EgoCOL: Egocentric Camera pose estimation for Open-world 3D object Localization @Ego4D challenge 2023
This work addresses camera pose estimation for 3D object localization in egocentric videos, which is incremental as it builds on existing benchmarks and methods.
The paper tackles the problem of egocentric camera pose estimation for open-world 3D object localization, achieving 62% and 59% more camera poses than the baseline on the Ego4D benchmark.
We present EgoCOL, an egocentric camera pose estimation method for open-world 3D object localization. Our method leverages sparse camera pose reconstructions in a two-fold manner, video and scan independently, to estimate the camera pose of egocentric frames in 3D renders with high recall and precision. We extensively evaluate our method on the Visual Query (VQ) 3D object localization Ego4D benchmark. EgoCOL can estimate 62% and 59% more camera poses than the Ego4D baseline in the Ego4D Visual Queries 3D Localization challenge at CVPR 2023 in the val and test sets, respectively. Our code is publicly available at https://github.com/BCV-Uniandes/EgoCOL