We propose a novel architecture for depth estimation from a single image. The
architecture itself is based on the popular encoder-decoder architecture that
is frequently used as a starting point for all dense regression tasks. We build
on AdaBins which estimates a global distribution of depth values for the input
image and evolve the architecture in two ways. First, instead of predicting
global depth distributions, we predict depth distributions of local
neighborhoods at every pixel. Second, instead of predicting depth distributions
only towards the end of the decoder, we involve all layers of the decoder. We
call this new architecture LocalBins. Our results demonstrate a clear
improvement over the state-of-the-art in all metrics on the NYU-Depth V2
dataset. Code and pretrained models will be made publicly available.

通过局部深度分布代替全局深度分布并将其引入编码器 - 解码器架构中，以提高从单个图像中估计深度的准确性

LocalBins: 通过学习局部分布改善深度估计

LocalBins: Improving Depth Estimation by Learning Local Distributions

We address the problem of estimating a high quality dense depth map from a
single RGB input image. We start out with a baseline encoder-decoder
convolutional neural network architecture and pose the question of how the
global processing of information can help improve overall depth estimation. To
this end, we propose a transformer-based architecture block that divides the
depth range into bins whose center value is estimated adaptively per image. The
final depth values are estimated as linear combinations of the bin centers. We
call our new building block AdaBins. Our results show a decisive improvement
over the state-of-the-art on several popular depth datasets across all metrics.
We also validate the effectiveness of the proposed block with an ablation study
and provide the code and corresponding pre-trained weights of the new
state-of-the-art model.

本论文提出了一种新型的基于 Transformer 的 AdaBins 深度估计架构，与现有技术相比，在多个流行的深度估计数据集上实现了显着提升，提供了代码和预训练模型的权重。