Related papers: Text-to-image synthesis method evaluation based on…

Achieving fairness in text-to-image generation demands mitigating social biases without compromising visual fidelity, a challenge critical to responsible AI. Current fairness evaluation procedures for text-to-image models rely on…

Language models are increasingly being incorporated as components in larger AI systems for various purposes, from prompt optimization to automatic evaluation. In this work, we analyze the construct validity of four recent, commonly used…

The field of text-conditioned image generation has made unparalleled progress with the recent advent of latent diffusion models. While remarkable, as the complexity of given text input increases, the state-of-the-art diffusion models may…

A non-parametric interpretable texture synthesis method, called the NITES method, is proposed in this work. Although automatic synthesis of visually pleasant texture can be achieved by deep neural networks nowadays, the associated…

Current methods for single-image depth estimation use training datasets with real image-depth pairs or stereo pairs, which are not easy to acquire. We propose a framework, trained on synthetic image-depth pairs and unpaired real images,…

This letter presents an incremental text-to-speech (TTS) method that performs synthesis in small linguistic units while maintaining the naturalness of output speech. Incremental TTS is generally subject to a trade-off between latency and…

The inherent ambiguity in defining visual concepts poses significant challenges for modern generative models, such as the diffusion-based Text-to-Image (T2I) models, in accurately learning concepts from a single image. Existing methods lack…

Synthesizing a realistic image from textual description is a major challenge in computer vision. Current text to image synthesis approaches falls short of producing a highresolution image that represent a text descriptor. Most existing…

Evaluating the quality of videos generated from text-to-video (T2V) models is important if they are to produce plausible outputs that convince a viewer of their authenticity. We examine some of the metrics used in this area and highlight…

Pre-trained large text-to-image models synthesize impressive images with an appropriate use of text prompts. However, ambiguities inherent in natural language and out-of-distribution effects make it hard to synthesize image styles, that…

This paper analyzes the impact of causal manner in the text encoder of text-to-image (T2I) diffusion models, which can lead to information bias and loss. Previous works have focused on addressing the issues through the denoising process.…

Diffusion models have revitalized the image generation domain, playing crucial roles in both academic research and artistic expression. With the emergence of new diffusion models, assessing the performance of text-to-image models has become…

Face sketch synthesis has wide applications ranging from digital entertainments to law enforcements. Objective image quality assessment scores and face recognition accuracy are two mainly used tools to evaluate the synthesis performance. In…

Recent text-to-image generation methods provide a simple yet exciting conversion capability between text and image domains. While these methods have incrementally improved the generated image fidelity and text relevancy, several pivotal…

We observe that the mapping between an image's representation in one model to its representation in another can be learned surprisingly well with just a linear layer, even across diverse models. Building on this observation, we propose…

Despite significant progress in generative AI, comprehensive evaluation remains challenging because of the lack of effective metrics and standardized benchmarks. For instance, the widely-used CLIPScore measures the alignment between a…

Recent strides in Text-to-3D techniques have been propelled by distilling knowledge from powerful large text-to-image diffusion models (LDMs). Nonetheless, existing Text-to-3D approaches often grapple with challenges such as…

Generating desired images conditioned on given text descriptions has received lots of attention. Recently, diffusion models and autoregressive models have demonstrated their outstanding expressivity and gradually replaced GAN as the favored…

Automatic evaluation for open-ended natural language generation tasks remains a challenge. Existing metrics such as BLEU show a low correlation with human judgment. We propose a novel and powerful learning-based evaluation metric:…

Recent significant advances in text-to-image models unlock the possibility of training vision systems using synthetic images, potentially overcoming the difficulty of collecting curated data at scale. It is unclear, however, how these…