Related papers: Bridge-SR: Schr\"odinger Bridge for Efficient SR
Singing voice synthesis (SVS) aims to generate expressive and high-quality vocals from musical scores, requiring precise modeling of pitch, duration, and articulation. While diffusion-based models have achieved remarkable success in image…
Versatile audio super-resolution (SR) aims to predict high-frequency components from low-resolution audio across diverse domains such as speech, music, and sound effects. Existing diffusion-based SR methods often fail to produce…
Schr\"odinger Bridges (SB) have recently gained the attention of the ML community as a promising extension of classic diffusion models which is also interconnected to the Entropic Optimal Transport (EOT). Recent solvers for SB exploit the…
We propose Image-to-Image Schr\"odinger Bridge (I$^2$SB), a new class of conditional diffusion models that directly learn the nonlinear diffusion processes between two given distributions. These diffusion bridges are particularly useful for…
Audio super-resolution is a fundamental task that predicts high-frequency components for low-resolution audio, enhancing audio quality in digital applications. Previous methods have limitations such as the limited scope of audio types…
Multi-modal brain MRI provides essential complementary information for clinical diagnosis. However, acquiring all modalities in practice is often constrained by time and cost. To address this, various methods have been proposed to generate…
Audio-visual speech separation methods aim to integrate different modalities to generate high-quality separated speech, thereby enhancing the performance of downstream tasks such as speech recognition. Most existing state-of-the-art (SOTA)…
Diffusion-based models have demonstrated remarkable effectiveness in image restoration tasks; however, their iterative denoising process, which starts from Gaussian noise, often leads to slow inference speeds. The Image-to-Image…
Reference-based super-resolution (RefSR) has the potential to build bridges across spatial and temporal resolutions of remote sensing images. However, existing RefSR methods are limited by the faithfulness of content reconstruction and the…
This paper aims to conduct a comprehensive theoretical analysis of current diffusion models. We introduce a novel generative learning methodology utilizing the Schr{\"o}dinger bridge diffusion model in latent space as the framework for…
Diffusion-based super-resolution (SR) is a key component in video generation and video restoration, but is slow and expensive, limiting scalability to higher resolutions and longer videos. Our key insight is that many regions in video are…
Self-supervised learning (SSL) has garnered significant attention in speech processing, excelling in linguistic tasks such as speech recognition. However, jointly improving the performance of pre-trained models on various downstream tasks,…
This paper presents an end-to-end high-quality singing voice synthesis (SVS) system that uses bidirectional encoder representation from Transformers (BERT) derived semantic embeddings to improve the expressiveness of the synthesized singing…
Speech enhancement(SE) aims to recover clean speech from noisy recordings. Although generative approaches such as score matching and Schrodinger bridge have shown strong effectiveness, they are often computationally expensive. Flow matching…
Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices. We propose the low-rank transformer (LRT), a memory-efficient and fast neural…
Even without auxiliary images, single hyperspectral image super-resolution (SHSR) methods can be designed to improve the spatial resolution of hyperspectral images. However, failing to explore coherence thoroughly along bands and…
Conventional super-resolution methods suffer from two drawbacks: substantial computational cost in upscaling an entire large image, and the introduction of extraneous or potentially detrimental information for downstream computer vision…
State-of-the-art statistical parametric speech synthesis (SPSS) generally uses a vocoder to represent speech signals and parameterize them into features for subsequent modeling. Magnitude spectrum has been a dominant feature over the years.…
Burst super-resolution (BurstSR) aims at reconstructing a high-resolution (HR) image from a sequence of low-resolution (LR) and noisy images, which is conducive to enhancing the imaging effects of smartphones with limited sensors. The main…
Image inpainting is an important image generation task, which aims to restore corrupted image from partial visible area. Recently, diffusion Schr\"odinger bridge methods effectively tackle this task by modeling the translation between…