Vision without Images: End-to-End Computer Vision from Single Compressive Measurements

TL;DR

This paper introduces a novel SCI-based vision framework using small binary masks and a specialized autoencoder to perform tasks directly from raw measurements, excelling in low-light conditions with low complexity.

Contribution

It presents a new end-to-end vision approach from compressive measurements using small masks and a multi-task autoencoder, enabling direct task inference without image reconstruction.

Findings

Achieves state-of-the-art performance in low-light conditions.

Uses small 8x8 masks suitable for hardware implementation.

Demonstrates lower complexity and high accuracy across tasks.

Abstract

Snapshot Compressed Imaging (SCI) offers high-speed, low-bandwidth, and energy-efficient image acquisition, but remains challenged by low-light and low signal-to-noise ratio (SNR) conditions. Moreover, practical hardware constraints in high-resolution sensors limit the use of large frame-sized masks, necessitating smaller, hardware-friendly designs. In this work, we present a novel SCI-based computer vision framework using pseudo-random binary masks of only 8$\times$8 in size for physically feasible implementations. At its core is CompDAE, a Compressive Denoising Autoencoder built on the STFormer architecture, designed to perform downstream tasks--such as edge detection and depth estimation--directly from noisy compressive raw pixel measurements without image reconstruction. CompDAE incorporates a rate-constrained training strategy inspired by BackSlash to promote compact, compressible models. A shared encoder paired with lightweight task-specific decoders enables a unified multi-task platform. Extensive experiments across multiple datasets demonstrate that CompDAE achieves state-of-the-art performance with significantly lower complexity, especially under ultra-low-light conditions where traditional CMOS and SCI pipelines fail.