[CVPR 2021] Monocular depth estimation using wavelets for efficiency

Overview

Single Image Depth Prediction with Wavelet Decomposition

Michaรซl Ramamonjisoa, Michael Firman, Jamie Watson, Vincent Lepetit and Daniyar Turmukhambetov

CVPR 2021

[Link to paper]

kitti gif nyu gif

We introduce WaveletMonoDepth, which improves efficiency of standard encoder-decoder monocular depth estimation methods by exploiting wavelet decomposition.

5 minute CVPR presentation video link

๐Ÿง‘โ€๐Ÿซ Methodology

WaveletMonoDepth was implemented for two benchmarks, KITTI and NYUv2. For each dataset, we build our code upon a baseline code. Both baselines share a common encoder-decoder architecture, and we modify their decoder to provide a wavelet prediction.

Wavelets predictions are sparse, and can therefore be computed only at relevant locations, therefore saving a lot of unnecessary computations.

our architecture

The network is first trained with a dense convolutions in the decoder until convergence, and the dense convolutions are then replaced with sparse ones.

This is because the network first needs to learn to predict sparse wavelet coefficients before we can use sparse convolutions.

๐Ÿ—‚ Environment Requirements ๐Ÿ—‚

We recommend creating a new Anaconda environment to use WaveletMonoDepth. Use the following to setup a new environment:

conda env create -f environment.yml
conda activate wavelet-mdp

Our work uses Pytorch Wavelets, a great package from Fergal Cotter which implements the Inverse Discrete Wavelet Transform (IDWT) used in our work, and a lot more! To install Pytorch Wavelets, simply run:

git clone https://github.com/fbcotter/pytorch_wavelets
cd pytorch_wavelets
pip install .

๐Ÿš— ๐Ÿšฆ KITTI ๐ŸŒณ ๐Ÿ›ฃ

Depth Hints was used as a baseline for KITTI.

Depth Hints builds upon monodepth2. If you have questions about running the code, please see the issues in their repositories first.

โš™ Setup, Training and Evaluation

Please see the KITTI directory of this repository for details on how to train and evaluate our method.

๐Ÿ“Š Results ๐Ÿ“ฆ Trained models

Please find below the scores using dense convolutions to predict wavelet coefficients. Download links coming soon!

Model name Training modality Resolution abs_rel RMSE ฮด<1.25 Weights Eigen Predictions
Ours Resnet18 Stereo + DepthHints 640 x 192 0.106 4.693 0.876 Coming soon Coming soon
Ours Resnet50 Stereo + DepthHints 640 x 192 0.105 4.625 0.879 Coming soon Coming soon
Ours Resnet18 Stereo + DepthHints 1024 x 320 0.102 4.452 0.890 Coming soon Coming soon
Ours Resnet50 Stereo + DepthHints 1024 x 320 0.097 4.387 0.891 Coming soon Coming soon

๐ŸŽš Playing with sparsity

However the most interesting part is that we can make use of the sparsity property of the predicted wavelet coefficients to trade-off performance with efficiency, at a minimal cost on performance. We do so by tuning the threshold, and:

  • low thresholds values will lead to high performance but high number of computations,
  • high thresholds will lead to highly efficient computation, as convolutions will be computed only in a few pixel locations. This will have a minimal impact on performance.

sparsify kitti

Computing coefficients at only 10% of the pixels in the decoding process gives a relative score loss of less than 1.4%.

scores kitti

Our wavelet based method allows us to greatly reduce the number of computation in the decoder at a minimal expense in performance. We can measure the performance-vs-efficiency trade-off by evaluating scores vs FLOPs.

scores vs flops kitti

๐Ÿช‘ ๐Ÿ› NYUv2 ๐Ÿ›‹ ๐Ÿšช

Dense Depth was used as a baseline for NYUv2. Note that we used the experimental PyTorch implementation of DenseDepth. Note that compared to the original paper, we made a few different modifications:

  • we supervise depth directly instead of supervising disparity
  • we do not use SSIM
  • we use DenseNet161 as encoder instead of DenseNet169

โš™ Setup, Training and Evaluation

Please see the NYUv2 directory of this repository for details on how to train and evaluate our method.

๐Ÿ“Š Results and ๐Ÿ“ฆ Trained models

Please find below the scores and associated trained models, using dense convolutions to predict wavelet coefficients.

Model name Encoder Resolution abs_rel RMSE ฮด<1.25 ฮต_acc Weights Eigen Predictions
Baseline DenseNet 640 x 480 0.1277 0.5479 0.8430 1.7170 Coming soon Coming soon
Ours DenseNet 640 x 480 0.1258 0.5515 0.8451 1.8070 Coming soon Coming soon
Baseline MobileNetv2 640 x 480 0.1772 0.6638 0.7419 1.8911 Coming soon Coming soon
Ours MobileNetv2 640 x 480 0.1727 0.6776 0.7380 1.9732 Coming soon Coming soon

๐ŸŽš Playing with sparsity

As with the KITTI dataset, we can tune the wavelet threshold to greatly reduce computation at minimal cost on performance.

sparsify nyu

Computing coefficients at only 5% of the pixels in the decoding process gives a relative depth score loss of less than 0.15%.

scores nyu

๐ŸŽฎ Try it yourself!

Try using our Jupyter notebooks to visualize results with different levels of sparsity, as well as compute the resulting computational saving in FLOPs. Notebooks can be found in <DATASET>/sparsity_test_notebook.ipynb where <DATASET> is either KITTI or NYUv2.

โœ๏ธ ๐Ÿ“„ Citation

If you find our work useful or interesting, please consider citing our paper:

@inproceedings{ramamonjisoa-2021-wavelet-monodepth,
  title     = {Single Image Depth Prediction with Wavelet Decomposition},
  author    = {Ramamonjisoa, Micha{\"{e}}l and
               Michael Firman and
               Jamie Watson and
               Vincent Lepetit and
               Daniyar Turmukhambetov},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  month = {June},
  year = {2021}
}

๐Ÿ‘ฉโ€โš–๏ธ License

Copyright ยฉ Niantic, Inc. 2021. Patent Pending. All rights reserved. Please see the license file for terms.

Owner
Niantic Labs
Building technologies and ideas that move us
Niantic Labs
PyTorch implementation of 'Gen-LaneNet: a generalized and scalable approach for 3D lane detection'

(pytorch) Gen-LaneNet: a generalized and scalable approach for 3D lane detection Introduction This is a pytorch implementation of Gen-LaneNet, which p

Yuliang Guo 233 Jan 06, 2023
Extreme Dynamic Classifier Chains - XGBoost for Multi-label Classification

Extreme Dynamic Classifier Chains Classifier chains is a key technique in multi-label classification, sinceit allows to consider label dependencies ef

6 Oct 08, 2022
Geometry-Aware Learning of Maps for Camera Localization (CVPR2018)

Geometry-Aware Learning of Maps for Camera Localization This is the PyTorch implementation of our CVPR 2018 paper "Geometry-Aware Learning of Maps for

NVIDIA Research Projects 321 Nov 26, 2022
A tight inclusion function for continuous collision detection

Tight-Inclusion Continuous Collision Detection A conservative Continuous Collision Detection (CCD) method with support for minimum separation. You can

Continuous Collision Detection 89 Jan 01, 2023
Public Models considered for emotion estimation from EEG

Emotion-EEG Set of models for emotion estimation from EEG. Composed by the combination of two deep-learing models learning together (RNN and CNN) with

Victor Delvigne 21 Dec 23, 2022
History Aware Multimodal Transformer for Vision-and-Language Navigation

History Aware Multimodal Transformer for Vision-and-Language Navigation This repository is the official implementation of History Aware Multimodal Tra

Shizhe Chen 46 Nov 23, 2022
An off-line judger supporting distributed problem repositories

Thaw ไธญๆ–‡ | English Thaw is an off-line judger supporting distributed problem repositories. Everyone can use Thaw release problems with license on GitHu

countercurrent_time 2 Jan 09, 2022
Supplemental learning materials for "Fourier Feature Networks and Neural Volume Rendering"

Fourier Feature Networks and Neural Volume Rendering This repository is a companion to a lecture given at the University of Cambridge Engineering Depa

Matthew A Johnson 133 Dec 26, 2022
Implements pytorch code for the Accelerated SGD algorithm.

AccSGD This is the code associated with Accelerated SGD algorithm used in the paper On the insufficiency of existing momentum schemes for Stochastic O

205 Jan 02, 2023
Semi-supervised Implicit Scene Completion from Sparse LiDAR

Semi-supervised Implicit Scene Completion from Sparse LiDAR Paper Created by Pengfei Li, Yongliang Shi, Tianyu Liu, Hao Zhao, Guyue Zhou and YA-QIN ZH

114 Nov 30, 2022
Modeling CNN layers activity with Gaussian mixture model

GMM-CNN This code package implements the modeling of CNN layers activity with Gaussian mixture model and Inference Graphs visualization technique from

3 Aug 05, 2022
Code for ICCV 2021 paper Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes using Scene Graphs

Graph-to-3D This is the official implementation of the paper Graph-to-3d: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphs | arx

Helisa Dhamo 33 Jan 06, 2023
A light and fast one class detection framework for edge devices. We provide face detector, head detector, pedestrian detector, vehicle detector......

A Light and Fast Face Detector for Edge Devices Big News: LFD, which is a big update of LFFD, now is released (2021.03.09). It is strongly recommended

YonghaoHe 1.3k Dec 25, 2022
Functional TensorFlow Implementation of Singular Value Decomposition for paper Fast Graph Learning

tf-fsvd TensorFlow Implementation of Functional Singular Value Decomposition for paper Fast Graph Learning with Unique Optimal Solutions Cite If you f

Sami Abu-El-Haija 14 Nov 25, 2021
A robust camera and Lidar fusion based velocity estimator to undistort the pointcloud.

Lidar with Velocity A robust camera and Lidar fusion based velocity estimator to undistort the pointcloud. related paper: Lidar with Velocity : Motion

ISEE Research Group 164 Dec 30, 2022
Portfolio analytics for quants, written in Python

QuantStats: Portfolio analytics for quants QuantStats Python library that performs portfolio profiling, allowing quants and portfolio managers to unde

Ran Aroussi 2.7k Jan 08, 2023
code for ICCV 2021 paper 'Generalized Source-free Domain Adaptation'

G-SFDA Code (based on pytorch 1.3) for our ICCV 2021 paper 'Generalized Source-free Domain Adaptation'. [project] [paper]. Dataset preparing Download

Shiqi Yang 84 Dec 26, 2022
Single-step adversarial training (AT) has received wide attention as it proved to be both efficient and robust.

Subspace Adversarial Training Single-step adversarial training (AT) has received wide attention as it proved to be both efficient and robust. However,

15 Sep 02, 2022
This is the pytorch code for the paper Curious Representation Learning for Embodied Intelligence.

Curious Representation Learning for Embodied Intelligence This is the pytorch code for the paper Curious Representation Learning for Embodied Intellig

19 Oct 19, 2022