论文标题
低记忆足迹量化了神经网络，以深度完成非常稀疏的飞行时间深度图
A Low Memory Footprint Quantized Neural Network for Depth Completion of Very Sparse Time-of-Flight Depth Maps
论文作者
论文摘要
稀疏的主动照明可以使精确的飞行时间深度感测，因为它可以最大程度地提高低功率预算的信号噪声比率。但是，需要完成深度以生成3D感知的密集深度图。我们通过模拟具有挑战性的稀疏度的室内3D感知的TOF数据集来通过逼真的照明和传感器分辨率约束来解决此任务。我们为此任务提出了一个量化的卷积编码器网络。我们的模型通过输入预处理和经过仔细调整的训练来实现最佳的深度图质量。我们还通过混合精确量化技术来实现低记忆足迹，以实现重量和激活。所得的量化模型在质量方面与艺术的状态相媲美，但是它们需要非常低的GPU时间，并实现了W.R.T.重量的最多14倍记忆尺寸。它们的浮点对应物对质量指标的影响很小。
Sparse active illumination enables precise time-of-flight depth sensing as it maximizes signal-to-noise ratio for low power budgets. However, depth completion is required to produce dense depth maps for 3D perception. We address this task with realistic illumination and sensor resolution constraints by simulating ToF datasets for indoor 3D perception with challenging sparsity levels. We propose a quantized convolutional encoder-decoder network for this task. Our model achieves optimal depth map quality by means of input pre-processing and carefully tuned training with a geometry-preserving loss function. We also achieve low memory footprint for weights and activations by means of mixed precision quantization-at-training techniques. The resulting quantized models are comparable to the state of the art in terms of quality, but they require very low GPU times and achieve up to 14-fold memory size reduction for the weights w.r.t. their floating point counterpart with minimal impact on quality metrics.
