Materials science

Programming language

Convolutional neural network

Artificial intelligence

Composite material

Set (abstract data type)

Range (aeronautics)

Geometry

Code (set theory)

Pattern recognition (psychology)

Mathematics

Operating system

Computer science

Block (permutation group theory)

RGB color model

Encoder

Computer vision

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.

AdaBins: Depth Estimation Using Adaptive Bins