Although Neural Radiance Fields (NeRF) is popular in the computer vision
community recently, registering multiple NeRFs has yet to gain much attention.
Unlike the existing work, NeRF2NeRF, which is based on traditional optimization
methods and needs human annotated keypoints, we propose DReg-NeRF to solve the
NeRF registration problem on object-centric scenes without human intervention.
After training NeRF models, our DReg-NeRF first extracts features from the
occupancy grid in NeRF. Subsequently, our DReg-NeRF utilizes a transformer
architecture with self-attention and cross-attention layers to learn the
relations between pairwise NeRF blocks. In contrast to state-of-the-art (SOTA)
point cloud registration methods, the decoupled correspondences are supervised
by surface fields without any ground truth overlapping labels. We construct a
novel view synthesis dataset with 1,700+ 3D objects obtained from Objaverse to
train our network. When evaluated on the test set, our proposed method beats
the SOTA point cloud registration methods by a large margin, with a mean
$\text{RPE}=9.67^{\circ}$ and a mean $\text{RTE}=0.038$.
Our code is available at this https URL

通过使用 DReg-NeRF 方法，我们能够在不需要人为干预的情况下解决对象中心场景的 NeRF 注册问题，并通过构建一个新颖的视图综合数据集进行训练，从而在测试集上显著超过目前最先进的点云注册方法。

DReg-NeRF：神经辐射场的深度配准

DReg-NeRF: Deep Registration for Neural Radiance Fields

This paper presents a novel approach to the Extreme Structure from Motion
(E-SfM) problem, which takes a set of room layouts as polygonal curves in the
top-down view, and aligns the room layout pieces by estimating their 2D
translations and rotations, akin to solving the jigsaw puzzle of room layouts.
The biggest discovery and surprise of the paper is that the simple use of a
Diffusion Model solves this challenging registration problem as a conditional
generation process. The paper presents a new dataset of room layouts and
floorplans for 98,780 houses. The qualitative and quantitative evaluations
demonstrate that the proposed approach outperforms the competing methods by
significant margins.

本文提出了一种新颖的方法来解决 “极端结构运动” 问题，通过估计 2D 平移和旋转来对齐房间布局，解决仿佛房间布局拼图的问题，并使用扩散模型解决了具有挑战性的注册问题。该论文还提出了一个新的数据集，用于 98,780 幢房屋的房间布局和平面图，并经定量和定性评估证明，所提出的方法表现出比竞争方法更好的性能。