Granular3D: Delving into multi-granularity 3D scene graph prediction

This paper addresses the significant challenges in 3D Semantic Scene Graph (3DSSG) prediction, essential for understanding complex 3D environments. Traditional approaches, primarily using PointNet and Graph Convolutional Networks, struggle with effectively extracting multi-grained features from intr...

Full description

Saved in:
Bibliographic Details
Main Authors: HUANG, Kaixiang, YANG, Jingru, WANG, Jin, HE, Shengfeng, WANG, Zhan, HE, Haiyan, ZHANG, Qifeng, LU, Guodong
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2024
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8811
https://ink.library.smu.edu.sg/context/sis_research/article/9814/viewcontent/Granular3D_av.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
Description
Summary:This paper addresses the significant challenges in 3D Semantic Scene Graph (3DSSG) prediction, essential for understanding complex 3D environments. Traditional approaches, primarily using PointNet and Graph Convolutional Networks, struggle with effectively extracting multi-grained features from intricate 3D scenes, largely due to a focus on global scene processing and single-scale feature extraction. To overcome these limitations, we introduce Granular3D, a novel approach that shifts the focus towards multi-granularity analysis by predicting relation triplets from specific sub-scenes. One key is the Adaptive Instance Enveloping Method (AIEM), which establishes an approximate envelope structure around irregular instances, providing shape-adaptive local point cloud sampling, thereby comprehensively covering the contextual environments of instances. Moreover, Granular3D incorporates a Hierarchical Dual-Stage Network (HDSN), which differentiates and processes features of instances and their pairs at varying scales, leading to a targeted prediction of instance categories and their relationships. To advance the perception of sub-scene in HDSN, we design a Gather Point Transformer structure (GaPT) that enables the combinatorial interaction of local information from multiple point cloud sets, achieving a more comprehensive local contextual feature extraction. Extensive evaluations on the challenging 3DSSG benchmark demonstrate that our methods provide substantial improvements, establishing a new state-of-the-art in 3DSSG prediction, boosting the top-50 triplet accuracy by +2.8%.