Search research articles

Related Concept Videos

Light Acquisition

Light Acquisition

In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

High-resolution mapping reveals features of bacterial NAD-capped RNAs and stress-responsive transcription initiation.

Nature communications·2026

Same author

Organ-specific delivery of an mRNA-encoded bispecific T cell engager targeting glypican-3 in hepatocellular carcinoma.

Nature communications·2025

Same author

Single-cell transcriptomics and time-series metabolite profiling reveal the spatiotemporal regulation of flavonoid biosynthesis genes and phytohormone homeostasis by PAP1 in Arabidopsis.

BMC biology·2025

Same author

Construction of PVA/OHA-Gs@PTMC/PHA double-layer nanofiber flexible scaffold with antibacterial function for tension free rectal in-situ reconstruction.

Biomaterials·2025

Same author

Harnessing spatial transcriptomics for advancing plant regeneration research.

Trends in plant science·2024

Same author

Polydopamine functionalized polyurethane shape memory sponge with controllable expansion performance triggered by near-infrared light for incompressible hemorrhage control.

Colloids and surfaces. B, Biointerfaces·2023

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 17, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

SPL-PlaneTR: Lightweight and Generalizable Indoor Plane Segmentation Based on Prompt Learning.

Zhongchen Deng¹, Yuanlong Ge^1,2, Xiatian Qi^1,2

¹School of Computer Science, Hubei University, Wuhan 430062, China.

Sensors (Basel, Switzerland)

|May 14, 2025

Summary

Spatial Prompt Learning PlaneTR (SPL-PlaneTR) enhances single-image plane segmentation by improving line segment utilization and reducing parameters. This novel approach achieves superior performance and zero-shot transfer capabilities in 3D indoor scene understanding.

Keywords:

data augmentation lightweight plane segmentation prompt learning spatial query

More Related Videos

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Published on: April 23, 2020

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: May 17, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Published on: April 23, 2020

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Area of Science:

Computer Vision
Artificial Intelligence
3D Scene Understanding

Background:

Single-image plane segmentation is crucial for 3D indoor scene analysis and reconstruction.
PlaneTR, a transformer-based method, excels in plane instance segmentation but has limitations in utilizing line segment information and parameter efficiency.

Purpose of the Study:

To propose an improved PlaneTR model, Spatial Prompt Learning PlaneTR (SPL-PlaneTR), addressing its limitations.
To enhance the utilization of structural line segment information and reduce model complexity.
To improve the accuracy and generalizability of plane segmentation in diverse indoor environments.

Main Methods:

Replaced PlaneTR's line segment transformer branch with a lightweight line segment prompt module and adapter.
Introduced spatial queries instead of conventional position queries for accurate plane localization.
Developed SPL-PlaneTR, a model balancing complexity and performance for 3D indoor scene segmentation.

Main Results:

SPL-PlaneTR demonstrates superior performance over PlaneTR on ScanNet datasets, even with noise.
Achieved better zero-shot transfer performance on Matterport3D, ICL-NUIM RGB-D, and 2D-3D-S datasets.
The proposed model achieves state-of-the-art results with fewer parameters.

Conclusions:

SPL-PlaneTR effectively leverages line segment information and spatial queries for improved plane segmentation.
The model offers a more efficient and accurate solution for 3D indoor scene understanding.
Publicly available code and model facilitate further research and application.