论文汇报
文章平均质量分 95
迷迭香、鹏
这个作者很懒,什么都没留下…
展开
-
MVSTER: Epipolar Transformer for EfficientMulti-View Stereo
MVSTER网络结构如图所示。给定参考图像及其对应的源图像,首先利用特征金字塔网络提取2D多尺度特征。然后将源图像特征变化到参考摄像机坐标系下,通过可微单应性构造源体(Sec. 3.1)。随后,利用极线Transformer聚合源体并产生代价体,辅助分支进行单目深度估计以增强上下文。该体由轻量级3D CNN正则化以进行深度估计(Sec. 3.2)。进一步以级联结构构建,以粗到细的方式传播深度图 (Sec. 3.3).。原创 2023-12-26 13:31:44 · 888 阅读 · 1 评论 -
NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields
We propose a novel geometric and photometric 3D mapping pipeline for accurate and real-time scene reconstruction from monocular images. To achieve this, we leverage recent advances in dense monocular SLAM and real-time hierarchical volumetric neural radian原创 2023-11-21 13:05:49 · 139 阅读 · 1 评论 -
Power Bundle Adjustment for Large-Scale 3D Reconstruction
We introduce Power Bundle Adjustment as an expansion type algorithm for solving large-scale bundle adjustment problems. It is based on the power series expansion of the inverse Schur complement and constitutes a new family of solvers that we call inverse e原创 2023-11-14 12:26:14 · 63 阅读 · 1 评论 -
MVSNet: Depth Inference for Unstructured Multi-view Stereo
We present an end-to-end deep learning architecture for depth map inference from multi-view images. In the network, we first extract deep visual image features, and then build the 3D cost volume upon the reference camera frustum via the differentiable homo原创 2023-10-23 21:37:12 · 76 阅读 · 0 评论 -
SAMLoc: Structure-Aware Constraints With Mutil-task Distillation for Long-term Visual Localization
Real-time and robust long-term visual localization is a key technology for autonomous driving. Season and illumination variance, as well as limited computing power make this problem more challenging. At present, most of the excellent visual localization al原创 2023-10-17 12:30:34 · 71 阅读 · 0 评论 -
ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer
通过这些方法,我们不仅能够保持相关系,还能够在高相关性的像素之间实现细粒度关注,从而补偿必要的局部信息。同时,在每个局部注意力模块,我们的网络需要回归一个辅助流图作为指导,这需要交叉视图上下文,因此加入了 轻量级的 global cross attention block。在sfm、vslam 中的图像匹配中,尽管像SIFT、ORB 等关键点检测算子具有很多的应用,但由于依赖关键点检测器和特征描述中的上下文丢失,这些基于检测器的匹配方法,在极端情况下(包括大视点变化和无纹理区域)会遇到困难。原创 2023-10-16 22:10:05 · 420 阅读 · 5 评论