BriefGPT.xyz
Dec, 2022
SceneRF: 用 Radiance Fields 进行自监督单目 3D 场景重建
SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields
HTML
PDF
Anh-Quan Cao, Raoul de Charette
TL;DR
本论文提出了SceneRF方法，采用自监督单目场景重建方法，只用图像序列进行训练，优化辐射场，生成新的深度视图，并成功应用于室内BundleFusion和室外SemanticKITTI的场景重建中，超越了最近的基线
Abstract
In the literature,
3d reconstruction
from 2D image has been extensively addressed but often still requires geometrical supervision. In this paper, we propose SceneRF, a
self-supervised
monocular scene reconstruct
→