The implemention of Video Depth Estimation by Fusing Flow-to-Depth Proposals

Last update: Jun 14, 2022

Related tags

Deep Learning Video-depth-estimation

Overview

Flow-to-depth (FDNet) video-depth-estimation

This is the implementation of paper

Video Depth Estimation by Fusing Flow-to-Depth Proposals

Jiaxin Xie, Chenyang Lei, Zhuwen Li, Li Erran Li, Qifeng Chen

In IROS 2020.

See our paper (https://arxiv.org/pdf/1912.12874.pdf) for more details. Please contact Jiaxin Xie ([email protected]) if you have any questions.

Prerequisites

This codebase was developed and tested with Tensorflow 1.4.0 and Numpy 1.16.2

Evaluation on KITTI Eigen Split

IF you want to generate GroundTruth Depth from KITTI RAW data, download KITTI dataset using this script provided on the official website.

Meanwhile, we also provided GroundTruth Depth save in npy file, download it from here

Our final results on KITTI Eigen is availible on here

Then run

python kitti_eval/eval_depth_general.py --kitti_dir=/path/to/raw/kitti/dataset/ or /path/to/downloaded/GoundTruth/npy/file/ --pred_file=/path/to/our/final/results/

EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation

EFENet EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation Code is a bit messy now. I woud clean up soon. For training the EF

6 Oct 20, 2021

RIFE - Real-Time Intermediate Flow Estimation for Video Frame Interpolation

RIFE - Real-Time Intermediate Flow Estimation for Video Frame Interpolation YouTube | BiliBili 16X interpolation results from two input images: Introd

28 Dec 9, 2022

Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals.

Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals This repo contains the Pytorch implementation of our paper: Unsupervised Seman

335 Dec 28, 2022

(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"

Res2Net The official pytorch implemention of the paper "Res2Net: A New Multi-scale Backbone Architecture" Our paper is accepted by IEEE Transactions o

928 Dec 29, 2022

Sparse R-CNN: End-to-End Object Detection with Learnable Proposals, CVPR2021

End-to-End Object Detection with Learnable Proposal, CVPR2021

1.2k Dec 27, 2022

Learning Open-World Object Proposals without Learning to Classify

Learning Open-World Object Proposals without Learning to Classify Pytorch implementation for "Learning Open-World Object Proposals without Learning to

149 Dec 22, 2022

Code for the paper SphereRPN: Learning Spheres for High-Quality Region Proposals on 3D Point Clouds Object Detection, ICIP 2021.

SphereRPN Code for the paper SphereRPN: Learning Spheres for High-Quality Region Proposals on 3D Point Clouds Object Detection, ICIP 2021. Authors: Th

15 Dec 2, 2022

AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation

AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation A pytorch-version implementation codes of paper:

11 Dec 13, 2022

Official PyTorch implemention of our paper "Learning to Rectify for Robust Learning with Noisy Labels".

WarPI The official PyTorch implemention of our paper "Learning to Rectify for Robust Learning with Noisy Labels". Run python main.py --corruption_type

3 Sep 3, 2022

Comments

Question regarding the evaluation protocol
Hi,

I had a few questions regarding the evaluation protocol. I was hoping if you could answer them.

The ScanNet ROB test set contains 962 images, but the data/ScanNet/ScanNet_files_ROB.txt file only contains 950 files. Were the 12 images discarded for a particular reason?

At test time, did you do the median matching? (i.e. pred = pred * (np.median(gt) / np.median(pred)))

I saw in the paper that you made a comparison against NeuralRGBD, but NeuralRGBD cannot make predictions for the first few (and the last few) frames. Did you ignore such frames when calculating the error metrics?

Thank you very much in advance!
opened by baegwangbin 0
Waymo dataset

Hi,

I would be interested in using your model to generate depth maps for the Waymo dataset. In your paper, you provide some results on this dataset. Can you please also release the code that would generate the depth maps?

Thank you very much in advance!

opened by vobecant 3

Owner

GitHub

Official PyTorch Implementation of Unsupervised Learning of Scene Flow Estimation Fusing with Local Rigidity

UnRigidFlow This is the official PyTorch implementation of UnRigidFlow (IJCAI2019). Here are two sample results (~10MB gif for each) of our unsupervis

28 Nov 16, 2022

Monocular Depth Estimation - Weighted-average prediction from multiple pre-trained depth estimation models

merged_depth runs (1) AdaBins, (2) DiverseDepth, (3) MiDaS, (4) SGDepth, and (5) Monodepth2, and calculates a weighted-average per-pixel absolute dept

39 Nov 21, 2022

Light-weight network, depth estimation, knowledge distillation, real-time depth estimation, auxiliary data.

light-weight-depth-estimation Boosting Light-Weight Depth Estimation Via Knowledge Distillation, https://arxiv.org/abs/2105.06143 Junjie Hu, Chenyou F

13 Dec 10, 2022

PyTorch implemention of ICCV'21 paper SGPA: Structure-Guided Prior Adaptation for Category-Level 6D Object Pose Estimation

SGPA: Structure-Guided Prior Adaptation for Category-Level 6D Object Pose Estimation This is the PyTorch implemention of ICCV'21 paper SGPA: Structure

24 Dec 5, 2022

official Pytorch implementation of ICCV 2021 paper FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting.

FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting By Rui Liu, Hanming Deng, Yangyi Huang, Xiaoyu Shi, Lewei Lu, Wenxiu

77 Dec 27, 2022

Just Go with the Flow: Self-Supervised Scene Flow Estimation

Just Go with the Flow: Self-Supervised Scene Flow Estimation Code release for the paper Just Go with the Flow: Self-Supervised Scene Flow Estimation,

50 Nov 22, 2022

The official pytorch implemention of the CVPR paper "Temporal Modulation Network for Controllable Space-Time Video Super-Resolution".

This is the official PyTorch implementation of TMNet in the CVPR 2021 paper "Temporal Modulation Network for Controllable Space-Time VideoSuper-Resolu

95 Oct 24, 2022