Predicting High-precision Depth on Low-Precision Devices Using 2D Hilbert Curves

TL;DR

This paper introduces a novel method to enhance high-precision depth prediction on low-precision devices by representing depth with Hilbert curve components, enabling accurate results with minimal computational overhead.

Contribution

The authors propose a new approach that uses Hilbert curve decomposition to restore high dynamic range depth from low-bit predictions, improving on-device depth accuracy.

Findings

Increases depth bit precision by up to three bits.

Reduces quantization error by up to 4.6 times.

Enables accurate depth prediction with 8-bit quantized DNNs.

Abstract

Dense depth prediction deep neural networks (DNN) have achieved impressive results for both monocular and binocular data, but still they are limited by high computational complexity, restricting their use on low-end devices. For better on-device efficiency and hardware utilization, weights and activations of the DNN should be converted to low-bit precision. However, this precision is not sufficient to represent high dynamic range depth. In this paper, we aim to overcome this limitation and restore high-precision depth from low-bit precision predictions. To achieve this, we propose to represent high dynamic range depth as two low dynamic range components of a Hilbert curve, and to train the full-precision DNN to directly predict the latter. For on-device deployment, we use standard quantization methods and add a post-processing step that reconstructs depth from the Hilbert curve components predicted in low-bit precision. Extensive experiments demonstrate that our method increases the bit precision of predicted depth by up to three bits with little computational overhead. We also observed a positive side effect of quantization error reduction by up to 4.6 times. Our method enables effective and accurate depth prediction with DNN weights and activations quantized to eight-bit precision.