Range-Agnostic Multi-View Depth Estimation With Keyframe Selection
This addresses a practical limitation in 3D reconstruction for applications like outdoor video sequences, where prior range knowledge is unreliable, though it appears incremental as it modifies the processing order rather than introducing a new paradigm.
The paper tackles the problem of multi-view depth estimation without requiring prior knowledge of the scene metric range, which is often unavailable or inaccurate in real scenarios like outdoor 3D reconstruction, and proposes RAMDepth, an efficient 2D framework that reverses the order of depth estimation and matching steps, achieving competitive performance on benchmarks.
Methods for 3D reconstruction from posed frames require prior knowledge about the scene metric range, usually to recover matching cues along the epipolar lines and narrow the search range. However, such prior might not be directly available or estimated inaccurately in real scenarios -- e.g., outdoor 3D reconstruction from video sequences -- therefore heavily hampering performance. In this paper, we focus on multi-view depth estimation without requiring prior knowledge about the metric range of the scene by proposing RAMDepth, an efficient and purely 2D framework that reverses the depth estimation and matching steps order. Moreover, we demonstrate the capability of our framework to provide rich insights about the quality of the views used for prediction. Additional material can be found on our project page https://andreaconti.github.io/projects/range_agnostic_multi_view_depth.