Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion

TL;DR

This paper introduces a method for high-quality scene reconstruction from handheld videos by modeling camera motion effects like blur and rolling shutter, using visual-inertial odometry to improve 3D scene synthesis.

Contribution

It presents a novel differentiable rendering pipeline that accounts for camera motion effects, enabling better scene reconstruction from handheld video data.

Findings

Outperforms existing methods in mitigating motion effects

Effective in both synthetic and real-world scenarios

Enhances 3D scene reconstruction quality

Abstract

High-quality scene reconstruction and novel view synthesis based on Gaussian Splatting (3DGS) typically require steady, high-quality photographs, often impractical to capture with handheld cameras. We present a method that adapts to camera motion and allows high-quality scene reconstruction with handheld video data suffering from motion blur and rolling shutter distortion. Our approach is based on detailed modelling of the physical image formation process and utilizes velocities estimated using visual-inertial odometry (VIO). Camera poses are considered non-static during the exposure time of a single image frame and camera poses are further optimized in the reconstruction process. We formulate a differentiable rendering pipeline that leverages screen space approximation to efficiently incorporate rolling-shutter and motion blur effects into the 3DGS framework. Our results with both synthetic and real data demonstrate superior performance in mitigating camera motion over existing methods, thereby advancing 3DGS in naturalistic settings.