VP-LLM: Text-Driven 3D Volume Completion with Large Language Models through Patchification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Jianmeng, Liu, Yichen, Zhang, Yuyao, Meng, Zeyuan, Tai, Yu-Wing, Tang, Chi-Keung
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909219777675264
author Liu, Jianmeng
Liu, Yichen
Zhang, Yuyao
Meng, Zeyuan
Tai, Yu-Wing
Tang, Chi-Keung
author_facet Liu, Jianmeng
Liu, Yichen
Zhang, Yuyao
Meng, Zeyuan
Tai, Yu-Wing
Tang, Chi-Keung
contents Recent conditional 3D completion works have mainly relied on CLIP or BERT to encode textual information, which cannot support complex instruction. Meanwhile, large language models (LLMs) have shown great potential in multi-modal understanding and generation tasks. Inspired by the recent advancements of LLM, we present Volume Patch LLM (VP-LLM), which leverages LLMs to perform conditional 3D completion in a single-forward pass. To integrate a 3D model into the LLM tokenization configuration, the incomplete 3D object is first divided into small patches that can be encoded independently. These encoded patches are then fed into an LLM along with the text prompt, instructing the LLM to capture the relations between these patches as well as injecting semantic meanings into the 3D object. Our results demonstrate a strong ability of LLMs to interpret complex text instructions and understand 3D objects, surpassing state-of-the-art diffusion-based 3D completion models in generation quality.
format Preprint
id arxiv_https___arxiv_org_abs_2406_05543
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VP-LLM: Text-Driven 3D Volume Completion with Large Language Models through Patchification
Liu, Jianmeng
Liu, Yichen
Zhang, Yuyao
Meng, Zeyuan
Tai, Yu-Wing
Tang, Chi-Keung
Computer Vision and Pattern Recognition
Artificial Intelligence
Recent conditional 3D completion works have mainly relied on CLIP or BERT to encode textual information, which cannot support complex instruction. Meanwhile, large language models (LLMs) have shown great potential in multi-modal understanding and generation tasks. Inspired by the recent advancements of LLM, we present Volume Patch LLM (VP-LLM), which leverages LLMs to perform conditional 3D completion in a single-forward pass. To integrate a 3D model into the LLM tokenization configuration, the incomplete 3D object is first divided into small patches that can be encoded independently. These encoded patches are then fed into an LLM along with the text prompt, instructing the LLM to capture the relations between these patches as well as injecting semantic meanings into the 3D object. Our results demonstrate a strong ability of LLMs to interpret complex text instructions and understand 3D objects, surpassing state-of-the-art diffusion-based 3D completion models in generation quality.
title VP-LLM: Text-Driven 3D Volume Completion with Large Language Models through Patchification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2406.05543