Autoregressive High-Order Finite Difference Modulo Imaging: High-Dynamic Range for Computer Vision Applications

2025-04-05

AI Summary

Conventional imaging systems suffer from limited dynamic range, hindering their applicability to high-dynamic-range (HDR) vision tasks such as autonomous driving. To address this without hardware modification, this paper proposes a modulo-based HDR imaging framework grounded in infinite sampling theory. We formulate the underlying problem as an autoregressive ℓ₂-phase deconvolution task and design a two-dimensional phase unwrapping algorithm that jointly regularizes higher-order spatial finite differences and discrete cosine transform (DCT) domain sparsity. A step-elimination mechanism is further introduced to enhance robustness against noise and quantization errors. Our method reconstructs high-fidelity HDR images directly from low-bit modulo measurements. Evaluated on autonomous driving benchmarks, it significantly improves object detection accuracy—without altering pre-trained detection models—while maintaining computational efficiency and full hardware compatibility.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

High dynamic range (HDR) imaging is vital for capturing the full range of light tones in scenes, essential for computer vision tasks such as autonomous driving. Standard commercial imaging systems face limitations in capacity for well depth, and quantization precision, hindering their HDR capabilities. Modulo imaging, based on unlimited sampling (US) theory, addresses these limitations by using a modulo analog-to-digital approach that resets signals upon saturation, enabling estimation of pixel resets through neighboring pixel intensities. Despite the effectiveness of (US) algorithms in one-dimensional signals, their optimization problem for two-dimensional signals remains unclear. This work formulates the US framework as an autoregressive $ell_2$ phase unwrapping problem, providing computationally efficient solutions in the discrete cosine domain jointly with a stride removal algorithm also based on spatial differences. By leveraging higher-order finite differences for two-dimensional images, our approach enhances HDR image reconstruction from modulo images, demonstrating its efficacy in improving object detection in autonomous driving scenes without retraining.

Problem

• Enhancing HDR imaging for computer vision tasks
• Overcoming limitations in commercial imaging systems
• Optimizing 2D signal processing for modulo imaging

Innovation

• Modulo imaging with analog-to-digital reset
• Autoregressive phase unwrapping in cosine domain
• Higher-order finite differences for HDR