arXiv Computer Vision By Md Rahatul Islam Udoy, Sumeet Kumar Gupta, Deep Jariwala, Ahmedullah Aziz

STEMPix: A Phase-Transition-Material-Based Pixel Sensor for Resolving Edge-Movement Direction

Read the original on arXiv Computer Vision →

The paper introduces STEMPix, a phase‑transition‑material‑based pixel that generates a 3‑bit local edge direction code (LEDC) by combining temporal change and spatial edge information within a CMOS‑compatible image sensor array. The design separates the photodiode and computation layers to maintain light‑collection efficiency while adding in‑array processing circuitry, achieving a 1.73 µm horizontal pitch, 2.36 µm vertical pitch, and 95.47% fill factor with an average switching energy of 0.465 fJ per LEDC operation. STEMPix supports global‑shutter capture and dynamic thresholding, offering a compact, scalable front‑end for edge‑movement‑aware sensing systems.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Machine Learning
Jun 26

FracEvent: Event-Camera Simulation via Fractional-Relaxation Pixel Dynamics

arXiv:2606. 26636v1 Announce Type: cross Abstract: Event cameras asynchronously report brightness changes with microsecond-level temporal resolution, but real event data remain difficult to collect at scale because specialized sensors, careful synchronization, and task-specific annotations are required.

By Langyi Chen, Chuanzhi Xu, Haoxian Zhou, Pengfei Ye, Ziyu Luo, Haodong Chen, Qiang Qu, Xiaoming Chen, Weidong Cai
arXiv Computer Vision
Sep 2

Hybrid Event Frame Sensors: Modeling, Calibration, and Simulation

Hybrid event-frame sensors combine an Event Vision Sensor (EVS) and an Active Pixel Sensor (APS) on a single chip, offering high dynamic range, low latency, and rich spatial intensity data. The paper introduces a unified statistics-based noise model that captures photon shot noise, dark current noise, fixed-pattern noise, and quantization noise for both APS and EVS pixels, and links EVS noise to illumination and dark current. It also presents a calibration pipeline to estimate these noise parameters from real data and proposes H-ESIM, a simulator that generates realistic RAW frames and events, validated on two hybrid sensors for tasks such as video frame interpolation and deblurring.

By Yunfan Lu, Nico Messikommer, Xiaogang Xu, Liming Chen, Yuhan Chen, Nikola Zubic, Davide Scaramuzza, Hui Xiong
arXiv AI
Jul 14

Edge Physical AI Deployment of Vision Transformers on Heterogeneous Edge GPU Targeting Autonomous Vehicles

arXiv:2607. 10942v1 Announce Type: cross Abstract: Physical AI systems, such as autonomous vehicles and intelligent machines, require transformer-based perception models that satisfy stringent edge latency and energy constraints.

By Ashiyana Abdul Majeed, Mahmoud Meribout, Neethu Joseph, Abel Kidane Haile, Mohammad Abdullah Al Faruque
arXiv Computer Vision
Sep 7

E-RGB-D: Real-Time Event-Based Perception with Structured Light

The paper introduces E‑RGB‑D, a real‑time event‑based perception system that combines a Digital Light Processing projector with a monochrome event camera to produce RGB‑D data. By projecting structured light and capturing asynchronous brightness changes, the system can detect color and depth for each pixel, achieving a color detection speed of 1400 fps and a depth detection rate of 4 kHz. The approach enables frameless RGB‑D sensing and delivers colorful point clouds without compromising spatial resolution.

By Seyed Ehsan Marjani Bajestani, Giovanni Beltrame