SCENES: エピポーラ教師あり学習によるサブピクセル対応点推定
SCENES: Subpixel Correspondence Estimation With Epipolar Supervision
3D構造や正解対応点を使わず、カメラ姿勢情報とエピポーラ制約のみで特徴マッチングモデルを新しいデータに微調整する手法を提案し、屋内ドローンや屋外スマホの難データセットで最高精度を達成した。
著者: Dominik A. Kloepfer, João F. Henriques, Dylan Campbell
分類: cs.CV, cs.AI, cs.LG, cs.RO
原文アブストラクト
Extracting point correspondences from two or more views of a scene is a fundamental computer vision problem with particular importance for relative camera pose estimation and structure-from-motion. Existing local feature matching approaches, trained with correspondence supervision on large-scale datasets, obtain highly-accurate matches on the test sets. However, they do not generalise well to new datasets with different characteristics to those they were trained on, unlike classic feature extractors. Instead, they require finetuning, which assumes that ground-truth correspondences or ground-truth camera poses and 3D structure are available. We relax this assumption by removing the requirement of 3D structure, e.g., depth maps or point clouds, and only require camera pose information, which can be obtained from odometry. We do so by replacing correspondence losses with epipolar losses, which encourage putative matches to lie on the associated epipolar line. While weaker than correspondence supervision, we observe that this cue is sufficient for finetuning existing models on new data. We then further relax the assumption of known camera poses by using pose estimates in a novel bootstrapping approach. We evaluate on highly challenging datasets, including an indoor drone dataset and an outdoor smartphone camera dataset, and obtain state-of-the-art results without strong supervision.
