AsyncEvGS reconstructs high-fidelity 3D scenes from motion-blurred images by first deblurring via event data then using VGGT-based pose estimation and structure-driven losses inside Gaussian Splatting.
Comogaussian: Continuous motion-aware gaussian splatting from motion-blurred images
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
EvFlow-GS jointly optimizes a learnable event double integral, poses, and 3DGS using optical flow and event-based losses to reduce residual artifacts in motion deblurring.
citing papers explorer
-
AsyncEvGS: Asynchronous Event-Assisted Gaussian Splatting for Handheld Motion-Blurred Scenes
AsyncEvGS reconstructs high-fidelity 3D scenes from motion-blurred images by first deblurring via event data then using VGGT-based pose estimation and structure-driven losses inside Gaussian Splatting.
-
EvFlow-GS: Event Enhanced Motion Deblurring with Optical Flow for 3D Gaussian Splatting
EvFlow-GS jointly optimizes a learnable event double integral, poses, and 3DGS using optical flow and event-based losses to reduce residual artifacts in motion deblurring.