Comments (7)
Unfortunately, your explanation only raises more questions. Anyway, thank you for the effort.
I do not see any point in further discussion, since our perception of what research is seems to be very different.
from featdepth.
Since Monodepth2 and Depth-VO-Feat are only 2 models from 20+ our baselines, there are plenty of other methods which use high resolution inputs and big models. For example, depthhint can be considered as an improved version of Monodepth2.
from featdepth.
I am afraid that is not quite what I asked. Fair comparison to Monodepth2 is important for 2 reasons:
- It is one of the best performing methods trained on monocular videos;
- Your model is basically Monodepth2 + proposed improvement, so fair comparison is essential to see the effect of the proposed method.
I don't want to sound rude, but from the point of view of experienced reader, your performance gain seems to be the result of a bigger encoder. I am really curious why the reviewers at ECCV did not insist on the comparison to Monodepth2 with ResNet50 and 320x1024 input resolution.
As for Depth-Hints, I don't know what variant of Depth-Hints you compare to, since the numbers in your paper are different from the reported in the original paper. They report the following numbers for ResNet18 320x1024 MS + post-processing model:
Abs Rel Sq Rel RMSE RMSE log δ<1.25 δ<1.25^2 δ<1.25^3
0.098 0.702 4.398 0.183 0.887 0.963 0.983
You report the following numbers for their method with pp:
0.100 0.728 4.469 0.185 0.885 0.962 0.982
Looking forward to your response to the question about Monodepth2.
from featdepth.
1、I think our ablation study can clearify this question, the base model without any improvement also got a very good performance, which is much higher than monodepth2. You can consider this gain comes from a bigger backbone and higher input resolutions (although we use a different architecture for depthdecoder). It not easy to make further imrpovement on such a high performance base model, but our technique really did.
2、The numbers of DepthHint in our paper is from table2 row 10 in its paper, the numbers you refer to is not using KITTI dataset. You can see that depthhint already use ResNet50 and 320*1024 input resolution (in table 3 with pp), so I afraid it is no need to make extra experiments.
I hope this explanation can help, looking forward to further discussion.
from featdepth.
Also very currious about how FeatDepth performs with ResNet 18 on 640x192 input :) Wondering if you could provide the weight?
from featdepth.
Sorry, I don't maintain pretrained weights of this settings.
from featdepth.
I wonder if the reported performance choice the best weights from different epochs in training phase according to the loss on the test set? As I konw, monodepth2 used the last epoch for their reported results. @sconlyshootery @Yevkuzn
from featdepth.
Related Issues (20)
- running infer_singleimage.py in win10 ModuleNotFoundError: No module named 'resource' HOT 1
- it seems that the decoder of the auto-encoder network is not trained in the code HOT 1
- About the training and testing setting. HOT 4
- Is there a way to visually check the output of the FeatureNet HOT 1
- Question about MS evaluation HOT 5
- dataset.flag HOT 1
- An error occurred while training my own dataset HOT 2
- How to start non-distributed training HOT 2
- Why use DistOptimizerHook? HOT 1
- Problems using DDP HOT 2
- Train only Image Reconstruction Model HOT 2
- cfg_kitti_fm.py stops while training, expected 4 input channels, but got 3 channels instead
- train on own dataset with fm_joint.cfg HOT 1
- pose question HOT 1
- pose question HOT 2
- feature-metric loss only use the first output of the Autoencoder HOT 2
- Evaluation Issue HOT 1
- how to use multi-gpus training?
- Weights for Monocular-only training
- 关于online refinement的疑问
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from featdepth.