AI RESEARCH
PixVOD: Pixel-Distributed Direct Visual Odometry and Depth Estimation
arXiv CS.CV
•
ArXi:2606.03989v1 Announce Type: new Images composed of 2D pixel arrays are the standard input to computer vision algorithms, yet many underlying computations can be distributed across pixels. Transmitting raw, redundant, and noisy pixel data off the sensor remains inefficient, motivating a shift toward focal-plane sensor-processors that perform a significant part of the computation directly within each pixel. We envision pixels synthesizing higher-level signals locally, reducing downstream load, and providing richer inputs for higher-level vision tasks.