VFM-VLM: Vision Foundation Model and Vision Language Model based Visual Comparison for 3D Pose Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sarowar, Md Selim, Kim, Sungho
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908699071610880
author Sarowar, Md Selim
Kim, Sungho
author_facet Sarowar, Md Selim
Kim, Sungho
contents Vision Foundation Models (VFMs) and Vision Language Models (VLMs) have revolutionized computer vision by providing rich semantic and geometric representations. This paper presents a comprehensive visual comparison between CLIP based and DINOv2 based approaches for 3D pose estimation in hand object grasping scenarios. We evaluate both models on the task of 6D object pose estimation and demonstrate their complementary strengths: CLIP excels in semantic understanding through language grounding, while DINOv2 provides superior dense geometric features. Through extensive experiments on benchmark datasets, we show that CLIP based methods achieve better semantic consistency, while DINOv2 based approaches demonstrate competitive performance with enhanced geometric precision. Our analysis provides insights for selecting appropriate vision models for robotic manipulation and grasping, picking applications.
format Preprint
id arxiv_https___arxiv_org_abs_2512_07215
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VFM-VLM: Vision Foundation Model and Vision Language Model based Visual Comparison for 3D Pose Estimation
Sarowar, Md Selim
Kim, Sungho
Computer Vision and Pattern Recognition
Artificial Intelligence
Vision Foundation Models (VFMs) and Vision Language Models (VLMs) have revolutionized computer vision by providing rich semantic and geometric representations. This paper presents a comprehensive visual comparison between CLIP based and DINOv2 based approaches for 3D pose estimation in hand object grasping scenarios. We evaluate both models on the task of 6D object pose estimation and demonstrate their complementary strengths: CLIP excels in semantic understanding through language grounding, while DINOv2 provides superior dense geometric features. Through extensive experiments on benchmark datasets, we show that CLIP based methods achieve better semantic consistency, while DINOv2 based approaches demonstrate competitive performance with enhanced geometric precision. Our analysis provides insights for selecting appropriate vision models for robotic manipulation and grasping, picking applications.
title VFM-VLM: Vision Foundation Model and Vision Language Model based Visual Comparison for 3D Pose Estimation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2512.07215