YCB-Ev SD: Synthetic event-vision dataset for 6DoF object pose estimation
This provides a foundational resource for researchers in event-based vision, addressing a gap in synthetic data for benchmarking and development, though it is incremental as it builds on existing methodologies like BOP and PBR.
The authors tackled the lack of comprehensive synthetic datasets for event-camera data in 6DoF object pose estimation by introducing YCB-Ev SD, a synthetic dataset with 50,000 event sequences, and found that time-surfaces with linear decay and dual-channel polarity encoding outperformed other representations by significant margins.
We introduce YCB-Ev SD, a synthetic dataset of event-camera data at standard definition (SD) resolution for 6DoF object pose estimation. While synthetic data has become fundamental in frame-based computer vision, event-based vision lacks comparable comprehensive resources. Addressing this gap, we present 50,000 event sequences of 34 ms duration each, synthesized from Physically Based Rendering (PBR) scenes of YCB-Video objects following the Benchmark for 6D Object Pose (BOP) methodology. Our generation framework employs simulated linear camera motion to ensure complete scene coverage, including background activity. Through systematic evaluation of event representations for CNN-based inference, we demonstrate that time-surfaces with linear decay and dual-channel polarity encoding achieve superior pose estimation performance, outperforming exponential decay and single-channel alternatives by significant margins. Our analysis reveals that polarity information contributes most substantially to performance gains, while linear temporal encoding preserves critical motion information more effectively than exponential decay. The dataset is provided in a structured format with both raw event streams and precomputed optimal representations to facilitate immediate research use and reproducible benchmarking. The dataset is publicly available at https://huggingface.co/datasets/paroj/ycbev_sd.