TIDES: Time-Derivative Event Simulation via Deformable Reconstruction
2026-06-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionRobotics
AI summaryⓘ
The authors developed TIDES, a new way to simulate data from event cameras, which detect changes in a scene asynchronously rather than capturing full images. Unlike older simulators that rely on frame sequences and cause many events to share the same timestamp, TIDES uses a continuous 3D scene model to predict exact event timings more accurately, even during fast motion and occlusion. It focuses computing power where objects block each other to better track brightness changes and models sensor limitations realistically. Their results show that TIDES creates more accurate simulated events that work better for real-world applications compared to previous methods.
event cameraevent simulationtimestamp batchingGaussian splatting3D scene representationocclusionbrightness dynamicsadaptive time steppingsensor bandwidthevent-stream fidelity
Authors
Christopher Thirgood, Dipon Kumar Ghosh, Simon Hadfield
Abstract
Event cameras emit asynchronous events in response to environmental appearance changes. The scarcity of real-world event datasets makes simulation essential. However, most simulators infer event timestamps from frame sequences, forcing many threshold crossings to share a small set of discrete times; a failure mode we term timestamp batching that worsens under fast motion and occlusion. We present TIDES, a continuous-time event simulator built on dynamic Gaussian splatting. Because TIDES operates on an explicit 3D scene representation with learnt geometry and motion, it can derive per-pixel intensity dynamics directly from the scene, rather than by differencing rendered frames. This enables accurate threshold-crossing prediction, including multiple crossings per rendering step, without temporal upsampling or frame interpolation. The same 3D scene model reveals where objects partially occlude one another; TIDES uses this to guide adaptive time stepping, concentrating computation only in regions where occlusion dynamics make simple models of brightness change unreliable. Finally, we model finite sensor bandwidth using a tile-level arbiter whose throughput, jitter, and event drops reproduce realistic sensor artifacts. Across paired RGB-event benchmarks, TIDES attains state-of-the-art event-stream fidelity. We also show that events simulated by TIDES transfer more effectively to real downstream tasks than competitors'.