3D Objectness Estimation via Bottom-up Regret Grouping

TL;DR

This paper introduces a bottom-up 3D objectness estimation method that iteratively groups segments using a learned predictor and a regret mechanism to improve accuracy and robustness in 3D scene understanding.

Contribution

It presents a novel bottom-up approach with a grouping predictor and regret mechanism, reducing errors and outperforming existing methods on challenging datasets.

Findings

Outperforms state-of-the-art methods on GMU-kitchen and CTD datasets.

The regret mechanism effectively reduces incorrect groupings.

The grouping predictor significantly improves proposal quality.

Abstract

3D objectness estimation, namely discovering semantic objects from 3D scene, is a challenging and significant task in 3D understanding. In this paper, we propose a 3D objectness method working in a bottom-up manner. Beginning with over-segmented 3D segments, we iteratively group them into object proposals by learning an ingenious grouping predictor to determine whether two 3D segments can be grouped or not. To enhance robustness, a novel regret mechanism is presented to withdraw incorrect grouping operations. Hence the irreparable consequences brought by mistaken grouping in prior bottom-up works can be greatly reduced. Our experiments show that our method outperforms state-of-the-art 3D objectness methods with a small number of proposals in two difficult datasets, GMU-kitchen and CTD. Further ablation study also demonstrates the effectiveness of our grouping predictor and regret mechanism.