.png){kind=icon}
.png){kind=icon}
Return
EventTracer: Fast Path Tracing-Based Event Stream Rendering
.png){kind=icon}
PRE
AI
DOI：10.1109/tvcg.2026.3701141.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Simulating event streams from 3D scenes has become a common practice in event-based vision research, as it meets the demand for large-scale, high temporal frequency data without setting up expensive hardware devices or undertaking extensive data collections. Yet existing methods in this direction typically work with noiseless RGB frames that are costly to render, and therefore their simulations are often unrealistically low in temporal resolution. In this work, we propose <i>EventTracer</i>, a path tracing-based rendering pipeline that simulates high-fidelity event sequences from complex 3D scenes in an efficient and physics-aware manner. Specifically, we speed up the rendering process via low sample-per-pixel (SPP) path tracing, and train a lightweight event spiking network to denoise the resulting RGB videos into realistic event sequences. Our EventTracerpipeline runs at a speed of <inline-formula><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula>1 minutes per second of 360p video, and it inherits the merit of accurate spatiotemporal modeling from its path tracing backbone. We show through the <i>Real2Sim</i> and <i>Sim2Real</i> tests that EventTracercaptures higher-fidelity scene details and demonstrates a greater similarity to real-world event data than alternative event simulators, which establishes it as a potential tool for creating large-scale event-RGB datasets, narrowing the sim-to-real gap in event-based vision, and boosting various downstream applications.
Keywords:
Event camera
event simulation
path tracing
spiking neural network
Journal
IF:
6.5
Papers:
294
Citations:
2.2W