arXiv Computer Vision
Learning Scene Coordinate Reconstruction from Unposed Images via Pose Graph Optimization
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
Oct 26
Learning Scene Coordinate Reconstruction from Unposed Images via Pose Graph Optimization
Learning-based structure-from-motion methods such as ACE-Zero have demonstrated strong performance in estimating cameraposes and scene coordinates from unordered image collections without requiring gr...
arXiv Computer Vision
Sep 10
Learning Global Camera Poses from Noisy View-Graphs for Structure from Motion
arXiv:2609.09491v1 Announce Type: new Abstract: Camera pose estimation is a key step in 3D reconstruction and view-synthesis pipelines. We present a deep, global Structure-from-Motion framework based...
arXiv Computer Vision
Aug 25
Robust Global Structure-from-Motion via View Graph Pruning
arXiv:2608.22054v1 Announce Type: new Abstract: Structure-from-Motion (SfM) aims to estimate camera poses and reconstruct 3D structures from a collection of unordered images. Compared with incrementa...
arXiv Computer Vision
Oct 27
SG-Splat: Stable Geometry Learning under Pose Uncertainty for Pose-Free 3D Gaussian Splatting
arXiv:2610.35361v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has become a promising representation for real-time novel view synthesis and 3D scene reconstruction. For practical deploy...
arXiv Computer Vision
Sep 14
Dense Dynamic Scene Reconstruction and Camera Pose Estimation from Multi-View Videos
arXiv:2603.12064v3 Announce Type: replace Abstract: We address the challenging problem of dense dynamic scene reconstruction and camera pose estimation from multiple freely moving cameras -- a settin...
arXiv Computer Vision
Oct 21
PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training
PURE is an unlabeled post‑training refinement framework that enhances feed‑forward 3D reconstruction models by improving depth and camera estimation without ground‑truth supervision. It distills structural knowledge from state‑of‑the‑art 2D priors into 4D architectures, using relative depth constraints, affine‑invariant geometry distillation, and pose refinement via feature correspondences. Experiments on synthetic and real‑world dynamic benchmarks show consistent improvements across multiple state‑of‑the‑art models, effectively mitigating domain shifts and unlocking their architectural limits in challenging in‑the‑wild scenes.