arXiv subjects

Rui Ma

Publications and source records attributed to Rui Ma.

At least 91 records · Page 5Linked to original sources

arXiv2024

DiffPop: Plausibility-Guided Object Placement Diffusion for Image Composition

In this paper, we address the problem of plausible object placement for the challenging task of realistic image composition. We propose DiffPop, the first framework that utilizes plausibility-guided denoising diffusion probabilistic model to learn the scale and spatial relations among multiple objects and the corresponding scene image. First, we train an unguided diffusion model to directly learn the object placement parameters in a self-supervised manner. Then, we develop a human-in-the-loop pipeline which exploits human labeling on the diffusion-generated composite images to provide the weak supervision for training a structural plausibility classifier. The classifier is further used to guide the diffusion sampling process towards generating the plausible object placement. Experimental results verify the superiority of our method for producing plausible and diverse composite images on the new Cityscapes-OP dataset and the public OPA dataset, as well as demonstrate its potential in applications such as data augmentation and multi-object placement tasks. Our dataset and code will be released.

cs.CV↗

arXiv2024

Self-locked broadband Raman-electro-optic microcomb

Optical frequency combs (OFCs), composed of equally spaced frequency tones, have spurred advancements in communications, spectroscopy, precision measurement and fundamental physics research. A prevalent method for generating OFCs involves the electro-optic (EO) effect, i.e., EO comb, renowned for its rapid tunability via precise microwave field control. Recent advances in integrated lithium niobate (LN) photonics have greatly enhanced the efficiency of EO effect, enabling the generation of broadband combs with reduced microwave power. However, parasitic nonlinear effects, such as Raman scattering and four-wave mixing, often emerge in high quality nonlinear devices, impeding the expansion of comb bandwidth and the minimization of frequency noise. Here, we tame these nonlinear effects and present a novel type of OFC, i.e., the self-locked Raman-electro-optic (REO) microcomb by leveraging the collaboration of EO, Kerr and Raman scattering processes. The spectral width of the REO microcomb benefits from the Raman gain and Kerr effect, encompassing nearly 1400 comb lines spanning over 300 nm with a fine repetition rate of 26.03 GHz, much larger than the pure EO combs. Remarkably, the system can maintain a self-locked low-noise state in the presence of multiple nonlinearities without the need for external active feedback. Our approach points to a direction for improving the performance of microcombs and paves the way for exploring new nonlinear physics, such as new laser locking techniques, through the collaboration of inevitable multiple nonlinear effects in integrated photonics.

physics.optics↗

arXiv2024

GaussianPrediction: Dynamic 3D Gaussian Prediction for Motion Extrapolation and Free View Synthesis

Forecasting future scenarios in dynamic environments is essential for intelligent decision-making and navigation, a challenge yet to be fully realized in computer vision and robotics. Traditional approaches like video prediction and novel-view synthesis either lack the ability to forecast from arbitrary viewpoints or to predict temporal dynamics. In this paper, we introduce GaussianPrediction, a novel framework that empowers 3D Gaussian representations with dynamic scene modeling and future scenario synthesis in dynamic environments. GaussianPrediction can forecast future states from any viewpoint, using video observations of dynamic scenes. To this end, we first propose a 3D Gaussian canonical space with deformation modeling to capture the appearance and geometry of dynamic scenes, and integrate the lifecycle property into Gaussians for irreversible deformations. To make the prediction feasible and efficient, a concentric motion distillation approach is developed by distilling the scene motion with key points. Finally, a Graph Convolutional Network is employed to predict the motions of key points, enabling the rendering of photorealistic images of future scenarios. Our framework shows outstanding performance on both synthetic and real-world datasets, demonstrating its efficacy in predicting and rendering future environments.

cs.CV↗

arXiv2024

Real-time equilibrium reconstruction by neural network based on HL-3 tokamak

A neural network model, EFITNN, has been developed capable of real-time magnetic equilibrium reconstruction based on HL-3 tokamak magnetic measurement signals. The model processes inputs from 68 channels of magnetic measurement data gathered from 1159 HL-3 experimental discharges, including plasma current, loop voltage, and the poloidal magnetic fields measured by equilibrium probes. The outputs of the model feature eight key plasma parameters, alongside high-resolution ($129\times129$) reconstructions of the toroidal current density $J_{\text P}$ and poloidal magnetic flux profiles $Ψ_{rz}$. Moreover, the network's architecture employs a multi-task learning structure, which enables the sharing of weights and mutual correction among different outputs, and lead to increase the model's accuracy by up to 32%. The performance of EFITNN demonstrates remarkable consistency with the offline EFIT, achieving average $R^2 = 0.941, 0.997$ and $0.959$ for eight plasma parameters, $Ψ_{rz}$ and $J_{\text P}$, respectively. The model's robust generalization capabilities are particularly evident in its successful predictions of quasi-snowflake (QSF) divertor configurations and its adept handling of data from shot numbers or plasma current intervals not previously encountered during training. Compared to numerical methods, EFITNN significantly enhances computational efficiency with average computation time ranging from 0.08ms to 0.45ms, indicating its potential utility in real-time isoflux control and plasma profile management.

physics.plasm-ph↗

arXiv2024

Broadband microwave-rate dark pulse microcombs in dissipation-engineered LiNbO$_3$ microresonators

Kerr microcombs generated in optical microresonators provide broadband light sources bridging optical and microwave signals. Their translation to thin-film lithium niobate unlocks second-order nonlinear optical interfaces such as electro-optic modulation and frequency doubling for completing comb functionalities. However, the strong Raman response of LiNbO$_3$ has complicated the formation of Kerr microcombs. Until now, dark pulse microcombs, requiring a double balance between Kerr nonlinearity and normal group velocity dispersion as well as gain and loss, have remained elusive in LiNbO$_3$ microresonators. Here, by incorporating dissipation engineering, we demonstrate dark pulse microcombs with 25 GHz repetition frequency and 200 nm span in a high-$Q$ LiNbO$_3$ microresonator. Resonances near the Raman-active wavelengths are strongly damped by controlling phase-matching conditions of a specially designed pulley coupler. The coherence and tunability of the dark pulse microcombs are also investigated. Our work provides a solution to realize high-power microcombs operating at microwave rates on LiNbO$_3$ chips, promising new opportunities for the monolithic integration of applications spanning communication to microwave photonics.

physics.optics↗

arXiv2024

PGAHum: Prior-Guided Geometry and Appearance Learning for High-Fidelity Animatable Human Reconstruction

Recent techniques on implicit geometry representation learning and neural rendering have shown promising results for 3D clothed human reconstruction from sparse video inputs. However, it is still challenging to reconstruct detailed surface geometry and even more difficult to synthesize photorealistic novel views with animated human poses. In this work, we introduce PGAHum, a prior-guided geometry and appearance learning framework for high-fidelity animatable human reconstruction. We thoroughly exploit 3D human priors in three key modules of PGAHum to achieve high-quality geometry reconstruction with intricate details and photorealistic view synthesis on unseen poses. First, a prior-based implicit geometry representation of 3D human, which contains a delta SDF predicted by a tri-plane network and a base SDF derived from the prior SMPL model, is proposed to model the surface details and the body shape in a disentangled manner. Second, we introduce a novel prior-guided sampling strategy that fully leverages the prior information of the human pose and body to sample the query points within or near the body surface. By avoiding unnecessary learning in the empty 3D space, the neural rendering can recover more appearance details. Last, we propose a novel iterative backward deformation strategy to progressively find the correspondence for the query point in observation space. A skinning weights prediction model is learned based on the prior provided by the SMPL model to achieve the iterative backward LBS deformation. Extensive quantitative and qualitative comparisons on various datasets are conducted and the results demonstrate the superiority of our framework. Ablation studies also verify the effectiveness of each scheme for geometry and appearance learning.

cs.CV↗

arXiv2024

D-Aug: Enhancing Data Augmentation for Dynamic LiDAR Scenes

Creating large LiDAR datasets with pixel-level labeling poses significant challenges. While numerous data augmentation methods have been developed to reduce the reliance on manual labeling, these methods predominantly focus on static scenes and they overlook the importance of data augmentation for dynamic scenes, which is critical for autonomous driving. To address this issue, we propose D-Aug, a LiDAR data augmentation method tailored for augmenting dynamic scenes. D-Aug extracts objects and inserts them into dynamic scenes, considering the continuity of these objects across consecutive frames. For seamless insertion into dynamic scenes, we propose a reference-guided method that involves dynamic collision detection and rotation alignment. Additionally, we present a pixel-level road identification strategy to efficiently determine suitable insertion positions. We validated our method using the nuScenes dataset with various 3D detection and tracking methods. Comparative experiments demonstrate the superiority of D-Aug.

cs.CV↗

arXiv2024

Mixed Variational Formulation of Coupled Plates

This paper proposes a mixed variational formulation for the problem of two coupled plates with a rigid {junction}. The proposed mixed {formulation} introduces {the union of} stresses and moments as {an auxiliary variable}, which {are} commonly of great interest in practical applications. The primary challenge lies in determining a suitable {space involving} both boundary and junction conditions of the auxiliary variable. The {theory} of densely defined operators in Hilbert spaces is employed to define {a nonstandard Sobolev space} without the use of trace operators. The well-posedness is established for the mixed formulation. Based on these conditions, this paper provides a framework {of} conforming {mixed} finite element methods. Numerical experiments are given to validate the theoretical results.

math.NA↗

arXiv2024

PiGW: A Plug-in Generative Watermarking Framework

Integrating watermarks into generative images is a critical strategy for protecting intellectual property and enhancing artificial intelligence security. This paper proposes Plug-in Generative Watermarking (PiGW) as a general framework for integrating watermarks into generative images. More specifically, PiGW embeds watermark information into the initial noise using a learnable watermark embedding network and an adaptive frequency spectrum mask. Furthermore, it optimizes training costs by gradually increasing timesteps. Extensive experiments demonstrate that PiGW enables embedding watermarks into the generated image with negligible quality loss while achieving true invisibility and high resistance to noise attacks. Moreover, PiGW can serve as a plugin for various commonly used generative structures and multimodal generative content types. Finally, we demonstrate how PiGW can also be utilized for detecting generated images, contributing to the promotion of secure AI development. The project code will be made available on GitHub.

cs.MM↗

arXiv2024

OSTAF: A One-Shot Tuning Method for Improved Attribute-Focused T2I Personalization

Personalized text-to-image (T2I) models not only produce lifelike and varied visuals but also allow users to tailor the images to fit their personal taste. These personalization techniques can grasp the essence of a concept through a collection of images, or adjust a pre-trained text-to-image model with a specific image input for subject-driven or attribute-aware guidance. Yet, accurately capturing the distinct visual attributes of an individual image poses a challenge for these methods. To address this issue, we introduce OSTAF, a novel parameter-efficient one-shot fine-tuning method which only utilizes one reference image for T2I personalization. A novel hypernetwork-powered attribute-focused fine-tuning mechanism is employed to achieve the precise learning of various attribute features (e.g., appearance, shape or drawing style) from the reference image. Comparing to existing image customization methods, our method shows significant superiority in attribute identification and application, as well as achieves a good balance between efficiency and output quality.

cs.CV↗

arXiv2024

SemanticHuman-HD: High-Resolution Semantic Disentangled 3D Human Generation

With the development of neural radiance fields and generative models, numerous methods have been proposed for learning 3D human generation from 2D images. These methods allow control over the pose of the generated 3D human and enable rendering from different viewpoints. However, none of these methods explore semantic disentanglement in human image synthesis, i.e., they can not disentangle the generation of different semantic parts, such as the body, tops, and bottoms. Furthermore, existing methods are limited to synthesize images at $512^2$ resolution due to the high computational cost of neural radiance fields. To address these limitations, we introduce SemanticHuman-HD, the first method to achieve semantic disentangled human image synthesis. Notably, SemanticHuman-HD is also the first method to achieve 3D-aware image synthesis at $1024^2$ resolution, benefiting from our proposed 3D-aware super-resolution module. By leveraging the depth maps and semantic masks as guidance for the 3D-aware super-resolution, we significantly reduce the number of sampling points during volume rendering, thereby reducing the computational cost. Our comparative experiments demonstrate the superiority of our method. The effectiveness of each proposed component is also verified through ablation studies. Moreover, our method opens up exciting possibilities for various applications, including 3D garment generation, semantic-aware image synthesis, controllable image synthesis, and out-of-domain image synthesis.

cs.CV↗

arXiv2024

3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation

Text-driven 3D scene generation techniques have made rapid progress in recent years. Their success is mainly attributed to using existing generative models to iteratively perform image warping and inpainting to generate 3D scenes. However, these methods heavily rely on the outputs of existing models, leading to error accumulation in geometry and appearance that prevent the models from being used in various scenarios (e.g., outdoor and unreal scenarios). To address this limitation, we generatively refine the newly generated local views by querying and aggregating global 3D information, and then progressively generate the 3D scene. Specifically, we employ a tri-plane features-based NeRF as a unified representation of the 3D scene to constrain global 3D consistency, and propose a generative refinement network to synthesize new contents with higher quality by exploiting the natural image prior from 2D diffusion model as well as the global 3D information of the current scene. Our extensive experiments demonstrate that, in comparison to previous methods, our approach supports wide variety of scene generation and arbitrary camera trajectories with improved visual quality and 3D consistency.

cs.CV↗

arXiv2024

Contemporary Recommendation Systems on Big Data and Their Applications: A Survey

This survey paper conducts a comprehensive analysis of the evolution and contemporary landscape of recommendation systems, which have been extensively incorporated across a myriad of web applications. It delves into the progression of personalized recommendation methodologies tailored for online products or services, organizing the array of recommendation techniques into four main categories: content-based, collaborative filtering, knowledge-based, and hybrid approaches, each designed to cater to specific contexts. The document provides an in-depth review of both the historical underpinnings and the cutting-edge innovations in the domain of recommendation systems, with a special focus on implementations leveraging big data analytics. The paper also highlights the utilization of prominent datasets such as MovieLens, Amazon Reviews, Netflix Prize, Last.fm, and Yelp in evaluating recommendation algorithms. It further outlines and explores the predominant challenges encountered in the current generation of recommendation systems, including issues related to data sparsity, scalability, and the imperative for diversified recommendation outputs. The survey underscores these challenges as promising directions for subsequent research endeavors within the discipline. Additionally, the paper examines various real-life applications driven by recommendation systems, addressing the hurdles involved in seamlessly integrating these systems into everyday life. Ultimately, the survey underscores how the advancements in recommendation systems, propelled by big data technologies, have the potential to significantly enhance real-world experiences.

cs.IR↗

arXiv2024

TaylorGrid: Towards Fast and High-Quality Implicit Field Learning via Direct Taylor-based Grid Optimization

Coordinate-based neural implicit representation or implicit fields have been widely studied for 3D geometry representation or novel view synthesis. Recently, a series of efforts have been devoted to accelerating the speed and improving the quality of the coordinate-based implicit field learning. Instead of learning heavy MLPs to predict the neural implicit values for the query coordinates, neural voxels or grids combined with shallow MLPs have been proposed to achieve high-quality implicit field learning with reduced optimization time. On the other hand, lightweight field representations such as linear grid have been proposed to further improve the learning speed. In this paper, we aim for both fast and high-quality implicit field learning, and propose TaylorGrid, a novel implicit field representation which can be efficiently computed via direct Taylor expansion optimization on 2D or 3D grids. As a general representation, TaylorGrid can be adapted to different implicit fields learning tasks such as SDF learning or NeRF. From extensive quantitative and qualitative comparisons, TaylorGrid achieves a balance between the linear grid and neural voxels, showing its superiority in fast and high-quality implicit field learning.

cs.CV↗

arXiv2024

EPSD: Early Pruning with Self-Distillation for Efficient Model Compression

Neural network compression techniques, such as knowledge distillation (KD) and network pruning, have received increasing attention. Recent work `Prune, then Distill' reveals that a pruned student-friendly teacher network can benefit the performance of KD. However, the conventional teacher-student pipeline, which entails cumbersome pre-training of the teacher and complicated compression steps, makes pruning with KD less efficient. In addition to compressing models, recent compression techniques also emphasize the aspect of efficiency. Early pruning demands significantly less computational cost in comparison to the conventional pruning methods as it does not require a large pre-trained model. Likewise, a special case of KD, known as self-distillation (SD), is more efficient since it requires no pre-training or student-teacher pair selection. This inspires us to collaborate early pruning with SD for efficient model compression. In this work, we propose the framework named Early Pruning with Self-Distillation (EPSD), which identifies and preserves distillable weights in early pruning for a given SD task. EPSD efficiently combines early pruning and self-distillation in a two-step process, maintaining the pruned network's trainability for compression. Instead of a simple combination of pruning and SD, EPSD enables the pruned network to favor SD by keeping more distillable weights before training to ensure better distillation of the pruned network. We demonstrated that EPSD improves the training of pruned networks, supported by visual and quantitative analyses. Our evaluation covered diverse benchmarks (CIFAR-10/100, Tiny-ImageNet, full ImageNet, CUB-200-2011, and Pascal VOC), with EPSD outperforming advanced pruning and SD techniques.

cs.LG↗

arXiv2024

3D-SSGAN: Lifting 2D Semantics for 3D-Aware Compositional Portrait Synthesis

Existing 3D-aware portrait synthesis methods can generate impressive high-quality images while preserving strong 3D consistency. However, most of them cannot support the fine-grained part-level control over synthesized images. Conversely, some GAN-based 2D portrait synthesis methods can achieve clear disentanglement of facial regions, but they cannot preserve view consistency due to a lack of 3D modeling abilities. To address these issues, we propose 3D-SSGAN, a novel framework for 3D-aware compositional portrait image synthesis. First, a simple yet effective depth-guided 2D-to-3D lifting module maps the generated 2D part features and semantics to 3D. Then, a volume renderer with a novel 3D-aware semantic mask renderer is utilized to produce the composed face features and corresponding masks. The whole framework is trained end-to-end by discriminating between real and synthesized 2D images and their semantic masks. Quantitative and qualitative evaluations demonstrate the superiority of 3D-SSGAN in controllable part-level synthesis while preserving 3D view consistency.

cs.CV↗

arXiv2023

P2M2-Net: Part-Aware Prompt-Guided Multimodal Point Cloud Completion

Inferring missing regions from severely occluded point clouds is highly challenging. Especially for 3D shapes with rich geometry and structure details, inherent ambiguities of the unknown parts are existing. Existing approaches either learn a one-to-one mapping in a supervised manner or train a generative model to synthesize the missing points for the completion of 3D point cloud shapes. These methods, however, lack the controllability for the completion process and the results are either deterministic or exhibiting uncontrolled diversity. Inspired by the prompt-driven data generation and editing, we propose a novel prompt-guided point cloud completion framework, coined P2M2-Net, to enable more controllable and more diverse shape completion. Given an input partial point cloud and a text prompt describing the part-aware information such as semantics and structure of the missing region, our Transformer-based completion network can efficiently fuse the multimodal features and generate diverse results following the prompt guidance. We train the P2M2-Net on a new large-scale PartNet-Prompt dataset and conduct extensive experiments on two challenging shape completion benchmarks. Quantitative and qualitative results show the efficacy of incorporating prompts for more controllable part-aware point cloud completion and generation. Code and data are available at https://github.com/JLU-ICL/P2M2-Net.

cs.CV↗

arXiv2023

Second-harmonic generation with a 440,000% W-1 conversion efficiency in a lithium niobate microcavity without periodic poling

Thin-film lithium niobate (TFLN) enables extremely high-efficiency second-order nonlinear optical effects due to large nonlinear coefficient d33 and strong optical field localization. Here, we first designed and fabricated a pulley-waveguide-coupled microring resonator with an intrinsic quality factor above 9.4 x10^5 on the reverse-polarized double-layer X-cut TFLN. In such a TFLN resonator without fine domain structures, second harmonic generation with an absolute (normalized) conversion efficiency of 30% (440,000% W-1), comparable to that in periodically poled lithium niobate (PPLN) microring resonators, was realized with a sub-microwatt continuous pump. This work reduces the dependence of high-efficiency nonlinear frequency conversion on PPLN microcavities that are difficult to prepare.

physics.optics↗