Neural Network Generalization: The impact of camera parameters
원문 초록
We quantify the generalization of a convolutional neural network (CNN) trained to identify cars. First, we perform a series of experiments to train the network using one image dataset - either synthetic or from a camera - and then test on a different image dataset. We show that generalization between images obtained with different cameras is roughly the same as generalization between images from a camera and ray-traced multispectral synthetic images. Second, we use ISETAuto, a soft prototyping tool that creates ray-traced multispectral simulations of camera images, to simulate sensor images with a range of pixel sizes, color filters, acquisition and post-acquisition processing. These experiments reveal how variations in specific camera parameters and image processing operations impact CNN generalization. We find that (a) pixel size impacts generalization, (b) demosaicking substantially impacts performance and generalization for shallow (8-bit) bit-depths but not deeper ones (10-bit), and (c) the network performs well using raw (not demosaicked) sensor data for 10-bit pixels.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
PIDSR: Complementary Polarized Image Demosaicing and Super-Resolution
Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS Demosaicing
Learning Joint Denoising, Demosaicing, and Compression from the Raw Natural Image Noise Dataset
Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image Enhancement
Efficient Polarization Demosaicking via Low-cost Edge-aware and Inter-channel Correlation
Learning deep illumination-robust features from multispectral filter array images
토론
이 논문과 연결된 포럼 글이 아직 없습니다.