MVLLaVA: An Intelligent Agent for Unified and Flexible Novel View Synthesis

Hanyu Jiang, Jian Xue, Xing Lan, Guohong Hu, Ke Lu,
University of Chinese Academy of Sciences
Paper Code (Coming soon)

Abstract

This paper introduces MVLLaVA, an intelligent agent designed for novel view synthesis tasks. MVLLaVA integrates multiple multi-view diffusion models with a large multimodal model, LLaVA, enabling it to handle a wide range of tasks efficiently. MVLLaVA represents a versatile and unified platform that adapts to diverse input types, including a single image, a descriptive caption, or a specific change in viewing azimuth, guided by language instructions for viewpoint generation. We carefully craft task-specific instruction templates, which are subsequently used to fine-tune LLaVA. As a result, MVLLaVA acquires the capability to generate novel view images based on user instructions, demonstrating its flexibility across diverse tasks. Experiments are conducted to validate the effectiveness of MVLLaVA, demonstrating its robust performance and versatility in tackling diverse novel view synthesis challenges.

MY ALT TEXT

MVLLaVA unifies multi-view generation capabilities to synthesize novel views, with user-friendly and intuitive instructions. It consists of three main components: a large multimodal model LLaVA, a post-processing module, and multi-view diffusion models.

BibTeX

@misc{jiang2024mvllavaintelligentagentunified,
        title={MVLLaVA: An Intelligent Agent for Unified and Flexible Novel View Synthesis}, 
        author={Hanyu Jiang and Jian Xue and Xing Lan and Guohong Hu and Ke Lu},
        year={2024},
        eprint={2409.07129},
        archivePrefix={arXiv},
        primaryClass={cs.CV},
        url={https://arxiv.org/abs/2409.07129}, 
  }