VisorGPT: Learning Visual Prior via Generative Pre-Training

TL;DR

VisorGPT introduces a method to explicitly learn and model visual priors using generative pre-training, enabling improved and customizable visual data synthesis by discretizing visual features into sequences.

Contribution

The paper presents a novel approach to explicitly learn visual priors through sequence modeling inspired by language models, allowing for customizable sampling in vision tasks.

Findings

Effectively models visual prior for various vision tasks

Enables customizable sampling of visual features

Improves conditional image synthesis accuracy

Abstract

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 of objects, 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 that VisorGPT can effectively model the visual prior, which can be employed for many vision tasks, such as customizing accurate human pose for conditional image synthesis models like ControlNet. Code will be released at https://github.com/Sierkinhane/VisorGPT.