VisionGPT-3D: A Generalized Multimodal Agent for Enhanced 3D Vision Understanding

TL;DR

VisionGPT-3D introduces a unified multimodal framework that integrates state-of-the-art vision models to enhance 3D vision understanding from diverse inputs like text and images.

Contribution

It consolidates multiple SOTA vision models into a single framework, automates model selection, and optimizes 3D mesh generation from multimodal data.

Findings

Successfully integrates various vision models for 3D understanding

Automates selection of optimal 3D mesh algorithms

Achieves improved 3D reconstruction accuracy

Abstract

The evolution of text to visual components facilitates people's daily lives, such as generating image, videos from text and identifying the desired elements within the images. Computer vision models involving the multimodal abilities in the previous days are focused on image detection, classification based on well-defined objects. Large language models (LLMs) introduces the transformation from nature language to visual objects, which present the visual layout for text contexts. OpenAI GPT-4 has emerged as the pinnacle in LLMs, while the computer vision (CV) domain boasts a plethora of state-of-the-art (SOTA) models and algorithms to convert 2D images to their 3D representations. However, the mismatching between the algorithms with the problem could lead to undesired results. In response to this challenge, we propose an unified VisionGPT-3D framework to consolidate the state-of-the-art vision models, thereby facilitating the development of vision-oriented AI. VisionGPT-3D provides a versatile multimodal framework building upon the strengths of multimodal foundation models. It seamlessly integrates various SOTA vision models and brings the automation in the selection of SOTA vision models, identifies the suitable 3D mesh creation algorithms corresponding to 2D depth maps analysis, generates optimal results based on diverse multimodal inputs such as text prompts. Keywords: VisionGPT-3D, 3D vision understanding, Multimodal agent