Comments (4)
- In the scaled depth space, I have tried it. It can also work. We used this configure in our later paper 'DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data.' (github [https://github.com/YvanYin/DiverseDepth]) .
- delta_diff_x/y/z is the distance difference between 2 points along x/y/z axis. delta_cos is the cosine is the
cos<AB, AC>
. delta_z is the threshold for the valid depth valid. z > delta_z is valid. I didn't do many ablation studies to compare different values for these hyperparameters. I just want to make the sampled points are far from each other instead of locating in a local region.
from vnl_monocular_depth_prediction.
Thank you very much for your quick reply.
- So this means that the variables gt_depth and pred_depth are assumed to be in the range 0-1, right? And this, in turn, means that the variables delta_z, delta_diff_x/y/z are also in this space and if I were to use this loss in the metric space e.g. let's say I assume that gt_depth and pred_depth are in the range 0-10 meters, I would want to multiply delta_z, delta_diff_x/y/z with 10, right?
- So to confirm, according to the paper, you constrain the L2 norm between sampled points to be at least 0.6 m, but in the code you instead check that along each axis the distance is larger than delta_diff_x/y/z? Just as a sanity check: you use delta_diff_x/y/z = 0.005. If we transform this hyperparameter into the metric space 0-10m according to the reasoning in "1.", we get delta_diff_x/y/z = 0.05 m. This value does not reflect the theta= 0.6 m that is reported in the paper and 0.05 m seem like a very low number to me. Could you perhaps educate me on why you select such a low number for delta_diff_x/y/z? Also, you say delta_cos is the angle restriction of cos<AB, AC> i.e. cos<AB, AC> needs to be less than 0.867 = cos(30 degrees), but more than -0.867 = cos(150 degrees). So alpha = 150 degrees in the code, correct?
Again, thanks for your kind reply!
Cheers,
Erik
from vnl_monocular_depth_prediction.
Hi YvanYin,
I just wanted to send you a reminder here, in case my previous message got lost. Take your time though, no rush.
Best,
Erik
from vnl_monocular_depth_prediction.
Hi
- In the training, the gt_depth is normalized to 0-1. If the gt_depth is in the 0-10m range, you have to adjust delta_z, delta_diif_x/y/z.
- In our naive implementation, we set the distance to 0.6m. In the released code, we set the delta_diiff_x/y/z to make sampled points far away from each other. You can also set the distance between them, but these two methods are the same. We didn't do the ablation study to compare them. About the alpha, the angle between <ab, ac> is [30, 150].
from vnl_monocular_depth_prediction.
Related Issues (20)
- Performance issue HOT 2
- Error while loading the model HOT 1
- How makew
- How make inference on single image? HOT 3
- Only can train 1 epoch? HOT 3
- Setting for training in ablation study HOT 1
- Some questions about surface normal estimation and robutness test HOT 3
- Might it be a small false figure reference of the paper uploaded on Arxiv? HOT 1
- how can I train with NYUD-V2 dataset HOT 1
- About the Camera Parameters HOT 2
- How can I generate the dense ground truth depth maps in KITTI? HOT 6
- How to generate a point cloud map? HOT 1
- Error when running train_kitti_metric.py HOT 1
- pretaind resnext101_32x4d.pth HOT 2
- abs_rel value
- yaml_cfg load error HOT 1
- Could you please provide the pretrain model of moblinenetv2? HOT 1
- The test_any_image file cannot correct output img and the test_nyu file output very bad quality image! HOT 2
- Questions about datasets
- How to understand the concept of convert depth to Point Cloud
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 vnl_monocular_depth_prediction.