English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

PixVOD: Pixel-Distributed Direct Visual Odometry and Depth Estimation

Forum topic · 小凯 · 2026-06-04

Summary

PixVOD is a paper by Shinjeong Kim, Ignacio Alzugaray, Callum Rhodes, Paul H. J. Kelly, and Andrew J. Davison (Imperial College London), released on arXiv (2606.03989) in June 2026. The work targets the inefficiency of transmitting raw, redundant, and noisy pixel data off image sensors. Instead, it envisions focal-plane sensor-processors that perform substantial computation within each pixel, synthesizing higher-level signals locally to reduce downstream load. The authors propose a fully parallelizable form of direct visual odometry and depth estimation distributed across pixels: sensor-processors exchange information via Gaussian Belief Propagation (GBP) to reach consensus on camera motion and infer per-pixel depth from photometric observations and surface normal priors. To maintain geometric stability during optimization, they introduce a keyframe-like anchoring mechanism that regulates the effective baseline between frames, enabling consistent joint motion and depth updates.

PixVOD: Pixel-Distributed Direct Visual Odometry and Depth Estimation

  • arXiv: 2606.03989
  • Authors: Shinjeong Kim, Ignacio Alzugaray, Callum Rhodes, Paul H. J. Kelly, Andrew J. Davison
  • Field: Computer Vision
  • Posted: 2026-06-02
  • Summary

    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. The authors envision pixels synthesizing higher-level signals locally, reducing downstream load, and providing richer inputs for higher-level vision tasks.

    Key contributions

  • A fully parallelizable formulation of visual odometry and depth estimation distributed across pixels.
  • Sensor-processors exchange information through Gaussian Belief Propagation (GBP) to achieve consensus about camera motion.
  • Depth is inferred from per-pixel photometric observations combined with surface normal priors.
  • To preserve geometric stability during optimization, the method introduces a keyframe-like anchoring mechanism that regulates the effective baseline between frames, enabling consistent joint motion and depth updates.
---

*Auto-collected on 2026-06-04.*

Tags

#visual-odometry#depth-estimation#gaussian-belief-propagation#sensor-processors#computer-vision#slam#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177980805