Revisit Self-supervised Depth Estimation with Local Structure-from-Motion
원문 초록
Both self-supervised depth estimation and Structure-from-Motion (SfM) recover scene depth from RGB videos. Despite sharing a similar objective, the two approaches are disconnected. Prior works of self-supervision backpropagate losses defined within immediate neighboring frames. Instead of learning-through-loss, this work proposes an alternative scheme by performing local SfM. First, with calibrated RGB or RGB-D images, we employ a depth and correspondence estimator to infer depthmaps and pair-wise correspondence maps. Then, a novel bundle-RANSAC-adjustment algorithm jointly optimizes camera poses and one depth adjustment for each depthmap. Finally, we fix camera poses and employ a NeRF, however, without a neural network, for dense triangulation and geometric verification. Poses, depth adjustments, and triangulated sparse depths are our outputs. For the first time, we show self-supervision within $5$ frames already benefits SoTA supervised depth and correspondence models. The project page is held in the link (https://shngjz.github.io/SSfM.github.io/).
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Improving Geometric Consistency for 360-Degree Neural Radiance Fields in Indoor Scenarios
Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations
Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation
MonoMVSNet: Monocular Priors Guided Multi-View Stereo Network
VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting
UnMix-NeRF: Spectral Unmixing Meets Neural Radiance Fields
토론
이 논문과 연결된 포럼 글이 아직 없습니다.