相关论文: Human Preference Score: Better Aligning Text-to-Im…

Large-scale text-to-image foundation models have achieved remarkable visual realism, yet generating human images with correct anatomical structures remains challenging. Existing approaches enforce anatomical constraints through…

Several studies have raised awareness about social biases in image generative models, demonstrating their predisposition towards stereotypes and imbalances. This paper contributes to this growing body of research by introducing an…

The ability to estimate the perceptual error between images is an important problem in computer vision with many applications. Although it has been studied extensively, however, no method currently exists that can robustly predict visual…

Recent studies have demonstrated the effectiveness of directly aligning diffusion models with human preferences using differentiable reward. However, they exhibit two primary challenges: (1) they rely on multistep denoising with gradient…

Current subject-driven image generation methods encounter significant challenges in person-centric image generation. The reason is that they learn the semantic scene and person generation by fine-tuning a common pre-trained diffusion, which…

Previous probabilistic models for 3D Human Pose Estimation (3DHPE) aimed to enhance pose accuracy by generating multiple hypotheses. However, most of the hypotheses generated deviate substantially from the true pose. Compared to…

With the incredibly growing amount of multimedia data shared on the social media platforms, recommender systems have become an important necessity to ease users' burden on the information overload. In such a scenario, extensive amount of…

Beyond scaling base models with more data or parameters, fine-tuned adapters provide an alternative way to generate high fidelity, custom images at reduced costs. As such, adapters have been widely adopted by open-source communities,…

Creative story illustration requires a consistent interplay of multiple characters or objects. However, conventional text-to-image models face significant challenges while producing images featuring multiple personalized subjects. For…

Controllable human image generation (HIG) has numerous real-life applications. State-of-the-art solutions, such as ControlNet and T2I-Adapter, introduce an additional learnable branch on top of the frozen pre-trained stable diffusion (SD)…

Debiased recommender models have recently attracted increasing attention from the academic and industry communities. Existing models are mostly based on the technique of inverse propensity score (IPS). However, in the recommendation domain,…

We present HuGDiffusion, a generalizable 3D Gaussian splatting (3DGS) learning pipeline to achieve novel view synthesis (NVS) of human characters from single-view input images. Existing approaches typically require monocular videos or…

In this paper, we propose a novel diffusion-based approach to generate stereo images given a text prompt. Since stereo image datasets with large baselines are scarce, training a diffusion model from scratch is not feasible. Therefore, we…

Despite their impressive performance on computer vision benchmarks, Deep Neural Networks (DNNs) still fall short of adequately modeling human visual behavior, as measured by error consistency and shape bias. Recent work hypothesized that…

3D content creation from text prompts has shown remarkable success recently. However, current text-to-3D methods often generate 3D results that do not align well with human preferences. In this paper, we present a comprehensive framework,…

Developing reliable and generalizable deep learning systems for medical imaging faces significant obstacles due to spurious correlations, data imbalances, and limited text annotations in datasets. Addressing these challenges requires…

Personalized text-to-image diffusion models have grown popular for their ability to efficiently acquire a new concept from user-defined text descriptions and a few images. However, in the real world, a user may wish to personalize a model…

Human image animation aims to generate a human motion video from the inputs of a reference human image and a target motion video. Current diffusion-based image animation systems exhibit high precision in transferring human identity into…

Acquiring high-quality data for training discriminative models is a crucial yet challenging aspect of building effective predictive systems. In this paper, we present Diffusion Inversion, a simple yet effective method that leverages the…

Emotional text-to-speech seeks to convey affect while preserving intelligibility and prosody, yet existing methods rely on coarse labels or proxy classifiers and receive only utterance-level feedback. We introduce Emotion-Aware Stepwise…