MSc Thesis Presentation - Wei Zhi Tang

Name: Wei Zhi Tang

Date: August 27, Tuesday

Time: 2pm - 3:30pm

Location: ICCS 202

Supervisor: Kwang Moo Yi

Title: Deblur NeRF by Modeling Camera Imperfection and Using RGB-Event Stereo

Abstract:

We present a method for reconstructing a clear Neural Radiance Field (NeRF) even with fast camera motions. To address blur artifacts, we leverage both (blurry) RGB images and event camera data captured in a binocular configuration. Importantly, when reconstructing our clear NeRF, we consider the camera modeling imperfections that arise from the simple pinhole camera model as learned embeddings for each camera measurement, and further learn a mapper that connects event camera measurements with RGB data. As no previous dataset exists for our binocular setting, we introduce an event camera dataset with captures from a 3D-printed stereo configuration between RGB and event cameras. Empirically, we evaluate on our introduced dataset and EVIMOv2 and show that our method leads to improved reconstructions.