Related papers: LoRaFlow: High-Quality Signal Reconstruction using…
In image restoration, single-step discriminative mappings often lack fine details via expectation learning, whereas generative paradigms suffer from inefficient multi-step sampling and noise-residual coupling. To address this dilemma, we…
Channel estimation is a fundamental challenge in massive multiple-input multiple-output systems, where estimation accuracy governs the spectral efficiency and link reliability. In this work, we introduce Recursive Flow (RC-Flow), a novel…
We propose ReinFlow, a simple yet effective online reinforcement learning (RL) framework that fine-tunes a family of flow matching policies for continuous robotic control. Derived from rigorous RL theory, ReinFlow injects learnable noise…
Image restoration aims to recover high-quality (HQ) images from degraded low-quality (LQ) ones by reversing the effects of degradation. Existing generative models for image restoration, including diffusion and score-based models, often…
The Reflow operation aims to straighten the inference trajectories of the rectified flow during training by constructing deterministic couplings between noises and images, thereby improving the quality of generated images in single-step or…
Although diffusion models in text-to-speech have become a popular choice due to their strong generative ability, the intrinsic complexity of sampling from diffusion models harms their efficiency. Alternatively, we propose VoiceFlow, an…
The difficulty of obtaining paired data remains a major bottleneck for learning image restoration and enhancement models for real-world applications. Current strategies aim to synthesize realistic training data by modeling noise and…
Recent advancements in generative modeling have significantly enhanced the reconstruction of audio waveforms from various representations. While diffusion models are adept at this task, they are hindered by latency issues due to their…
LoRa wireless networks are considered as a key enabling technology for next generation internet of things (IoT) systems. New IoT deployments (e.g., smart city scenarios) can have thousands of devices per square kilometer leading to huge…
We present IllumFlow, a novel framework that synergizes conditional Rectified Flow (CRF) with Retinex theory for low-light image enhancement (LLIE). Our model addresses low-light enhancement through separate optimization of illumination and…
Low-resolution image representation is a special form of sparse representation that retains only low-frequency information while discarding high-frequency components. This property reduces storage and transmission costs and benefits various…
Low-Power Wide-Area Networks (LPWANs) are an emerging Internet-of-Things (IoT) paradigm marked by low-power and long-distance communication. Among them, LoRa is widely deployed for its unique characteristics and open-source technology. By…
LoRaWAN is nowadays one of the most popular protocols for low-power Internet-of-Things communications. Although its physical layer, namely LoRa, has been thoroughly studied in the literature, aspects related to the synchronization of LoRa…
RGB-to-RAW reconstruction, or the reverse modeling of a camera Image Signal Processing (ISP) pipeline, aims to recover high-fidelity RAW data from RGB images. Despite notable progress, existing learning-based methods typically treat this…
The Deep Prior framework has emerged as a powerful generative tool which can be used for reconstructing sound fields in an environment from few sparse pressure measurements. It employs a neural network that is trained solely on a limited…
Diffusion models (DMs) have demonstrated remarkable success in real-world image super-resolution (SR), yet their reliance on time-consuming multi-step sampling largely hinders their practical applications. While recent efforts have…
Long-range low-power wireless communications, such as LoRa, are used in many IoT and environmental monitoring applications. They typically increase the communication range to several kilometers, at the cost of reducing the bitrate to a few…
Diffusion models create data from noise by inverting the forward paths of data towards noise and have emerged as a powerful generative modeling technique for high-dimensional, perceptual data such as images and videos. Rectified flow is a…
Generative flow models offer powerful priors learned from large-scale natural images, but directly adapting them to restoration tasks such as motion deblurring causes severe fidelity degradation, as their training objective is inherently…
Flow matching has emerged as a promising generative approach that addresses the lengthy sampling times associated with state-of-the-art diffusion models and enables a more flexible trajectory design, while maintaining high-quality image…