Related papers: NoiseCLR: A Contrastive Learning Approach for Unsu…

Diffusion-based methods represented as stochastic differential equations on a continuous-time domain have recently proven successful as a non-adversarial generative model. Training such models relies on denoising score matching, which can…

Text-guided image editing has recently experienced rapid development. However, simultaneously performing multiple editing actions on a single image, such as background replacement and specific subject attribute changes, while maintaining…

Generative adversarial networks (GANs) have proven to be surprisingly efficient for image editing by inverting and manipulating the latent code corresponding to an input real image. This editing property emerges from the disentangled nature…

Diffusion-based image translation guided by semantic texts or a single target image has enabled flexible style transfer which is not limited to the specific domains. Unfortunately, due to the stochastic nature of diffusion models, it is…

Disentangled generative models map a latent code vector to a target space, while enforcing that a subset of the learned latent codes are interpretable and associated with distinct properties of the target distribution. Recent advances have…

Learning from a large corpus of data, pre-trained models have achieved impressive progress nowadays. As popular generative pre-training, diffusion models capture both low-level visual knowledge and high-level semantic relations. In this…

Evaluating diffusion-based image-editing models is a crucial task in the field of Generative AI. Specifically, it is imperative to assess their capacity to execute diverse editing tasks while preserving the image content and realism. While…

Although diffusion models have achieved remarkable success in the field of image generation, their latent space remains under-explored. Current methods for identifying semantics within latent space often rely on external supervision, such…

Recently, diffusion models have emerged as a powerful class of generative models. Despite their success, there is still limited understanding of their semantic spaces. This makes it challenging to achieve precise and disentangled image…

Deep generative models have emerged as promising tools for detecting arbitrary anomalies in data, dispensing with the necessity for manual labelling. Recently, autoregressive transformers have achieved state-of-the-art performance for…

Large-scale text-to-image generative models have been a ground-breaking development in generative AI, with diffusion models showing their astounding ability to synthesize convincing images following an input text prompt. The goal of image…

Editing real facial images is a crucial task in computer vision with significant demand in various real-world applications. While GAN-based methods have showed potential in manipulating images especially when combined with CLIP, these…

In the Text-to-speech(TTS) task, the latent diffusion model has excellent fidelity and generalization, but its expensive resource consumption and slow inference speed have always been a challenging. This paper proposes Discrete Diffusion…

Text-to-Image synthesis is the task of generating an image according to a specific text description. Generative Adversarial Networks have been considered the standard method for image synthesis virtually since their introduction. Denoising…

Unsupervised Contrastive learning has gained prominence in fields such as vision, and biology, leveraging predefined positive/negative samples for representation learning. Data augmentation, categorized into hand-designed and model-based…

Conditional diffusion models rely on language-to-image alignment methods to steer the generation towards semantically accurate outputs. Despite the success of this architecture, misalignment and hallucinations remain common issues and…

Fashionable image generation aims to synthesize images of diverse fashion prevalent around the globe, helping fashion designers in real-time visualization by giving them a basic customized structure of how a specific design preference would…

We propose the first unsupervised and learning-based method to identify interpretable directions in h-space of pre-trained diffusion models. Our method is derived from an existing technique that operates on the GAN latent space.…

Research in vision-language models has seen rapid developments off-late, enabling natural language-based interfaces for image generation and manipulation. Many existing text guided manipulation techniques are restricted to specific classes…

Despite the rapid advancement of unsupervised learning in visual representation, it requires training on large-scale datasets that demand costly data collection, and pose additional challenges due to concerns regarding data privacy.…