MIRAGE: Metric Inference and Reliability-Aware Gaussian Estimation from Feed-Forward Vision
cs.CV
Submitted: 2026-10-08
Updated: 2026-10-14
Comments: Project Page: https://hiroxzwang.github.io/publications/mirage/
Project page: https://hiroxzwang.github.io/publications/mirage
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- EllipseLIO: Adaptive LiDAR Inertial Odometry with an Ellipsoid Representation
- Direct LiDAR-Inertial Odometry: Lightweight LIO with Continuous-Time Motion Correction
- PreF3R: Pose-Free Feed-Forward 3D Gaussian Splatting from Variable-length Image Sequence
- Glob3R: Global Structure-from-Motion with 3D Foundation Models
- VPGS-SLAM: Voxel-based Progressive 3D Gaussian SLAM in Large-Scale Scenes
- PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction
- Gaussian-LIC2: LiDAR-Inertial-Camera Gaussian Splatting SLAM
- RMGS-SLAM: Real-time Multi-sensor Gaussian Splatting SLAM
- Depth Anything 3: Recovering the Visual Space from Any Views
- VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction
- M^3: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM
- $\pi^3$: Permutation-Equivariant Visual Geometry Learning
- Depth Anything with Any Prior
- LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory
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