【论文精读】RayMVSNet

今天读的是发表在CVPR2022上的无监督MVS文章,作者来自于国防科大。
文章链接:RayMVSNet
项目地址:Github

Abstract

作者希望直接优化每个camera ray上的深度值,所以提出这个RayMVSNet来学习1D implicit field的序列预测。使用了传统MVS里的方法进行极线搜索和transformer提取特征,并且使用了mutli-task learning。

1 Introduction

贡献主要是:

  • 一个新颖的表现形式,来学习1D隐式场。
  • epipolar transformer来学习特征。
  • mutli-task learning来建模和预测,并且基于LSTM。
  • 效果好。

2 Related Work

介绍了基于深度学习的MVS和implicit的表征。

3 Method

Overview

3.1 3D Cost Volume and Coarse Depth Prediction

Build a variance-based 3D cost volume and get coarse depth map.

3.2 Epipolar Transformer

Goal is to estimate the location of the zero-crossing point on each ray, so we can obtainthe depth map of reference image.

Why ray-based?

  • depth map is view-dependent. So optimization is more straightforward and lightweight.
  • all the 1D implicit fields share an identical spatial property, i.e. the monotonicity of the SDFs along the ray direction.

Zero-crossing hypothesis sampling

adopt coarse depth map and uniformly sample K K K points P = { p k } 1 K P=\{p_k\}_{1}^{K} P={pk}1K on the ray in the range of ± δ \pm \delta ±δ.

Epipolar transformer

Use 4 self-attention layers, each followed by 2 AddNorm and 1 feed-forward layer.


3.3 Ray-based 1D Implicit Field

Given the features of the hypothesized points, the ray-based 1D implicit fields are learned with an LSTM. Crucially, we leverage two attributes of LSTM.

  • The mechanism of sequential processing inherently facilitates the learning of the SDF monotonicity along the ray direction.
  • The property of time invariance increases the network robustness by allowing the zero-crossing position to appear at any place (time-step) on the ray.

Ray-based 1D implicit field

3.4 Implementations

4 Results and Evaluation

DTU
T&T-Intermediate

5 Conclusion

  • 22
    点赞
  • 12
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

YuhsiHu

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值