相关论文: Skrr: Skip and Re-use Text Encoder Layers for Memo…

We study on image super-resolution (SR), which aims to recover realistic textures from a low-resolution (LR) image. Recent progress has been made by taking high-resolution images as references (Ref), so that relevant textures can be…

Transformer encoders are widely deployed in large-scale web services for natural language understanding tasks such as text classification, semantic retrieval, and content ranking. However, their high inference latency and memory consumption…

Flow matching and diffusion models have shown impressive results in text-to-image generation, producing photorealistic images through an iterative denoising process. A common strategy to speed up synthesis is to perform early denoising at…

Diffusion models have recently surpassed GANs in image synthesis and editing, offering superior image quality and diversity. However, achieving precise control over attributes in generated images remains a challenge. Concept Sliders…

The rapid advancement of text-to-image (T2I) diffusion models has enabled them to generate unprecedented results from given texts. However, as text inputs become longer, existing encoding methods like CLIP face limitations, and aligning the…

Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend…

Image denoising is a fundamental and challenging task in the field of computer vision. Most supervised denoising methods learn to reconstruct clean images from noisy inputs, which have intrinsic spectral bias and tend to produce…

Image-to-text (I2T) understanding and text-to-image (T2I) generation are two fundamental, important yet traditionally isolated multimodal tasks. Despite their intrinsic connection, existing approaches typically optimize them independently,…

Diffusion-based image super-resolution (SR) methods are mainly limited by the low inference speed due to the requirements of hundreds or even thousands of sampling steps. Existing acceleration sampling techniques inevitably sacrifice…

Recent text-to-image (T2I) diffusion models have achieved remarkable advancement, yet faithfully following complex textual descriptions remains challenging due to insufficient interactions between textual and visual features. Prior…

Spiking neural networks (SNNs) have gained considerable interest due to their energy-efficient characteristics, yet lack of a scalable training algorithm has restricted their applicability in practical machine learning problems. The deep…

The reliability of using fully convolutional networks (FCNs) has been successfully demonstrated by recent studies in many speech applications. One of the most popular variants of these FCNs is the `U-Net', which is an encoder-decoder…

Text-to-Image (T2I) generation methods based on diffusion model have garnered significant attention in the last few years. Although these image synthesis methods produce visually appealing results, they frequently exhibit spelling errors…

As recent advances in large-scale Text-to-Image (T2I) diffusion models have yielded remarkable high-quality image generation, diverse downstream Image-to-Image (I2I) applications have emerged. Despite the impressive results achieved by…

Existing mainstream approaches follow the encoder-decoder paradigm for generating radiology reports. They focus on improving the network structure of encoders and decoders, which leads to two shortcomings: overlooking the modality gap and…

Despite recent advances, single-image super-resolution (SR) remains challenging, especially in real-world scenarios with complex degradations. Diffusion-based SR methods, particularly those built on Stable Diffusion, leverage strong…

Single encoder-decoder methodologies for semantic segmentation are reaching their peak in terms of segmentation quality and efficiency per number of layers. To address these limitations, we propose a new architecture based on a decoder…

With the advent of Generative AI, Single Image Super-Resolution (SISR) quality has seen substantial improvement, as the strong priors learned by Text-2-Image Diffusion (T2IDiff) Foundation Models (FM) can bridge the gap between…

Diffusion models have revolutionized text-to-image (T2I) synthesis, producing high-quality, photorealistic images. However, they still struggle to properly render the spatial relationships described in text prompts. To address the lack of…

Tokenizers are a key component of state-of-the-art generative image models, extracting the most important features from the signal while reducing data dimension and redundancy. Most current tokenizers are based on KL-regularized variational…