Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yang, Dejie, Xu, Zhu, Mo, Wentao, Chen, Qingchao, Huang, Siyuan, Liu, Yang
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2407.06084
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913421289586688
author Yang, Dejie
Xu, Zhu
Mo, Wentao
Chen, Qingchao
Huang, Siyuan
Liu, Yang
author_facet Yang, Dejie
Xu, Zhu
Mo, Wentao
Chen, Qingchao
Huang, Siyuan
Liu, Yang
contents 3D Vision-Language Pre-training (3D-VLP) aims to provide a pre-train model which can bridge 3D scenes with natural language, which is an important technique for embodied intelligence. However, current 3D-VLP datasets are hindered by limited scene-level diversity and insufficient fine-grained annotations (only 1.2K scenes and 280K textual annotations in ScanScribe), primarily due to the labor-intensive of collecting and annotating 3D scenes. To overcome these obstacles, we construct SynVL3D, a comprehensive synthetic scene-text corpus with 10K indoor scenes and 1M descriptions at object, view, and room levels, which has the advantages of diverse scene data, rich textual descriptions, multi-grained 3D-text associations, and low collection cost. Utilizing the rich annotations in SynVL3D, we pre-train a simple and unified Transformer for aligning 3D and language with multi-grained pretraining tasks. Moreover, we propose a synthetic-to-real domain adaptation in downstream task fine-tuning process to address the domain shift. Through extensive experiments, we verify the effectiveness of our model design by achieving state-of-the-art performance on downstream tasks including visual grounding, dense captioning, and question answering.
format Preprint
id arxiv_https___arxiv_org_abs_2407_06084
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle 3D Vision and Language Pretraining with Large-Scale Synthetic Data
Yang, Dejie
Xu, Zhu
Mo, Wentao
Chen, Qingchao
Huang, Siyuan
Liu, Yang
Computer Vision and Pattern Recognition
3D Vision-Language Pre-training (3D-VLP) aims to provide a pre-train model which can bridge 3D scenes with natural language, which is an important technique for embodied intelligence. However, current 3D-VLP datasets are hindered by limited scene-level diversity and insufficient fine-grained annotations (only 1.2K scenes and 280K textual annotations in ScanScribe), primarily due to the labor-intensive of collecting and annotating 3D scenes. To overcome these obstacles, we construct SynVL3D, a comprehensive synthetic scene-text corpus with 10K indoor scenes and 1M descriptions at object, view, and room levels, which has the advantages of diverse scene data, rich textual descriptions, multi-grained 3D-text associations, and low collection cost. Utilizing the rich annotations in SynVL3D, we pre-train a simple and unified Transformer for aligning 3D and language with multi-grained pretraining tasks. Moreover, we propose a synthetic-to-real domain adaptation in downstream task fine-tuning process to address the domain shift. Through extensive experiments, we verify the effectiveness of our model design by achieving state-of-the-art performance on downstream tasks including visual grounding, dense captioning, and question answering.
title 3D Vision and Language Pretraining with Large-Scale Synthetic Data
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.06084