OptiGeo: Efficient Monocular Geometry for Embodied Perception in Optically Challenging Scenes
cs.CV
Submitted: 2026-08-30
Updated: 2026-10-10
Comments: Accepted at CoRL 2026. Project page: https://mx-liu6.github.io/OptiGeo-web/
Code: https://github.com/ros-planning/navigation2
Project page: https://mx-liu6.github.io/OptiGeo-web
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- DINOv3
- MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts
- UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler
- SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacification
- Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation
- Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis
- ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth
- UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Driving
- IRS: A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal Estimation
- DIODE: A Dense Indoor and Outdoor DEpth Dataset
- Depth Anything 3: Recovering the Visual Space from Any Views
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models