Xing Liu

Jinbo Wu, Xiaobo Gao, Xing Liu et al.

In this paper, we study Text-to-3D content generation leveraging 2D diffusion priors to enhance the quality and detail of the generated 3D models. Recent progress (Magic3D) in text-to-3D has shown that employing high-resolution (e.g., 512 x 512) renderings can lead to the production of high-quality 3D models using latent diffusion priors. To enable rendering at even higher resolutions, which has the potential to further augment the quality and detail of the models, we propose a novel approach that combines multiple noise estimation processes with a pretrained 2D diffusion prior. Distinct from the Bar-Tal et al.s' study which binds multiple denoised results to generate images from texts, our approach integrates the computation of scoring distillation losses such as SDS loss and VSD loss which are essential techniques for the 3D content generation with 2D diffusion priors. We experimentally evaluated the proposed approach. The results show that the proposed approach can generate high-quality details compared to the baselines.

Di Jin, Xing Liu, Yu Liu et al.

The rapid development of large language models (LLMs) and large vision models (LVMs) have propelled the evolution of multi-modal AI systems, which have demonstrated the remarkable potential for industrial applications by emulating human-like cognition. However, they also pose significant ethical challenges, including amplifying harmful content and reinforcing societal biases. For instance, biases in some industrial image generation models highlighted the urgent need for robust fairness assessments. Most existing evaluation frameworks focus on the comprehensiveness of various aspects of the models, but they exhibit critical limitations, including insufficient attention to content generation alignment and social bias-sensitive domains. More importantly, their reliance on pixel-detection techniques is prone to inaccuracies. To address these issues, this paper presents INFELM, an in-depth fairness evaluation on widely-used text-to-image models. Our key contributions are: (1) an advanced skintone classifier incorporating facial topology and refined skin pixel representation to enhance classification precision by at least 16.04%, (2) a bias-sensitive content alignment measurement for understanding societal impacts, (3) a generalizable representation bias evaluation for diverse demographic groups, and (4) extensive experiments analyzing large-scale text-to-image model outputs across six social-bias-sensitive domains. We find that existing models in the study generally do not meet the empirical fairness criteria, and representation bias is generally more pronounced than alignment errors. INFELM establishes a robust benchmark for fairness assessment, supporting the development of multi-modal AI systems that align with ethical and human-centric principles.

Yan Zhang, Mete Ozay, Xing Liu et al.

We propose a method for integration of features extracted using deep representations of Convolutional Neural Networks (CNNs) each of which is learned using a different image dataset of objects and materials for material recognition. Given a set of representations of multiple pre-trained CNNs, we first compute activations of features using the representations on the images to select a set of samples which are best represented by the features. Then, we measure the uncertainty of the features by computing the entropy of class distributions for each sample set. Finally, we compute the contribution of each feature to representation of classes for feature selection and integration. We examine the proposed method on three benchmark datasets for material recognition. Experimental results show that the proposed method achieves state-of-the-art performance by integrating deep features. Additionally, we introduce a new material dataset called EFMD by extending Flickr Material Database (FMD). By the employment of the EFMD with transfer learning for updating the learned CNN models, we achieve 84.0%+/-1.8% accuracy on the FMD dataset which is close to human performance that is 84.9%.