# CoCam4D enables camera‑only cars to share depth data

> A new Bayesian framework lets autonomous vehicles exchange compact 3D Gaussian representations, cutting depth uncertainty without LiDAR.

Oossa · 2026-10-09 · https://oossa.com/en/cocam4d-enables-camera-only-cars-to-share-depth-data

Researchers led by Soham Pahari introduced CoCam4D, a camera‑only collaborative perception system for autonomous driving. It models geometric uncertainty with 3D Gaussian scene primitives and shares them via C‑V2X using a 35‑byte format called Dynamic Object Primitives. Tests on public datasets show an 11.48% boost over the best recent vision‑only method on OPV2V+ and a 10.62% gain on DAIR‑V2X‑C. The approach works without LiDAR, relying only on shared camera data.

## The facts

- Paper posted on arXiv on 2026-10-09 ("Fri Oct 09 2026")
- Improvement of 11.48% on OPV2V+ and 10.62% on DAIR‑V2X‑C

## Why it matters

It lets fleets of camera‑equipped cars improve perception in blind spots without costly LiDAR hardware.

## Sources & references

1. [CoCam4D: Geometry-Aware Cooperative 4D Perception for Camera-Only Autonomous Driving](https://arxiv.org/abs/2610.11577) – arXiv cs.RO, 2026-10-09

Last updated: 2026-10-09