Geometric 4D Stitching for Grounded 4D Generation
This work addresses geometric inconsistencies and expensive optimization in 4D generation for scene-level content creation, offering a faster and more consistent alternative.
The paper proposes Geometric 4D Stitching, a framework that explicitly identifies missing geometric regions in 4D scenes and complements them with geometrically grounded stitches, constructing 4D scene representations in under 10 minutes on a single GPU while improving geometric consistency.
Recent 4D generation methods complete scene-level missing information using generative models and reconstruct the scene into radiance-based representations. However, these pipelines often present geometric inconsistencies in the generated content, and the radiance-based reconstruction requires expensive optimization. Furthermore, radiance-based representations often absorb these geometric inconsistencies into their view-dependent nature, failing to enforce the grounded geometric consistency. To address these issues, we propose Geometric 4D Stitching, an efficient framework that explicitly identifies missing geometric regions and complements them with geometrically grounded 4D stitches. As a result, our method constructs 4D scene representations in under 10 minutes on a single NVIDIA RTX 5090 GPU per one-step scene expansion, while improving geometric consistency. Moreover, we demonstrate that our explicit 4D stitching supports interative expansion of 4D mesh as well as 4D scene editing.