High-Resolution Novel View Synthesis from Low-Resolution Event Streams

Abstract

Event cameras offer microsecond-level temporal resolution and high dynamic range, but their spatial resolution remains much lower than that of modern RGB cameras. This paper studies high-resolution novel-view synthesis from low-resolution (i.e., low-spatial-resolution) event streams alone. Given multi-view low-resolution events of a static scene, without RGB images or any high-resolution signal, our goal is to reconstruct a 3D Gaussian radiance field that can be rendered beyond the native event-sensor resolution. To this end, we propose an event-only framework that integrates event super-resolution into event-driven 3D Gaussian optimization. The framework exploits two types of cues. Temporal cues convert the high temporal resolution of event streams into dense local multi-view constraints by constructing event observations between nearby viewpoints. Spatial cues provide target-resolution event priors by lifting low-resolution event increments with a 2D event super-resolution module. To make these priors compatible with the physical measurements, we apply pool correction so that each high-resolution prior reproduces the original low-resolution event increment after downsampling. The corrected high-resolution priors and the native low-resolution measurements are jointly used to optimize a shared 3D Gaussian radiance field, enforcing multi-view consistency during reconstruction. Experiments on synthetic multi-view scenes with paired low- and high-resolution event ground truth show that our method outperforms Pre-SR and Post-SR baselines in both quantitative metrics and visual quality, demonstrating the effectiveness of reconstructing high-resolution radiance fields from low-resolution events alone.