# 4D Primitive-Mach'e: Glueing Primitives for Persistent 4D Scene Reconstruction

arXiv: https://arxiv.org/abs/2512.16564 · HTML: https://mlsanity.com/paper/2512.16564/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 18 Dec 2025.

## Builds on (most cited first, 25 of 25)

- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos](https://mlsanity.com/paper/2412.04463/) (2024)
- [MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors](https://mlsanity.com/paper/2412.12392/) (2024)
- [Robust Consistent Video Depth Estimation](https://mlsanity.com/paper/2012.05901/) (2020)
- [ViPE: Video Pose Engine for 3D Geometric Perception](https://mlsanity.com/paper/2508.10934/) (2025)
- [CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAM](https://mlsanity.com/paper/1804.00874/) (2018)
- [A micro Lie theory for state estimation in robotics](https://mlsanity.com/paper/1812.01537/) (2018)
- [DeepFactors: Real-Time Probabilistic Dense Monocular SLAM](https://mlsanity.com/paper/2001.05049/) (2020)
- [St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World](https://mlsanity.com/paper/2504.13152/) (2025)
- [MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM](https://mlsanity.com/paper/1812.07976/) (2018)
- [AllTracker: Efficient Dense Point Tracking at High Resolution](https://mlsanity.com/paper/2506.07310/) (2025)
- [Co-Fusion: Real-time Segmentation, Tracking and Fusion of Multiple Objects](https://mlsanity.com/paper/1706.06629/) (2017)
- [Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction](https://mlsanity.com/paper/2503.16318/) (2025)
- [Trace Anything: Representing Any Video in 4D via Trajectory Fields](https://mlsanity.com/paper/2510.13802/) (2025)
- [Monocular Dense 3D Reconstruction of a Complex Dynamic Scene from Two Perspective Frames](https://mlsanity.com/paper/1708.04398/) (2017)
- [POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction](https://mlsanity.com/paper/2504.05692/) (2025)
- [Superpixel Soup: Monocular Dense 3D Reconstruction of a Complex Dynamic Scene](https://mlsanity.com/paper/1911.09092/) (2019)
- [CodeMapping: Real-Time Dense Mapping for Sparse SLAM using Compact Scene Representations](https://mlsanity.com/paper/2107.08994/) (2021)
- [SuperPrimitive: Scene Reconstruction at a Primitive Level](https://mlsanity.com/paper/2312.05889/) (2023)
- [COMO: Compact Mapping and Odometry](https://mlsanity.com/paper/2404.03531/) (2024)
- [One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory](https://mlsanity.com/paper/2505.23617/) (2025)

## Built on by (most cited first, 1 of 1)

- [VGGT-Omega](https://mlsanity.com/paper/2605.15195/) (2026)

## Abstract (arXiv)

We present a dynamic reconstruction system that receives a casual monocular RGB video as input, and outputs a complete and persistent reconstruction of the scene. In other words, we reconstruct not only the the currently visible parts of the scene, but also all previously viewed parts, which enables replaying the complete reconstruction across all timesteps. Our method decomposes the scene into a set of rigid 3D primitives, which are assumed to be moving throughout the scene. Using estimated dense 2D correspondences, we jointly infer the rigid motion of these primitives through an optimisation pipeline, yielding a 4D reconstruction of the scene, i.e. providing 3D geometry dynamically moving through time. To achieve this, we also introduce a mechanism to extrapolate motion for objects that become invisible, employing motion-grouping techniques to maintain continuity. The resulting system enables 4D spatio-temporal awareness, offering capabilities such as replayable 3D reconstructions of articulated objects through time, multi-object scanning, and object permanence. On object scanning and multi-object datasets, our system significantly outperforms existing methods both quantitatively and qualitatively.