Compensating Spatiotemporally Inconsistent Observations for Online Dynamic 3D Gaussian Splatting
This work addresses temporal inconsistency issues in online dynamic scene reconstruction, which is important for applications requiring real-time processing, but it appears incremental as it builds on existing baselines.
The paper tackles the problem of temporal inconsistency artifacts in online dynamic 3D reconstruction from live-streaming video, caused by errors like noise in real-world recordings, and shows that their method significantly enhances both temporal consistency and rendering quality across datasets.
Online reconstruction of dynamic scenes is significant as it enables learning scenes from live-streaming video inputs, while existing offline dynamic reconstruction methods rely on recorded video inputs. However, previous online reconstruction approaches have primarily focused on efficiency and rendering quality, overlooking the temporal consistency of their results, which often contain noticeable artifacts in static regions. This paper identifies that errors such as noise in real-world recordings affect temporal inconsistency in online reconstruction. We propose a method that enhances temporal consistency in online reconstruction from observations with temporal inconsistency which is inevitable in cameras. We show that our method restores the ideal observation by subtracting the learned error. We demonstrate that applying our method to various baselines significantly enhances both temporal consistency and rendering quality across datasets. Code, video results, and checkpoints are available at https://bbangsik13.github.io/OR2.