🤖 AI Summary
Existing 4D generation methods often suffer from geometric inconsistency and high computational costs due to their reliance on radiance field optimization. This work proposes an efficient framework that introduces, for the first time, an explicit geometry-aware 4D stitching mechanism. By identifying missing geometric regions and performing plausible completion, the method achieves geometrically consistent 4D scene reconstruction. It avoids implicitly embedding geometric errors into view-dependent representations and enables iterative expansion and editing of 4D meshes. Experimental results demonstrate that each step of scene expansion takes less than 10 minutes on a single NVIDIA RTX 5090 GPU, significantly improving both geometric consistency and computational efficiency in 4D generation.
📝 Abstract
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.