# TinyTracker: Ultra-Fast and Ultra-Low-Power Edge Vision In-Sensor for Gaze Estimation

arXiv: https://arxiv.org/abs/2307.07813 · HTML: https://mlsanity.com/paper/2307.07813/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 46 references that are in the map.
- First posted on arXiv 15 Jul 2023.

## Builds on (most cited first, 17 of 17)

- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Eye Tracking for Everyone](https://mlsanity.com/paper/1606.05814/) (2016)
- [Appearance-Based Gaze Estimation in the Wild](https://mlsanity.com/paper/1504.02863/) (2015)
- [ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation](https://mlsanity.com/paper/2007.15837/) (2020)
- [Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression](https://mlsanity.com/paper/2003.08935/) (2020)
- [Gaze Estimation using Transformer](https://mlsanity.com/paper/2105.14424/) (2021)
- [Event Based, Near Eye Gaze Tracking Beyond 10,000Hz](https://mlsanity.com/paper/2004.03577/) (2020)
- [Rendering of Eyes for Eye-Shape Registration and Gaze Estimation](https://mlsanity.com/paper/1505.05916/) (2015)
- [TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers](https://mlsanity.com/paper/2306.00001/) (2023)
- [TinyRadarNN: Combining Spatial and Temporal Convolutional Neural Networks for Embedded Gesture Recognition with Short Range Radars](https://mlsanity.com/paper/2006.16281/) (2020)
- [A Generalized and Robust Method Towards Practical Gaze Estimation on Smart Phone](https://mlsanity.com/paper/1910.07331/) (2019)
- [An Open Source and Open Hardware Deep Learning-powered Visual Navigation Engine for Autonomous Nano-UAVs](https://mlsanity.com/paper/1905.04166/) (2019)
- [Sound Event Detection with Binary Neural Networks on Tightly Power-Constrained IoT Devices](https://mlsanity.com/paper/2101.04446/) (2021)
- [ColibriUAV: An Ultra-Fast, Energy-Efficient Neuromorphic Edge Processing UAV-Platform with Event-Based and Frame-Based Cameras](https://mlsanity.com/paper/2305.18371/) (2023)
- [Exploring Automatic Gym Workouts Recognition Locally On Wearable Resource-Constrained Devices](https://mlsanity.com/paper/2301.05748/) (2023)

## Built on by (most cited first, 16 of 16)

- [Retina : Low-Power Eye Tracking with Event Camera and Spiking Hardware](https://mlsanity.com/paper/2312.00425/) (2023)
- [Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO](https://mlsanity.com/paper/2311.01057/) (2023)
- [EvGNN: An Event-driven Graph Neural Network Accelerator for Edge Vision](https://mlsanity.com/paper/2404.19489/) (2024)
- [ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Data](https://mlsanity.com/paper/2402.01393/) (2024)
- [MambaPupil: Bidirectional Selective Recurrent model for Event-based Eye tracking](https://mlsanity.com/paper/2404.12083/) (2024)
- [PicoSAM2: Low-Latency Segmentation In-Sensor for Edge Vision Applications](https://mlsanity.com/paper/2506.18807/) (2025)
- [Performance Analysis of Edge and In-Sensor AI Processors: A Comparative Review](https://mlsanity.com/paper/2603.08725/) (2026)
- [On-device Learning of EEGNet-based Network For Wearable Motor Imagery Brain-Computer Interface](https://mlsanity.com/paper/2409.00083/) (2024)
- [TinyGLASS: Real-Time Self-Supervised In-Sensor Anomaly Detection](https://mlsanity.com/paper/2603.16451/) (2026)
- [Gaze Estimation on Spresense](https://mlsanity.com/paper/2308.12313/) (2023)
- [Q-Segment: Segmenting Images In-Sensor for Vessel-Based Medical Diagnosis](https://mlsanity.com/paper/2312.09854/) (2023)
- [Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions](https://mlsanity.com/paper/2508.08352/) (2025)
- [PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation](https://mlsanity.com/paper/2603.11917/) (2026)
- [Low Latency Gaze Tracking via Latent Optical Sensing](https://mlsanity.com/paper/2605.17990/) (2026)
- [FTerViT: Fully Ternary Vision Transformer](https://mlsanity.com/paper/2605.21171/) (2026)
- [Exploiting In-Sensor Computing for Energy-Efficient Earth Observation](https://mlsanity.com/paper/2606.01271/) (2026)

## Abstract (arXiv)

Intelligent edge vision tasks encounter the critical challenge of ensuring power and latency efficiency due to the typically heavy computational load they impose on edge platforms.This work leverages one of the first "AI in sensor" vision platforms, IMX500 by Sony, to achieve ultra-fast and ultra-low-power end-to-end edge vision applications. We evaluate the IMX500 and compare it to other edge platforms, such as the Google Coral Dev Micro and Sony Spresense, by exploring gaze estimation as a case study. We propose TinyTracker, a highly efficient, fully quantized model for 2D gaze estimation designed to maximize the performance of the edge vision systems considered in this study. TinyTracker achieves a 41x size reduction (600Kb) compared to iTracker [1] without significant loss in gaze estimation accuracy (maximum of 0.16 cm when fully quantized). TinyTracker's deployment on the Sony IMX500 vision sensor results in end-to-end latency of around 19ms. The camera takes around 17.9ms to read, process and transmit the pixels to the accelerator. The inference time of the network is 0.86ms with an additional 0.24 ms for retrieving the results from the sensor. The overall energy consumption of the end-to-end system is 4.9 mJ, including 0.06 mJ for inference. The end-to-end study shows that IMX500 is 1.7x faster than CoralMicro (19ms vs 34.4ms) and 7x more power efficient (4.9mJ VS 34.2mJ)