DiET-GS: Diffusion Prior and Event Stream-Assisted Motion Deblurring 3D Gaussian Splatting
This work addresses motion deblurring for 3D reconstruction in computer vision, offering incremental improvements by combining event streams and diffusion priors to enhance visual quality.
The paper tackles the problem of reconstructing sharp 3D representations from blurry multi-view images by proposing DiET-GS, a method that uses diffusion prior and event streams to enhance motion deblurring in 3D Gaussian Splatting, resulting in significantly better quality novel views compared to existing baselines.
Reconstructing sharp 3D representations from blurry multi-view images are long-standing problem in computer vision. Recent works attempt to enhance high-quality novel view synthesis from the motion blur by leveraging event-based cameras, benefiting from high dynamic range and microsecond temporal resolution. However, they often reach sub-optimal visual quality in either restoring inaccurate color or losing fine-grained details. In this paper, we present DiET-GS, a diffusion prior and event stream-assisted motion deblurring 3DGS. Our framework effectively leverages both blur-free event streams and diffusion prior in a two-stage training strategy. Specifically, we introduce the novel framework to constraint 3DGS with event double integral, achieving both accurate color and well-defined details. Additionally, we propose a simple technique to leverage diffusion prior to further enhance the edge details. Qualitative and quantitative results on both synthetic and real-world data demonstrate that our DiET-GS is capable of producing significantly better quality of novel views compared to the existing baselines. Our project page is https://diet-gs.github.io