[2506.18601] BulletGen: Improving 4D Reconstruction with Bullet-Time Generation

Computer Science > Graphics arXiv:2506.18601 (cs) [Submitted on 23 Jun 2025 (v1), last revised 7 Apr 2026 (this version, v2)] Title:BulletGen: Improving 4D Reconstruction with Bullet-Time Generation Authors:Denis Rozumny, Jonathon Luiten, Numair Khan, Johannes Schönberger, Peter Kontschieder View a PDF of the paper titled BulletGen: Improving 4D Reconstruction with Bullet-Time Generation, by Denis Rozumny and 4 other authors View PDF HTML (experimental) Abstract:Transforming casually captured, monocular videos into fully immersive dynamic experiences is a highly ill-posed task, and comes with significant challenges, e.g., reconstructing unseen regions, and dealing with the ambiguity in monocular depth estimation. In this work we introduce BulletGen, an approach that takes advantage of generative models to correct errors and complete missing information in a Gaussian-based dynamic scene representation. This is done by aligning the output of a diffusion-based video generation model with the 4D reconstruction at a single frozen "bullet-time" step. The generated frames are then used to supervise the optimization of the 4D Gaussian model. Our method seamlessly blends generative content with both static and dynamic scene components, achieving state-of-the-art results on both novel-view synthesis, and 2D/3D tracking tasks. Comments: Subjects: Graphics (cs.GR); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) Cite as: arXiv...