Related Experiment Video
Updated: May 24, 2025
07:12
Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
Published on: April 11, 2025
263
Progressive Knowledge Transfer Network Based on Human Visual Perception Mechanism for No-Reference Point Cloud
IEEE Transactions on Visualization and Computer Graphics
|March 3, 2025
Summary
We developed PKT-PCQA, a novel deep learning network for assessing point cloud quality without reference data. This method accurately predicts perceptual quality, outperforming existing techniques.
Area of Science:
- Computer Vision
- Machine Learning
- Signal Processing
Background:
- Point cloud perceptual quality assessment is vital for applications like compression and communication.
- Existing methods often require reference data or lack accuracy in predicting human perception.
Purpose of the Study:
- To propose PKT-PCQA, a no-reference deep learning network for accurate point cloud quality assessment.
- To emulate the human visual system for enhanced quality prediction.
Main Methods:
- Developed a point-based, no-reference deep learning network (PKT-PCQA).
- Employed progressive knowledge transfer for coarse-to-fine quality prediction.
- Utilized local and global feature extraction with spatial and channel attention mechanisms.
Main Results:
- PKT-PCQA demonstrated superior performance over existing no-reference and reduced-reference methods.
- Achieved performance comparable to state-of-the-art full-reference methods on independent datasets.
- Validated effectiveness across three large-scale point cloud quality assessment datasets.
Conclusions:
- PKT-PCQA offers a robust and accurate solution for no-reference point cloud quality assessment.
- The proposed network effectively models human visual perception for quality prediction.
- This work advances the field of point cloud quality assessment for various applications.
Related Concept Videos
01:15Depth Perception and Spatial Vision
508
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
508
01:12Perceptual Constancy
317
Perceptual constancy is the ability to recognize that objects remain consistent and unchanged even when their appearance varies due to changes in sensory input. There are four main types of perceptual constancy: size constancy, shape constancy, color constancy, and brightness constancy.
Size constancy is the recognition that an object remains the same size, even when its image on the retina changes. For instance, a bus is perceived to be large enough to carry people, even if it looks tiny from...
Size constancy is the recognition that an object remains the same size, even when its image on the retina changes. For instance, a bus is perceived to be large enough to carry people, even if it looks tiny from...
317
01:24Vision
52.9K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
52.9K