arXiv Computer Vision
OptiGeo: Efficient Monocular Geometry for Embodied Perception in Optically Challenging Scenes
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Oct 7
DepthWorld: 3D World Model for Robot Manipulation
arXiv:2610.08780v1 Announce Type: cross Abstract: World models offer a data-driven alternative to traditional simulators for robotics, with applications spanning policy evaluation, improvement, and p...
Hugging Face Trending Papers
Oct 6
DepthWorld: 3D World Model for Robot Manipulation
World models offer a data-driven alternative to traditional simulators for robotics, with applications spanning policy evaluation, improvement, and planning. All of these uses depend on faithful 3D ge...
Hugging Face Trending Papers
Jul 13
FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry
We present FoundationGeo, a two-stage framework that explicitly bridges relative and metric prediction via spatial calibration and principled data design. Stage 1 learns a high-fidelity, affine-invariant geometry model by initializing with DINOv3 and training on a curated 10.
arXiv Computer Vision
Sep 23
Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene Reconstruction
arXiv:2609.23796v2 Announce Type: replace Abstract: Single-image 3D object generation can now produce high-fidelity assets, yet accurately placing them into a coherent scene layout remains an open ch...
arXiv Computer Vision
Sep 22
Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene
arXiv:2609.23796v1 Announce Type: new Abstract: Single-image 3D object generation can now produce high-fidelity assets, yet accurately placing them into a coherent scene layout remains an open challe...
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.