Comments (5)
Hi!
thank you for being interested in our work!
The figures in the paper were created applying the model trained on KITTI-360 on the KITTI Raw data. Your results seem to come from the KITTI Raw model.
The model trained on KITTI-360 is better at predicting geometry in occluded areas because KITTI-360 has additional fisheye cameras.
Which pretrained model did you use to obtain those results?
Best,
Felix
from behindthescenes.
Thanks for your quick response!
The test data I used is the data/KITTI-Raw/2011_09_26/2011_09_26_drive_0005_sync/image_02/data/0000000002.png
, and the model I used is out/kitti_raw/pretrained/training-checkpoint.pt
.
I just tried to use the KITTI-360 model to apply the same image, and obtained the results like this:
They seem much better, but still have some differences.
from behindthescenes.
Hi!
It looks like the profile you generated covers a much bigger area. You can try to reduce the size to obtain the same results as in the paper.
Best,
Felix
from behindthescenes.
I see, I just used the default settings of your codes that generating 256x256 profile images with distances between 3 and 21. It seems the profiles in your paper are closer.
BTW, I am curious about the depth processing details. When I try to convert the depth map to point cloud, I found that the converted point cloud is so strange, especially for the upper region (maybe the sky region in the image). I found the reasons may be that you predict the depth for every pixel in the images with the depth constraints that z_near=3
and z_far=80
.
Thus, the depth of the sky regions is not correct.
After reading the codes more carefully, I found that you set hard_alpha_cap=1
, and that you set the farthest alphas = 1:
if self.hard_alpha_cap:
alphas[:, -1] = 1
It seems that this part would have effects on the training process, but I am not very sure.
So could you help me understand this phenomenon and are there any solutions to filter the depth for the sky regions?
from behindthescenes.
Setting this hard alpha cap makes training more stable. Otherwise, the network could predict zero density along the entire ray (maybe because this pixel is occluded in all other images -> no matching color -> reduce color on all samples along the ray).
This would cause numerical problems and is prevented by this measure.
When generating pointclouds: The depth maps are only a 2D visualization of the predicted density field. I would advice so sample random points from the frustum and then keeping / discarding them based on the predicted density at that point. This allows you to also obtain a meaningful pointcloud in occluded areas.
Best,
Felix
from behindthescenes.
Related Issues (20)
- question about visualizing ground truth depth HOT 5
- Is the result of this method on KITTI-Raw based on stereo cameras? HOT 3
- Question about of generate novel view animations HOT 1
- Please add license
- Will the evaluation code be released? HOT 1
- Occupancy visualization code
- Missing some files in KITTI-RAW Poses in datasets/kitti_raw/orb-slam_poses. HOT 4
- question about change the rotation to get the novel view in image custome HOT 1
- These files are not in the link mentioned by you. HOT 1
- Question about the log file HOT 4
- Experiment settings of other works mentioned in the paper HOT 2
- Some details I feel confused about HOT 3
- Train on KITTI-360 with fisheye HOT 2
- details with the keyParam ray_batch_size: 4096 HOT 2
- FisheyeToPinholeSampler HOT 2
- Does larger MLP affects the final results? HOT 1
- Inferior scores of both provided models and trained models HOT 1
- Wrong depth projection of kitti360 dataset
- Some problem about this architecture
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 behindthescenes.