Learning Visual Prior via Generative Pre-Training
Various stuff and things in visual data possess specific traits, which can be learned by deep neural networks and are implicitly represented as the visual prior, e.g., object location and shape, in the model. Such prior potentially impacts many vision tasks. For example, in conditional image synthesis, spatial conditions failing to adhere to the prior can result in visually inaccurate synthetic results. This work aims to explicitly learn the visual prior and enable the customization of sampling. Inspired by advances in language modeling, we propose to learn Visual prior via Generative Pre-Training, dubbed VisorGPT. By discretizing visual locations, e.g., bounding boxes, human pose, and instance masks, into sequences, VisorGPT can model visual prior through likelihood maximization. Besides, prompt engineering is investigated to unify various visual locations and enable customized sampling of sequential outputs from the learned prior. Experimental results demonstrate the effectiveness of VisorGPT in modeling visual prior and extrapolating to novel scenes, potentially motivating that discrete visual locations can be integrated into the learning paradigm of current language models to further perceive visual world. Code is available at https://sierkinhane.github.io/visor-gpt.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Learning Visual Generative Priors without Text
Although text-to-image (T2I) models have recently thrived as visual generative priors, their reliance on high-quality text-image pairs makes scaling up expensive. We argue that grasping the cross-modality alignment is no…
Image to 3DPhilosophyVisorGPT: Learning Visual Prior via Generative Pre-Training
Various stuff and things in visual data possess specific traits, which can be learned by deep neural networks and are implicitly represented as the visual prior, e.g., object location and shape, in the model. Such prior …
Image GenerationLanguage ModelingLanguage ModellingPrompt EngineeringV-Bridge: Bridging Video Generative Priors to Versatile Few-shot Image Restoration
Large-scale video generative models are trained on vast and diverse visual data, enabling them to internalize rich structural, semantic, and dynamic priors of the visual world. While these models have demonstrated impres…
Image RestorationLearning Long-form Video Prior via Generative Pre-Training
Concepts involved in long-form videos such as people, objects, and their interactions, can be viewed as following an implicit prior. They are notably complex and continue to pose challenges to be comprehensively learned.…
FormELITE: Efficient Gaussian Head Avatar from a Monocular Video via Learned Initialization and TEst-time Generative Adaptation
We introduce ELITE, an Efficient Gaussian head avatar synthesis from a monocular video via Learned Initialization and TEst-time generative adaptation. Prior works rely either on a 3D data prior or a 2D generative prior t…