Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2506.18601

BulletGen: Improving 4D Reconstruction with Bullet-Time Generation

Denis Rozumny·Jonathon Luiten·Numair Khan·Johannes Schönberger·Peter Kontschieder
View original source ↗Read source document ↗Export metadata ↓

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.

Explore related subjects

cs.GRcs.AIcs.CVcs.LG

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Denis Rozumny, Jonathon Luiten, Numair Khan, Johannes Schönberger, Peter Kontschieder. 2026-04-07. BulletGen: Improving 4D Reconstruction with Bullet-Time Generation. https://arxiv.org/abs/2506.18601

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Constrained Program Generation for 3D Reaction Animation with a 0.8B Model

Visualizing a chemical reaction requires making its molecular changes visible while keeping the animation faithful to the stated chemistry. Equations, structural diagrams and molecular viewers provide complementary descriptions, but assembling an interactive three-dimensional explanation still requires specifying the changes and checking their consistency. We present ChemXRG, a domain-specific language (DSL) framework that addresses this gap by representing a reaction animation as an executable program. Persistent atom identifiers and explicit bond, charge and grouping operations connect the symbolic reaction to the displayed transformation. This shared representation lets generation, verification and rendering operate on the same account of what changes. Given known, atom-mapped reactant and product structures, reaction-grounded constraints fix input-determined facts and restrict action choices; execution checks validate the resulting transformation before geometry and frames are constructed. We implement this paradigm with a reaction-program corpus and ChemQwen, a trained 0.8B DSL generator. Paired and component evaluations show improved compiler acceptance and normalized full-program agreement under input-conditioned constraints, while identifying remaining failures that require execution checks. A public browser application demonstrates the connection from symbolic reaction descriptions to inspectable programs and interactive 3D animations.

cs.GR↗
arXiv2026

NaRPA: Navigation and Rendering Pipeline for Astronautics

This paper presents the applications of scientific ray-tracing in modeling and simulating light transport for space-borne image data generation. A ray-tracing engine, the Navigation and Rendering Pipeline for Astronautics (NaRPA), is introduced as a rendering framework to generate virtual datasets and support simulations for robust navigation pipelines. Sensor and environment models that enable the synthesis of space-to-space and ground-to-space virtual observations are presented. The work demonstrates the capabilities of simulating passive and active vision-based sensors using NaRPA to facilitate the design, testing, and verification of aerospace visual navigation algorithms. Additionally, the paper describes a velocimeter LiDAR model and its statistical validation with experimental data.

cs.GR↗
arXiv2026

VoroUDF: Meshing Unsigned Distance Fields with Voronoi Optimization

We present VoroUDF, an algorithm for reconstructing high-quality triangle meshes from Unsigned Distance Fields (UDFs). Our algorithm supports non-manifold geometry, sharp features, and open boundaries, without relying on error-prone inside/outside estimation, restrictive look-up tables nor topologically noisy optimization. Unlike fixed-grid approaches, our Voronoi-based formulation optimizes a set of movable seeds that travel freely along the iso-surface, jointly minimizing a tangent-plane fitting energy, driven by a fixed set of surface samples queried once from the UDF and its gradient, and a repulsion energy that keeps the seeds evenly distributed. It achieves significantly improved topological consistency and geometric fidelity compared to existing methods, while producing lightweight meshes suitable for downstream real-time and interactive applications.

cs.GR↗