バンドル調整付きNeRF：未知カメラ姿勢からの3D表現学習
BARF: Bundle-Adjusting Neural Radiance Fields
カメラ姿勢が未知・不正確な場合でもNeRFを学習できるよう、古典的画像位置合わせの粗から細への登録をNeRFに統合したBARFを提案し、合成・実データで姿勢推定と新規視点合成の有効性を示した。
著者: Chen-Hsuan Lin, Wei-Chiu Ma, Antonio Torralba, Simon Lucey
分類: cs.CV, cs.GR, cs.LG, cs.RO
原文アブストラクト
Neural Radiance Fields (NeRF) have recently gained a surge of interest within the computer vision community for its power to synthesize photorealistic novel views of real-world scenes. One limitation of NeRF, however, is its requirement of accurate camera poses to learn the scene representations. In this paper, we propose Bundle-Adjusting Neural Radiance Fields (BARF) for training NeRF from imperfect (or even unknown) camera poses -- the joint problem of learning neural 3D representations and registering camera frames. We establish a theoretical connection to classical image alignment and show that coarse-to-fine registration is also applicable to NeRF. Furthermore, we show that na\"ively applying positional encoding in NeRF has a negative impact on registration with a synthesis-based objective. Experiments on synthetic and real-world data show that BARF can effectively optimize the neural scene representations and resolve large camera pose misalignment at the same time. This enables view synthesis and localization of video sequences from unknown camera poses, opening up new avenues for visual localization systems (e.g. SLAM) and potential applications for dense 3D mapping and reconstruction.
