arXiv subjects

Keming Wu

Publications and source records attributed to Keming Wu.

22 records · Page 2Linked to original sources

arXiv2025

PrismLayers: Open Data for High-Quality Multi-Layer Transparent Image Generative Models

Generating high-quality, multi-layer transparent images from text prompts can unlock a new level of creative control, allowing users to edit each layer as effortlessly as editing text outputs from LLMs. However, the development of multi-layer generative models lags behind that of conventional text-to-image models due to the absence of a large, high-quality corpus of multi-layer transparent data. In this paper, we address this fundamental challenge by: (i) releasing the first open, ultra-high-fidelity PrismLayers (PrismLayersPro) dataset of 200K (20K) multilayer transparent images with accurate alpha mattes, (ii) introducing a trainingfree synthesis pipeline that generates such data on demand using off-the-shelf diffusion models, and (iii) delivering a strong, open-source multi-layer generation model, ART+, which matches the aesthetics of modern text-to-image generation models. The key technical contributions include: LayerFLUX, which excels at generating high-quality single transparent layers with accurate alpha mattes, and MultiLayerFLUX, which composes multiple LayerFLUX outputs into complete images, guided by human-annotated semantic layout. To ensure higher quality, we apply a rigorous filtering stage to remove artifacts and semantic mismatches, followed by human selection. Fine-tuning the state-of-the-art ART model on our synthetic PrismLayersPro yields ART+, which outperforms the original ART in 60% of head-to-head user study comparisons and even matches the visual quality of images generated by the FLUX.1-[dev] model. We anticipate that our work will establish a solid dataset foundation for the multi-layer transparent image generation task, enabling research and applications that require precise, editable, and visually compelling layered imagery.

cs.CV↗

arXiv2024

RSC-SNN: Exploring the Trade-off Between Adversarial Robustness and Accuracy in Spiking Neural Networks via Randomized Smoothing Coding

Spiking Neural Networks (SNNs) have received widespread attention due to their unique neuronal dynamics and low-power nature. Previous research empirically shows that SNNs with Poisson coding are more robust than Artificial Neural Networks (ANNs) on small-scale datasets. However, it is still unclear in theory how the adversarial robustness of SNNs is derived, and whether SNNs can still maintain its adversarial robustness advantage on large-scale dataset tasks. This work theoretically demonstrates that SNN's inherent adversarial robustness stems from its Poisson coding. We reveal the conceptual equivalence of Poisson coding and randomized smoothing in defense strategies, and analyze in depth the trade-off between accuracy and adversarial robustness in SNNs via the proposed Randomized Smoothing Coding (RSC) method. Experiments demonstrate that the proposed RSC-SNNs show remarkable adversarial robustness, surpassing ANNs and achieving state-of-the-art robustness results on large-scale dataset ImageNet. Our open-source implementation code is available at this https URL: https://github.com/KemingWu/RSC-SNN.

cs.CV↗

arXiv2024

A Fractal-based Complex Belief Entropy for Uncertainty Measure in Complex Evidence Theory

Complex Evidence Theory (CET), an extension of the traditional D-S evidence theory, has garnered academic interest for its capacity to articulate uncertainty through Complex Basic Belief Assignment (CBBA) and to perform uncertainty reasoning using complex combination rules. Nonetheless, quantifying uncertainty within CET remains a subject of ongoing research. To enhance decision-making, a method for Complex Pignistic Belief Transformation (CPBT) has been introduced, which allocates CBBAs of multi-element focal elements to subsets. CPBT's core lies in the fractal-inspired redistribution of the complex mass function. This paper presents an experimental simulation and analysis of CPBT's generation process along the temporal dimension, rooted in fractal theory. Subsequently, a novel Fractal-Based Complex Belief (FCB) entropy is proposed to gauge the uncertainty of CBBA. The properties of FCB entropy are examined, and its efficacy is demonstrated through various numerical examples and practical application.

cs.IT↗

arXiv2020

Dispersion of deterministic sound wave into stochastic noise by a linear acoustic layer with time-varying and quantized material properties

Wave is crucial to acquiring information from the world and its interaction with matter is determined by the wavelength, or frequency. Search for the ability to shift frequency often points to material nonlinearity, which is significant only when the excitation level is very high. Temporal modulated material is expected to shift sound frequency in a linear manner, but is so far not effectively realized due to inadequate modulation ratio. This study introduces a new class of temporal modulation material with a giant modulation ratio. When the modulation is given in a random time sequence, a monochromatic sound wave is converted to a white noise of a continuous frequency band. The demonstrated device is called a randomized acoustic meta-layer, consisting of a suspended diaphragm shunted by an analog circuit. The circuit alters the acoustic impedance of the layer which operates in two quantized states when the shunt is connected and disconnected by a MOSFET with a pseudo-random time sequence. The device has unprecedented potential applications such as converting annoying tones to white-noise-like hum to improve psychoacoustic quality, allowing encrypted underwater communication, and super-resolution imaging.

physics.app-ph↗