Related Experiment Videos
Lightweight Low-Light Enhancement Network with Multi-Bio-Inspired Visual Mechanisms.
Yafeng Zhao1, Xiang Li1, Shuaipeng Hao1
1College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China.
Biomimetics (Basel, Switzerland)
|June 25, 2026
Summary
This study introduces a bio-inspired model for low-light image enhancement, balancing complexity and quality for edge devices. It achieves superior perceptual quality with minimal parameters, outperforming existing lightweight methods.
Area of Science:
- Computer Vision
- Bio-inspired Computing
- Image Processing
Background:
- Edge deployment scenarios necessitate lightweight models for low-light image enhancement.
- Existing lightweight models often struggle with a trade-off between model complexity and perceptual quality.
- Resource constraints in edge devices limit the application of complex image enhancement algorithms.
Purpose of the Study:
- To propose a novel perceptual quality optimization model for low-light image enhancement inspired by biological visual mechanisms.
- To address the limitations of existing lightweight models in resource-constrained edge environments.
- To improve both objective metrics (PSNR, SSIM) and subjective visual quality (LPIPS).
Main Methods:
- Introduced a GT-Mean loss to simulate mammalian retinal luminance adaptation, mitigating exposure inconsistency.
- Incorporated LPIPS loss to align with human visual system (HVS) preferences for enhanced subjective quality.
- Integrated biologically inspired modules: texture-aware attention, multi-scale feature fusion, and chrominance denoising.
Main Results:
- The proposed model achieves state-of-the-art performance on the LOL dataset series.
- Maintained an extremely low parameter count (0.52 M), demonstrating high efficiency.
- Outperformed existing lightweight methods in PSNR, SSIM, and LPIPS metrics.
Conclusions:
- The bio-inspired model offers an efficient solution for perceptual quality optimization in low-light image enhancement.
- The model is suitable for resource-constrained edge deployment scenarios.
- This work advances bio-inspired visual sensing with practical applications in edge computing.
Related Concept Videos
02:16Light 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.
01:22Photoreceptors and Visual Pathways
At the molecular level, visual signals trigger transformations in photopigment molecules, resulting in changes in the photoreceptor cell's membrane potential. The photon's energy level is denoted by its wavelength, with each specific wavelength of visible light associated with a distinct color. The spectral range of visible light, classified as electromagnetic radiation, spans from 380 to 720 nm. Electromagnetic radiation wavelengths exceeding 720 nm fall under the infrared category, whereas...
01:26Visual System
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
Once through the pupil, the light passes through the lens, a...
02:00Photoreceptors and Plant Responses to Light
Light plays a significant role in regulating the growth and development of plants. In addition to providing energy for photosynthesis, light provides other important cues to regulate a range of developmental and physiological responses in plants.
01:24Vision
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.