Hyper-V2X: Hypernetworks for Estimating Epistemic and Aleatoric Uncertainty in Cooperative Bird's-Eye-View Semantic Segmentation

TL;DR

Hyper-V2X introduces a hypernetwork-based method for estimating both epistemic and aleatoric uncertainties in cooperative V2X perception, enhancing autonomous driving safety with efficient uncertainty quantification.

Contribution

It proposes a novel hypernetwork framework with partial weight generation and context embedding for uncertainty estimation in V2X perception, compatible with existing architectures.

Findings

Hyper-V2X provides accurate uncertainty estimates in BEV segmentation.

The approach improves perception reliability on the OPV2V benchmark.

It achieves this with minimal additional computational overhead.

Abstract

Cooperative perception enabled by Vehicle-to-Everything (V2X) communication enhances autonomous driving safety by creating a unified environmental representation through shared sensory data. While recent works have advanced multi-agent fusion for improved perception, uncertainty quantification in such cooperative frameworks remains largely unexplored. This paper introduces Hyper-V2X, a hypernetwork-based framework for estimating both epistemic and aleatoric uncertainties in V2X-based perception. Specifically, we propose a partial weight generation scheme and V2X context embedding module that conditions a Bayesian hypernetwork on fused multi-agent features to generate weight distributions for stochastic Bird's-Eye-View (BEV) segmentation. Unlike existing deterministic BEV models, Hyper-V2X enables efficient uncertainty estimation with little computation overhead. Our approach is architecture-agnostic, and can be seamlessly integrating with modern cooperative backbones such as CoBEVT. Experiments on the OPV2V benchmark demonstrate that Hyper-V2X provides accurate, well-calibrated uncertainty estimates and improves overall perception reliability. Our code and benchmark are publicly available under an open-source license: https://github.com/abhishekjagtap1/Hyper-V2X