In the field of monocular 3D detection, it is common practice to utilize
scene geometric clues to enhance the detector's performance. However, many
existing works adopt these clues explicitly such as estimating a depth map and
back-projecting it into 3D space. This explicit methodology induces sparsity in
3D representations due to the increased dimensionality from 2D to 3D, and leads
to substantial information loss, especially for distant and occluded objects.
To alleviate this issue, we propose MonoNeRD, a novel detection framework that
can infer dense 3D geometry and occupancy. Specifically, we model scenes with
Signed Distance Functions (SDF), facilitating the production of dense 3D
representations. We treat these representations as Neural Radiance Fields
(NeRF) and then employ volume rendering to recover RGB images and depth maps.
To the best of our knowledge, this work is the first to introduce volume
rendering for M3D, and demonstrates the potential of implicit reconstruction
for image-based 3D perception. Extensive experiments conducted on the KITTI-3D
benchmark and Waymo Open Dataset demonstrate the effectiveness of MonoNeRD.
Codes are available at this https URL

在单目三维检测领域，为了提高检测性能常常使用场景几何线索，然而现有的方法明确采用这些线索，例如估计深度图并将其反投影到三维空间。为了缓解这个问题，我们提出了 MonoNeRD，这是一个能够推断密集三维几何和占用的新型检测框架，我们将场景建模为有符号距离函数（SDF），利用体素渲染恢复 RGB 图像和深度图。据我们所知，这项工作首次将体素渲染引入到单目三维检测中，并展示了基于隐式重构的图像三维感知的潜力。在 KITTI-3D 基准和 Waymo 开放数据集上进行的大量实验证明了 MonoNeRD 的有效性。代码可在此 URL 上找到。