Geometric 4D Stitching for Grounded 4D Generation

TL;DR

This paper introduces Geometric 4D Stitching, a fast and efficient framework for improving geometric consistency in 4D scene generation by explicitly stitching missing regions, enabling quick scene expansion and editing.

Contribution

The proposed method explicitly identifies and stitches missing geometric regions in 4D scenes, significantly improving geometric consistency and efficiency over existing radiance-based approaches.

Findings

Constructs 4D scene representations in under 10 minutes on a single GPU.

Improves geometric consistency in 4D scene generation.

Supports iterative 4D mesh expansion and editing.

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.