Comments (6)
Hi, yes, the code could be more easy to understand, sorry about that. In order to run the full model, you basically need to fill in the dictionary of values specified here:
mannequinchallenge/loaders/image_folder.py
Line 180 in 3448d9d
these correspond to the various buffers mentioned in loss definitions in the paper. You don't need to create your own HDF5s etc. as long as you can create a dictionary including those buffers. Hope that helps.
from mannequinchallenge.
How to I get gt_depth, human_mask, flow, keypoints_img in your format on my own data so that I can inference your full model?
from mannequinchallenge.
Ok, I realised that providing full pipeline for inferring full model on any data is almost impossible for you.
Can you provide inference result of your full model for MC dataset?
from mannequinchallenge.
Unfortunately, we don't have permission to share image-like-results (e.g., depth buffers) from the MC dataset. Sorry about that.
For inference, you shouldn't need the gt_depth, and the model with keypoints input performs only marginally better than the model without, so the only things you really need are flow and the human mask.
from mannequinchallenge.
Thanks for your indications above. So I looked at the load_tum_hdf5 function. I have a few questions.
A) the code reads 11 objects:
- img_1: is it a simple 24bits RGB numpy matrix of the image we are trying to infer?
- gt_depth: I can ignore it since I just want to infer, but can I just comment this piece of code and all downstream reference to the treatment of this object or do I need to fake a dummy input?
- lr_error: what is that? Can I ignore the same way as gt_depth? It looks like it is used to comput the confidence map which seems a key input to your model no?
- human_mask: I assume this is a binary mask of the same size as img_1, right? What is the format expected, 0.0=transparent and 1.0 equals opaque, i.e. the mask shape? (Rgb black/white image I assume?)
- angle_prior: what is that? Is it the second image? It looks like it is used to comput the confidence map which seems a key input to your model no?
- pp_depth: what is that? It looks like it is used to comput the confidence map which seems a key input to your model no?
- flow: the output of FlowNet2 I assume but is it a 24bits rgb image or is it the raw flow data structure of the .flo object of FlowNet? Does it need to have the exact same height × width size as img_1 ?
- T_1_G: what is that? It looks like it is used to comput the confidence map which seems a key input to your model no?
- T_2_G: same as for T_1_G
- intrinsic: same as for T_1_G
- keypoints_img: can I just input a keypoint image from OpenPose for instance? Do the points need to be single pixels? Is there a particular colouring scheme for each point which needs to be followed or I can just pass the colouring of OpenPose?
Thanks a lot for your guidance on this.
from mannequinchallenge.
Hi, I am the first author of this paper.
img_1: should be RGB image between 0 and 1
lr_error: is the left-right consistency error corresponding to C_lr in Eq.5 of supplementary material: http://www.cs.cornell.edu/~zl548/images/mannequin_depth_cvpr2019_supp_doc.pdf
human_mask: is the binary mask, where 1 indicates human, 0 indicates background.
angle_prior: is C_pa in Eq.5 of supplementary material.
pp_depth: depth from motion parallax using P+P representation in Eq. 4 of supplementary material.
T_1_G: this is the 4X4 homogenous transformation matrix from global to reference image described in the paper.
T_2_G: this is the 4X4 homogenous transformation matrix from global to source image in the paper.
intrinsic: 3X3 intrinsic matrix
keypoints_img: You can use any keypoint detection algorithm you want but you have to normalize their index based on MaskRCNN. In particular, what you need to do is from https://github.com/roytseng-tw/Detectron.pytorch/blob/master/lib/utils/vis.py, you can see line 198-199:
i1 = kp_lines[l][0]
i2 = kp_lines[l][1],
you need to normalize it by using following code:
final_i1_value = (i1 + 1.0)/18.0
final_i2_value = (i2 + 1.0)/18.0
Please send me email ([email protected]) for more questions since I seldom reply in Github.
from mannequinchallenge.
Related Issues (20)
- typo in instruction HOT 1
- Images Downscaled HOT 1
- CPU Support HOT 3
- Camera pose and intrinsics estimation at inference time HOT 2
- Colmap Patch matching settings HOT 2
- Code to generate depth maps from Youtube videos HOT 1
- How to generate HDF5 data?
- RuntimeError: unexpected EOF, expected 109330 more bytes. The file might be corrupted.
- Clarifications on training pipeline HOT 2
- Running on custom videos HOT 3
- thank you for your work~when do you offer the training code? HOT 12
- Could I get more detail about object insertion from depth-based visual effect part?
- training data
- will you share the MannequinChallenge Dataset? HOT 2
- Would you like to share the initial depth estimation methods? HOT 3
- Some of the video in the datasets become unavailable HOT 5
- Inference Performance HOT 2
- How to get the camera intrinsic parameters from the original YouTube wild videos? HOT 1
- Output depth data format HOT 5
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 mannequinchallenge.