mlsanityData to 14 Oct 2026

ETHEREAL: A 25.6-μs/inf. Low-latency Event-driven Graph-neural-network Processor for High-resolution Vision at the Edge

arXiv 2608.17787 ↗First posted 18 Aug 2026cs.AR cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Dynamic vision sensors (DVS) are enticing candidates to reach the low-latency, sub-ms target of edge-vision applications, as they generate events with a μs-level time resolution. However, using DVS front ends also calls for novel algorithm/hardware back ends capable of efficiently handling streams of sparse spatiotemporal events. While event-driven graph neural networks (EV-GNNs) have emerged as a solution on the algorithmic side that is both accurate and efficient, there is no dedicated hardware to date capable of efficiently supporting their mixed requirements of dense-regular compute operations and sparse-irregular memory accesses. We therefore introduce ETHEREAL, the first EV-GNN processor chip, capable of bridging this gap by means of a neighbor-parallel spline-convolution engine combined with a split-2D/3D memory hierarchy that introduces a novel spatiotemporal event-caching mechanism. Measurement results demonstrate a 25.6μs latency and a 1.6μJ energy per end-to-end event-wise inference on the state-of-the art DAGr-GNN workload and VGA-resolution (640x480 pixels) DSEC dataset.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 33 references that are in the map. First posted on arXiv 18 Aug 2026.

Builds on

21 of 33 references.

References · 21

  1. 2021DSEC: A Stereo Event Camera Dataset for Driving Scenarioscited by 303
  2. 2018HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classificationcited by 218
  3. 2018Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Carscited by 200
  4. 2017SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernelscited by 161
  5. 2022Recurrent Vision Transformers for Object Detection with Event Camerascited by 159
  6. 2022AEGNN: Asynchronous Event-based Graph Neural Networkscited by 118
  7. 2020Event-based Asynchronous Sparse Convolutional Networkscited by 104
  8. 2016A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detectioncited by 83
  9. 2018NVIDIA Tensor Core Programmability, Performance & Precisioncited by 79
  10. 2018Asynchronous Convolutional Networks for Object Detection in Neuromorphic Camerascited by 57
  11. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  12. 2022ReckOn: A 28nm Sub-mm2 Task-Agnostic Spiking Recurrent Neural Network Processor Enabling On-Chip Learning over Second-Long Timescalescited by 35
9 more
  1. 2021CarSNN: An Efficient Spiking Neural Network for Event-Based Autonomous Cars on the Loihi Neuromorphic Research Processorcited by 27
  2. 2024eTraM: Event-based Traffic Monitoring Datasetcited by 24
  3. 2018Towards Low-Latency and Ultra-Reliable Virtual Realitycited by 18
  4. 2024EvGNN: An Event-driven Graph Neural Network Accelerator for Edge Visioncited by 13
  5. 2023To Spike or Not To Spike: A Digital Hardware Perspective on Deep Learning Accelerationcited by 10
  6. 2024Embedded Graph Convolutional Networks for Real-Time Event Data Processing on SoC FPGAscited by 7
  7. 2025A 28nm 0.22μJ/token memory-compute-intensity-aware CNN-Transformer accelerator with hybrid-attention-based layer-fusion and cascaded pruning for semantic-segmentationcited by 3
  8. 2025An Open-Source HW-SW Co-Development Framework Enabling Efficient Multi-Accelerator Systemscited by 2
  9. 2025Croc: An End-to-End Open-Source Extensible RISC-V MCU Platform to Democratize Siliconcited by 1

Built on by

Not cited yet.