MonoNeRF: カメラ姿勢なしの単眼動画から汎化可能なNeRFを学習
MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Pose
深度やカメラ姿勢の正解なしに単眼動画から学習できる汎化可能なNeRFを提案し、深度推定・カメラ姿勢推定・単一画像からの新視点合成を実現した。
著者: Yang Fu, Ishan Misra, Xiaolong Wang
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
We propose a generalizable neural radiance fields - MonoNeRF, that can be trained on large-scale monocular videos of moving in static scenes without any ground-truth annotations of depth and camera poses. MonoNeRF follows an Autoencoder-based architecture, where the encoder estimates the monocular depth and the camera pose, and the decoder constructs a Multiplane NeRF representation based on the depth encoder feature, and renders the input frames with the estimated camera. The learning is supervised by the reconstruction error. Once the model is learned, it can be applied to multiple applications including depth estimation, camera pose estimation, and single-image novel view synthesis. More qualitative results are available at: https://oasisyang.github.io/mononerf .
