3D Objectness Estimation via Bottom-up Regret Grouping

12/05/2019
by   Zelin Ye, et al.
0

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.

READ FULL TEXT

page 1

page 6

page 8

research
03/29/2020

Grouping headlines

In this work we deal with the problem of grouping in headlines of the ne...
research
08/07/2018

Universal Perceptual Grouping

In this work we aim to develop a universal sketch grouper. That is, a gr...
research
03/03/2015

Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation

We propose a unified approach for bottom-up hierarchical image segmentat...
research
05/26/2020

ALBA : Reinforcement Learning for Video Object Segmentation

We consider the challenging problem of zero-shot video object segmentati...
research
08/19/2023

Scene-Aware Feature Matching

Current feature matching methods focus on point-level matching, pursuing...
research
09/18/2023

EGFE: End-to-end Grouping of Fragmented Elements in UI Designs with Multimodal Learning

When translating UI design prototypes to code in industry, automatically...
research
08/20/2020

An Examination of Grouping and Spatial Organization Tasks for High-Dimensional Data Exploration

How do analysts think about grouping and spatial operations? This overar...

Please sign up or login with your details

Forgot password? Click here to reset