Event-driven Robust Fitting on Neuromorphic Hardware

2025-08-12

AI Summary

To address the high energy consumption of geometric model robust fitting in computer vision, this paper proposes the first neuromorphic, event-driven solution. Methodologically, we pioneer the mapping of robust fitting algorithms onto spiking neural networks (SNNs), implement event-driven model estimation on Intel Loihi 2, and introduce hardware-aware optimizations—including low-precision stochastic sampling and quantization-aware training. Our contributions are: (1) a cross-modal mapping framework bridging SNNs and geometric fitting theory; and (2) an energy-efficiency breakthrough achieving accuracy comparable to CPU-based implementations while consuming only 15% of the CPU’s energy. Experiments demonstrate superior accuracy–efficiency trade-offs for RANSAC-like tasks, validating the viability of our approach for resource-constrained edge vision systems. This work establishes a practical neuromorphic paradigm for real-time geometric reasoning.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Robust fitting of geometric models is a fundamental task in many computer vision pipelines. Numerous innovations have been produced on the topic, from improving the efficiency and accuracy of random sampling heuristics to generating novel theoretical insights that underpin new approaches with mathematical guarantees. However, one aspect of robust fitting that has received little attention is energy efficiency. This performance metric has become critical as high energy consumption is a growing concern for AI adoption. In this paper, we explore energy-efficient robust fitting via the neuromorphic computing paradigm. Specifically, we designed a novel spiking neural network for robust fitting on real neuromorphic hardware, the Intel Loihi 2. Enabling this are novel event-driven formulations of model estimation that allow robust fitting to be implemented in the unique architecture of Loihi 2, and algorithmic strategies to alleviate the current limited precision and instruction set of the hardware. Results show that our neuromorphic robust fitting consumes only a fraction (15%) of the energy required to run the established robust fitting algorithm on a standard CPU to equivalent accuracy.

Problem

• Energy-efficient robust fitting for computer vision
• Neuromorphic hardware implementation for low energy consumption
• Event-driven model estimation on Intel Loihi 2

Innovation

• Event-driven model estimation on neuromorphic hardware
• Spiking neural network for energy-efficient robust fitting
• Algorithmic strategies for limited hardware precision