information at a specific spatio(-temporal) location. In this work we present Moving Off-the-Grid (MooG), a self-supervised video representation model that offers an alternative approach, allowing tokens to move "off-the-grid" to better enable them to represent scene elements consistently, even as they move across the image plane through time. By using a combination of cross-attention and positional embeddings we disentangle the representation structure and image structure. We find that a simple self-supervised objective--next frame prediction--trained on video data, results in a set of latent tokens which bind to specific scene structures and track them as they move. We demonstrate the usefulness of MooG's learned representation both qualitatively and quantitatively by training readouts on top of the learned representation on a variety of downstream tasks. We show that MooG can provide a strong foundation for different vision tasks when compared to "on-the-grid" baselines.

cs.CV↗

arXiv2024

NeuroFly: A framework for whole-brain single neuron reconstruction

Neurons, with their elongated, tree-like dendritic and axonal structures, enable efficient signal integration and long-range communication across brain regions. By reconstructing individual neurons' morphology, we can gain valuable insights into brain connectivity, revealing the structure basis of cognition, movement, and perception. Despite the accumulation of extensive 3D microscopic imaging data, progress has been considerably hindered by the absence of automated tools to streamline this process. Here we introduce NeuroFly, a validated framework for large-scale automatic single neuron reconstruction. This framework breaks down the process into three distinct stages: segmentation, connection, and proofreading. In the segmentation stage, we perform automatic segmentation followed by skeletonization to generate over-segmented neuronal fragments without branches. During the connection stage, we use a 3D image-based path following approach to extend each fragment and connect it with other fragments of the same neuron. Finally, human annotators are required only to proofread the few unresolved positions. The first two stages of our process are clearly defined computer vision problems, and we have trained robust baseline models to solve them. We validated NeuroFly's efficiency using in-house datasets that include a variety of challenging scenarios, such as dense arborizations, weak axons, images with contamination. We will release the datasets along with a suite of visualization and annotation tools for better reproducibility. Our goal is to foster collaboration among researchers to address the neuron reconstruction challenge, ultimately accelerating advancements in neuroscience research. The dataset and code are available at https://github.com/beanli161514/neurofly

cs.CV↗

arXiv2024

LCP-Fusion: A Neural Implicit SLAM with Enhanced Local Constraints and Computable Prior

Recently the dense Simultaneous Localization and Mapping (SLAM) based on neural implicit representation has shown impressive progress in hole filling and high-fidelity mapping. Nevertheless, existing methods either heavily rely on known scene bounds or suffer inconsistent reconstruction due to drift in potential loop-closure regions, or both, which can be attributed to the inflexible representation and lack of local constraints. In this paper, we present LCP-Fusion, a neural implicit SLAM system with enhanced local constraints and computable prior, which takes the sparse voxel octree structure containing feature grids and SDF priors as hybrid scene representation, enabling the scalability and robustness during mapping and tracking. To enhance the local constraints, we propose a novel sliding window selection strategy based on visual overlap to address the loop-closure, and a practical warping loss to constrain relative poses. Moreover, we estimate SDF priors as coarse initialization for implicit features, which brings additional explicit constraints and robustness, especially when a light but efficient adaptive early ending is adopted. Experiments demonstrate that our method achieve better localization accuracy and reconstruction consistency than existing RGB-D implicit SLAM, especially in challenging real scenes (ScanNet) as well as self-captured scenes with unknown scene bounds. The code is available at https://github.com/laliwang/LCP-Fusion.

cs.RO↗

arXiv2024

Exploring the Interplay Between Video Generation and World Models in Autonomous Driving: A Survey

World models and video generation are pivotal technologies in the domain of autonomous driving, each playing a critical role in enhancing the robustness and reliability of autonomous systems. World models, which simulate the dynamics of real-world environments, and video generation models, which produce realistic video sequences, are increasingly being integrated to improve situational awareness and decision-making capabilities in autonomous vehicles. This paper investigates the relationship between these two technologies, focusing on how their structural parallels, particularly in diffusion-based models, contribute to more accurate and coherent simulations of driving scenarios. We examine leading works such as JEPA, Genie, and Sora, which exemplify different approaches to world model design, thereby highlighting the lack of a universally accepted definition of world models. These diverse interpretations underscore the field's evolving understanding of how world models can be optimized for various autonomous driving tasks. Furthermore, this paper discusses the key evaluation metrics employed in this domain, such as Chamfer distance for 3D scene reconstruction and Fréchet Inception Distance (FID) for assessing the quality of generated video content. By analyzing the interplay between video generation and world models, this survey identifies critical challenges and future research directions, emphasizing the potential of these technologies to jointly advance the performance of autonomous driving systems. The findings presented in this paper aim to provide a comprehensive understanding of how the integration of video generation and world models can drive innovation in the development of safer and more reliable autonomous vehicles.

cs.AI↗

arXiv2024

Luminous Type II Short-Plateau SN 2023ufx: Asymmetric Explosion of a Partially-Stripped Massive Progenitor

We present supernova (SN) 2023ufx, a unique Type IIP SN with the shortest known plateau duration ($t_\mathrm{PT}$ $\sim$47 days), a luminous V-band peak ($M_{V}$ = $-$18.42 $\pm$ 0.08 mag), and a rapid early decline rate ($s1$ = 3.47 $\pm$ 0.09 mag (50 days)$^{-1}$). By comparing observed photometry to a hydrodynamic MESA+STELLA model grid, we constrain the progenitor to be a massive red supergiant with M$_\mathrm{ZAMS}$ $\simeq$19 - 25 M$_{\odot}$. Independent comparisons with nebular spectral models also suggest an initial He-core mass of $\sim$6 M$_{\odot}$, and thus a massive progenitor. For a Type IIP, SN 2023ufx produced an unusually high amount of nickel ($^{56}$Ni) $\sim$0.14 $\pm$ 0.02 M$_{\odot}$, during the explosion. We find that the short plateau duration in SN 2023ufx can be explained with the presence of a small hydrogen envelope (M$_\mathrm{H_\mathrm{env}}$ $\simeq$1.2 M$_{\odot}$), suggesting partial stripping of the progenitor. About $\simeq$0.09 M$_{\odot}$ of CSM through mass loss from late-time stellar evolution of the progenitor is needed to fit the early time ($\lesssim$10 days) pseudo-bolometric light curve. Nebular line diagnostics of broad and multi-peak components of [O I] $λλ$6300, 6364, H$α$, and [Ca II] $λλ$7291, 7323 suggest that the explosion of SN 2023ufx could be inherently asymmetric, preferentially ejecting material along our line-of-sight.

astro-ph.HE↗

arXiv2024

TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment

Recent advancements in image understanding have benefited from the extensive use of web image-text pairs. However, video understanding remains a challenge despite the availability of substantial web video-text data. This difficulty primarily arises from the inherent complexity of videos and the inefficient language supervision in recent web-collected video-text datasets. In this paper, we introduce Text-Only Pre-Alignment (TOPA), a novel approach to extend large language models (LLMs) for video understanding, without the need for pre-training on real video data. Specifically, we first employ an advanced LLM to automatically generate Textual Videos comprising continuous textual frames, along with corresponding annotations to simulate real video-text data. Then, these annotated textual videos are used to pre-align a language-only LLM with the video modality. To bridge the gap between textual and real videos, we employ the CLIP model as the feature extractor to align image and text modalities. During text-only pre-alignment, the continuous textual frames, encoded as a sequence of CLIP text features, are analogous to continuous CLIP image features, thus aligning the LLM with real video representation. Extensive experiments, including zero-shot evaluation and finetuning on various video understanding tasks, demonstrate that TOPA is an effective and efficient framework for aligning video content with LLMs. In particular, without training on any video data, the TOPA-Llama2-13B model achieves a Top-1 accuracy of 51.0% on the challenging long-form video understanding benchmark, Egoschema. This performance surpasses previous video-text pre-training approaches and proves competitive with recent GPT-3.5-based video agents.

cs.CV↗

arXiv2024

Dessie: Disentanglement for Articulated 3D Horse Shape and Pose Estimation from Images

In recent years, 3D parametric animal models have been developed to aid in estimating 3D shape and pose from images and video. While progress has been made for humans, it's more challenging for animals due to limited annotated data. To address this, we introduce the first method using synthetic data generation and disentanglement to learn to regress 3D shape and pose. Focusing on horses, we use text-based texture generation and a synthetic data pipeline to create varied shapes, poses, and appearances, learning disentangled spaces. Our method, Dessie, surpasses existing 3D horse reconstruction methods and generalizes to other large animals like zebras, cows, and deer. See the project website at: \url{https://celiali.github.io/Dessie/}.

cs.CV↗

arXiv2024

VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions

Visual imitation learning (VIL) provides an efficient and intuitive strategy for robotic systems to acquire novel skills. Recent advancements in Vision Language Models (VLMs) have demonstrated remarkable performance in vision and language reasoning capabilities for VIL tasks. Despite the progress, current VIL methods naively employ VLMs to learn high-level plans from human videos, relying on pre-defined motion primitives for executing physical interactions, which remains a major bottleneck. In this work, we present VLMimic, a novel paradigm that harnesses VLMs to directly learn even fine-grained action levels, only given a limited number of human videos. Specifically, VLMimic first grounds object-centric movements from human videos, and learns skills using hierarchical constraint representations, facilitating the derivation of skills with fine-grained action levels from limited human videos. These skills are refined and updated through an iterative comparison strategy, enabling efficient adaptation to unseen environments. Our extensive experiments exhibit that our VLMimic, using only 5 human videos, yields significant improvements of over 27% and 21% in RLBench and real-world manipulation tasks, and surpasses baselines by over 37% in long-horizon tasks.

cs.RO↗

arXiv2024

Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesis

Generalizable 3D Gaussian splitting (3DGS) can reconstruct new scenes from sparse-view observations in a feed-forward inference manner, eliminating the need for scene-specific retraining required in conventional 3DGS. However, existing methods rely heavily on epipolar priors, which can be unreliable in complex realworld scenes, particularly in non-overlapping and occluded regions. In this paper, we propose eFreeSplat, an efficient feed-forward 3DGS-based model for generalizable novel view synthesis that operates independently of epipolar line constraints. To enhance multiview feature extraction with 3D perception, we employ a selfsupervised Vision Transformer (ViT) with cross-view completion pre-training on large-scale datasets. Additionally, we introduce an Iterative Cross-view Gaussians Alignment method to ensure consistent depth scales across different views. Our eFreeSplat represents an innovative approach for generalizable novel view synthesis. Different from the existing pure geometry-free methods, eFreeSplat focuses more on achieving epipolar-free feature matching and encoding by providing 3D priors through cross-view pretraining. We evaluate eFreeSplat on wide-baseline novel view synthesis tasks using the RealEstate10K and ACID datasets. Extensive experiments demonstrate that eFreeSplat surpasses state-of-the-art baselines that rely on epipolar priors, achieving superior geometry reconstruction and novel view synthesis quality. Project page: https://tatakai1.github.io/efreesplat/.

cs.CV↗

arXiv2024

An Isodiametric Problem with Additional Constraints in Euclidean space R^3

Let $C_θ$ be a circular cone in Euclidean space $\mathbb{R}^{3}$,which apex is the origin and apex angle of the cone is $θ\in \left(π/3, π\right)$. Let $M_θ$ be the class of compact convex domains in Euclidean space $\mathbb{R}^{3}$, which have diameter one, contains the origin and are included in $C_θ$. In this paper, we show that there is a unique compact convex domain with maximal volume and also we determine the shape of the above domain.

math.DS↗

arXiv2024

Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models

Prevalent human-object interaction (HOI) detection approaches typically leverage large-scale visual-linguistic models to help recognize events involving humans and objects. Though promising, models trained via contrastive learning on text-image pairs often neglect mid/low-level visual cues and struggle at compositional reasoning. In response, we introduce DIFFUSIONHOI, a new HOI detector shedding light on text-to-image diffusion models. Unlike the aforementioned models, diffusion models excel in discerning mid/low-level visual concepts as generative models, and possess strong compositionality to handle novel concepts expressed in text inputs. Considering diffusion models usually emphasize instance objects, we first devise an inversion-based strategy to learn the expression of relation patterns between humans and objects in embedding space. These learned relation embeddings then serve as textual prompts, to steer diffusion models generate images that depict specific interactions, and extract HOI-relevant cues from images without heavy fine-tuning. Benefited from above, DIFFUSIONHOI achieves SOTA performance on three datasets under both regular and zero-shot setups.

cs.CV↗

arXiv2024

SPROUT: an Interactive Authoring Tool for Generating Programming Tutorials with the Visualization of Large Language Models

The rapid development of large language models (LLMs), such as ChatGPT, has revolutionized the efficiency of creating programming tutorials. LLMs can be instructed with text prompts to generate comprehensive text descriptions of code snippets. However, the lack of transparency in the end-to-end generation process has hindered the understanding of model behavior and limited user control over the generated results. To tackle this challenge, we introduce a novel approach that breaks down the programming tutorial creation task into actionable steps. By employing the tree-of-thought method, LLMs engage in an exploratory process to generate diverse and faithful programming tutorials. We then present SPROUT, an authoring tool equipped with a series of interactive visualizations that empower users to have greater control and understanding of the programming tutorial creation process. A formal user study demonstrated the effectiveness of SPROUT, showing that our tool assists users to actively participate in the programming tutorial creation process, leading to more reliable and customizable results. By providing users with greater control and understanding, SPROUT enhances the user experience and improves the overall quality of programming tutorial. A free copy of this paper and all supplemental materials are available at https://osf.io/uez2t/?view_only=5102e958802341daa414707646428f86.

cs.HC↗