arXiv Computer Vision
Remember, Revisit, Revise: Scaffold Memory for Long-Horizon 3D Geometry
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
5d ago
Remember, Revisit, Revise: Scaffold Memory for Long-Horizon 3D Geometry
Geometry foundation models estimate camera poses and 3D scene structure from video sequences, but maintaining consistent reconstructions over long horizons remains challenging. Feed-forward models pro...
arXiv Computer Vision
Aug 31
Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction
arXiv:2608.27529v1 Announce Type: new Abstract: Streaming 3D reconstruction from extremely long videos requires estimating camera motion and scene geometry online under bounded memory and computation...
arXiv Computer Vision
Sep 21
Adaptive World Memory 3D Foundation Model for Scalable 3D Mapping, Localization, and Rendering
The paper introduces Adaptive World Memory 3D Foundation Model (AWM-3DFM), a memory‑centric 3D foundation model that scales to large‑scale robotic localization, reconstruction, and Gaussian rendering. It employs transformer‑based gated updates, test‑time temporal‑spatial regulation, and local submap organization to maintain persistent memory, accuracy, and consistency across long image sequences. A Gaussian reconstruction head unifies pose estimation, dense point‑cloud reconstruction, and photorealistic rendering, achieving superior trajectory accuracy, reconstruction completeness, and rendering quality on public benchmarks and diverse robotic datasets.
arXiv Machine Learning
Jul 23
WorldPack: Dynamic Frame Compression for Long-context Video World Modeling
arXiv:2512. 02473v2 Announce Type: replace-cross Abstract: Video world models have attracted significant attention for their ability to produce high-fidelity future visual observations conditioned on past observations and navigation actions.
arXiv Computer Vision
Sep 15
Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping
Anchor3R is a streaming 3D reconstruction framework that predicts window-relative poses and local geometry in the current‑frame coordinate system, forming a dense relative‑pose graph for online pose updates and loop‑aware motion averaging. It improves long‑horizon pose accuracy and dense reconstruction quality on indoor, outdoor, driving, and RGB‑D benchmarks, and generalizes from 48‑frame training sequences to streams exceeding 10,000 frames while keeping GPU memory bounded. The method addresses issues of train‑test mismatch, early‑anchor bias, and accumulated drift found in previous streaming models.
arXiv Computer Vision
Oct 1
Matisse: Evidence-Space Reasoning for Active 3D Reconstruction
Matisse is a training‑free framework that combines active 3D reconstruction with keyframe selection by using evidence from a pretrained generative 3D model. It estimates evidential uncertainty via cross‑attention on 3D latent tokens and derives an evidential information gain to guide view acquisition and keyframe selection, reducing redundant observations and supporting multi‑object scenes with occlusion‑aware aggregation. On GSO30, YCB‑V, and Replica, Matisse improves Chamfer distance by 12.7%, 3.8%, and 9.2% respectively, and speeds up end‑to‑end reconstruction by 1.5× compared to the best baseline.