ChronoFuseGS improves 3D scene models over time with detailed change views
ChronoFuseGS: Multi-Temporal Gaussian Fusion with Per-Splat Persistence and Change Visualization
GraphicsComputer Vision and Pattern Recognition
Summary
Reconstructing 3D scenes can be hard when parts of the environment change over time. ChronoFuseGS combines multiple 3D models taken at different times into one, improving details by sharing information across times. It also tracks which parts of the scene stay the same and which change, helping people see even small changes clearly. The team tested this on real outdoor scenes with floods, snow, and vegetation changes and found it captures details better than models made from single moments.
What this means in practice
- •For environmental monitoring teams: Create detailed 3D visualizations that highlight subtle seasonal and event-driven changes in outdoor areas over time.
- •For urban planners and flood engineers: Build up-to-date combined models of flood-prone regions to support assessment and planning with fine-grained change insights.
Authors
Tobias Batik, Diana Marin, Peter Kán, Hannes Kaufmann
Abstract
Reconstructing environments where parts of the scene change between captured image sets poses a challenge for 3D scene reconstruction. We present ChronoFuseGS, a multi-temporal Gaussian Splatting approach that addresses this issue by taking multiple separately trained Gaussian Splatting models, each representing a distinct timestep and partially overlapping in geographic coverage, and merging them into a single combined model. By allowing Gaussians from one timestep to contribute to the reconstruction at other timesteps, our approach leverages data across all captured timesteps to refine persistent parts of the scene. The model supports incremental extension, allowing new timesteps to be added while preserving the existing merged reconstruction. It encodes, for each Gaussian primitive, at which timesteps it contributes to the reconstruction. To support visual exploration of the reconstructed scene, we present a change-aware visualization approach that highlights the parts of the scene that have changed across a user-defined time selection, while preserving the color of persistent parts. Since the persistence encoding operates at the Gaussian primitive level, changes are visualized at sub-object granularity rather than being limited to object-level changes. We evaluate our approach on a real-world outdoor dataset of a flood management area, captured over 7 months across eight recording days and covering seasonal vegetation changes, snow cover, and flooding events, which we make publicly available. Our results demonstrate that the combined model consistently outperforms individually trained single-timestep models in novel-view synthesis quality, recovers structural details absent in the individual reconstructions, and reliably highlights changes in fine details and sub-parts of objects and natural structures.