相关论文: Reconstruction-Anchored Diffusion Model for Text-t…

Document reconstruction constitutes a significant facet of document analysis and recognition, a field that has been progressively accruing interest within the scholarly community. A multitude of these researchers employ an array of document…

Regional prompting, or compositional generation, which enables fine-grained spatial control, has gained increasing attention for its practicality in real-world applications. However, previous methods either introduce additional trainable…

Multi-modal image fusion aims to consolidate complementary information from diverse source images into a unified representation. The fused image is expected to preserve fine details and maintain high visual fidelity. While diffusion models…

Dance serves as a powerful medium for expressing human emotions, but the lifelike generation of dance is still a considerable challenge. Recently, diffusion models have showcased remarkable generative abilities across various domains. They…

Cameras capture scene-referred linear raw images, which are processed by onboard image signal processors (ISPs) into display-referred 8-bit sRGB outputs. Although raw data is more faithful for low-level vision tasks, collecting large-scale…

This paper presents a new Text-to-Image generation model, named Distribution Regularization Generative Adversarial Network (DR-GAN), to generate images from text descriptions from improved distribution learning. In DR-GAN, we introduce two…

Aside from offering state-of-the-art performance in medical image generation, denoising diffusion probabilistic models (DPM) can also serve as a representation learner to capture semantic information and potentially be used as an image…

As a class of generative artificial intelligence frameworks inspired by statistical physics, diffusion models have shown extraordinary performance in synthesizing complicated data distributions through a denoising process gradually guided…

Pre-trained diffusion models have enabled significant advancements in All-in-One Restoration (AiOR), offering improved perceptual quality and generalization. However, diffusion-based restoration methods primarily rely on fine-tuning or…

Current large-scale diffusion models represent a giant leap forward in conditional image synthesis, capable of interpreting diverse cues like text, human poses, and edges. However, their reliance on substantial computational resources and…

Text-to-image generation (TTI) refers to the usage of models that could process text input and generate high fidelity images based on text descriptions. Text-to-image generation using neural networks could be traced back to the emergence of…

Bilingual text-to-motion generation, which synthesizes 3D human motions from bilingual text inputs, holds immense potential for cross-linguistic applications in gaming, film, and robotics. However, this task faces critical challenges: the…

The goal of scene text image super-resolution is to reconstruct high-resolution text-line images from unrecognizable low-resolution inputs. The existing methods relying on the optimization of pixel-level loss tend to yield text edges that…

Image restoration aims to enhance low quality images, producing high quality images that exhibit natural visual characteristics and fine semantic attributes. Recently, the diffusion model has emerged as a powerful technique for image…

Diffusion-based super-resolution (SR) models have recently garnered significant attention due to their potent restoration capabilities. But conventional diffusion models perform noise sampling from a single distribution, constraining their…

Denoising diffusion models have shown great promise in human motion synthesis conditioned on natural language descriptions. However, integrating spatial constraints, such as pre-defined motion trajectories and obstacles, remains a challenge…

Diffusion models have become a central paradigm for image and multimodal generation, yet their deployment raises persistent questions about alignment, safety, preference satisfaction, and robustness to misuse. This survey reviews recent…

Although Diffusion Transformer (DiT) has emerged as a predominant architecture for image and video generation, its iterative denoising process results in slow inference, which hinders broader applicability and development. Caching-based…

Speech super-resolution (SR) is the task that restores high-resolution speech from low-resolution input. Existing models employ simulated data and constrained experimental settings, which limit generalization to real-world SR. Predictive…

Real-world datasets collected from sensors or human inputs are prone to noise and errors, posing significant challenges for applying offline reinforcement learning (RL). While existing methods have made progress in addressing corrupted…