Research Analyzer
← Back ICRA 2026

Efficient Plane Segmentation in Depth Image Based on Adaptive Patch-Wise Region Growing

Lantao Zhang, Haochen Niu, Peilin Liu, Fei Wen, RENDONG YING

PDF

AI summary

Key figure (auto-extracted from paper)
APRG achieves over 600 FPS on a mid-range CPU while outperforming state-of-the-art methods in both speed and segmentation accuracy.
Plane segmentation Depth images Adaptive patching Region growing Real-time robotics Edge computing

Problem

Existing plane segmentation methods struggle with computational redundancy on varying planar region sizes or require excessive resources, making real-time deployment on resource-limited edge devices challenging.

Approach

APRG constructs a data pyramid from depth images to adaptively extract variable-sized planar patches in a top-down manner, then merges them using a specialized patch-wise region growing algorithm for efficient boundary refinement.

Key results

  • Achieves over 600 FPS at 640x480 resolution on a mid-range CPU
  • Outperforms state-of-the-art methods by a factor of 1.46 in speed
  • Significantly improves segmentation accuracy on noisy real-world depth data
  • Introduces a novel adaptive-patch representation that eliminates redundant plane fitting

Why it matters

Enables real-time, high-precision 3D scene understanding for resource-constrained robotic systems and edge devices.

Abstract

Plane segmentation algorithms are widely used in robotics, serving key roles in scenarios such as indoor local- ization, scene understanding, and robotic manipulation. These applications typically require real-time, precise, and robust plane segmentation processing, which presents a significant challenge. Existing methods based on pixel-wise or fix-sized patch-wise operation are redundant, as planar regions in real-world scenes are of diverse sizes. In this paper, we introduce a highly efficient method for plane segmentation, namely Adaptive Patch-wise Region Growing (APRG). APRG begins with data sampling to construct a data pyramid. To avoid redundant planer fitting in large planar regions, we introduce an adaptive patch-wise plane fitting algorithm with the pyramid accessed in a top-down manner. The largest possible planar patches are obtained in this process. Subsequently we introduce a region growing algorithm specially designed for our patch representation. Overall, APRG achieves more than 600 FPS at a 640x480 resolution on a mid-range CPU without using parallel acceleration techniques, which outperforms the state-of-the-art method by a factor of 1.46. Besides, in addition to its speedup in run-time, APRG significantly improves the segmentation quality, especially on real-world data. Code is available at ZhangLanTao/APRG.

Index terms

RGB-D Perception Object Detection Segmentation and Categorization

Related papers