Saved in:
Bibliographic Details
Main Authors: Tokumitsu, Junsei, Wada, Yuiga
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.19312
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913910075949056
author Tokumitsu, Junsei
Wada, Yuiga
author_facet Tokumitsu, Junsei
Wada, Yuiga
contents In this work, we address the challenge of affordance detection in 3D point clouds, a task that requires effectively capturing fine-grained alignments between point clouds and text. Existing methods often struggle to model such alignments, resulting in limited performance on standard benchmarks. A key limitation of these approaches is their reliance on simple cosine similarity between point cloud and text embeddings, which lacks the expressiveness needed for fine-grained reasoning. To address this limitation, we propose LM-AD, a novel method for affordance detection in 3D point clouds. Moreover, we introduce the Affordance Query Module (AQM), which efficiently captures fine-grained alignment between point clouds and text by leveraging a pretrained language model. We demonstrated that our method outperformed existing approaches in terms of accuracy and mean Intersection over Union on the 3D AffordanceNet dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2506_19312
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Capturing Fine-Grained Alignments Improves 3D Affordance Detection
Tokumitsu, Junsei
Wada, Yuiga
Computer Vision and Pattern Recognition
Artificial Intelligence
In this work, we address the challenge of affordance detection in 3D point clouds, a task that requires effectively capturing fine-grained alignments between point clouds and text. Existing methods often struggle to model such alignments, resulting in limited performance on standard benchmarks. A key limitation of these approaches is their reliance on simple cosine similarity between point cloud and text embeddings, which lacks the expressiveness needed for fine-grained reasoning. To address this limitation, we propose LM-AD, a novel method for affordance detection in 3D point clouds. Moreover, we introduce the Affordance Query Module (AQM), which efficiently captures fine-grained alignment between point clouds and text by leveraging a pretrained language model. We demonstrated that our method outperformed existing approaches in terms of accuracy and mean Intersection over Union on the 3D AffordanceNet dataset.
title Capturing Fine-Grained Alignments Improves 3D Affordance Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2506.19312