Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

R-4.5.0 #126

Open
wants to merge 25 commits into
base: master
Choose a base branch
from
Open

R-4.5.0 #126

wants to merge 25 commits into from

Conversation

OPHoperHPO
Copy link
Owner

Changelog:

  1. Removed obsolete models
  2. Fixed typos in tracer b7
  3. Added new AutoScene preprocessing method
  4. Added warning about fp16 to u2net class
  5. Updated README.
  6. Changelog
  7. Added ISNet segmentation network Support isnet.pth? (Dichotomous Image Segmentation) #119
  8. Added object classifier YOLOv4.
  9. Added AutoInterface to automatically select the best methods for images with different scene types.
    AutoInterface uses a scene classifier and an object classifier to perform full analysis on all images. At the moment, since there are not enough models for so many types of scenes, universal models are selected for some domains. In the future, when some variety of models is added, auto-selection will be rewritten for the better.
  10. Updated metrics
  11. Added CascadePSP segmentation refinement network.
    It will refine the segmentation mask before passing it to the matting network. This should provide more accurate background removal for objects and people. (Check repo from CREDITS.md for more details)
  12. Fixed trimap generator unknown area value as FBA Matting expect.
  13. Added noise filter switch (needed for smooth mask prediction on the final stage for soft scenes)
  14. Updated alpha composition algorithm

AutoScene RC-4.2.0

Description

It performs a primary analysis of the image in order to automatically select the necessary method for removing the background.
The choice is made by classifying the scene type.

Model accuracy:

Model achieves 91.3% accuracy on the validation set.

Classes info

The output can be the following types:

  • hard
  • soft
  • digital*

The hard class denotes a group of scenes to which a coarser background removal method should be applied, intended for objects with an edge without small details.
The hard class contains the following categories of objects: object, laptop, charger, pc mouse, pc, rocks, table, bed, box, sneakers, ship, wire, guitar, fork, spoon, plate, keyboard, car, bus, screwdriver, ball, door, flower, clocks, fruit , food, robot.

The soft class denotes a group of scenes to which you want to apply a soft background removal method intended for people, hair, clothes, and other similar types of objects.
The soft class contains the following categories of objects: animal, people, human, man, woman, t-shirt, hairs, hair, dog, cat, monkey, cow, medusa, clothes

The digital* class denotes a group of images with digital graphics, such as screenshots, logos, and so on.
The digital class contains the following categories of scenes: screenshot

* - Not fully supported at this moment

More details on model here:  https://huggingface.co/Carve/scene_classifier/

Architecture

image
The classifier uses DenseNet161 as the encoder and some linear layers at classifier base.

Some examples

image 1
image 1 (3)

OPHoperHPO and others added 24 commits January 3, 2023 09:22
Fixed typos in tracer b7
prepared for adding postprocessing and preprocessing
2. Added warning about fp16 to u2net class

AutoScene Description:
        Performs a primary analysis of the image in order to automatically select the necessary method for removing the background.
        The choice is made by classifying the scene type.

        The output can be the following types:
        - hard
        - soft
        - digital

        More info here:  https://huggingface.co/Carve/scene_classifier/
…erfaces.

2. Updated Russian README.md
3. Updated examples
…setup not being fully configured. Fixed models download(added scene classifier) and tests(same here).
Added AutoInterface to automatically select the best methods for images with different scene types. AutoInterface uses a scene classifier and an object classifier to perform full analysis on all images. At the moment, since there are not enough models for so many types of scenes, universal models are selected for some domains. In the future, when some variety of models is added, auto-selection will be rewritten for the better.
…ods for images with different scene types. auto uses a scene classifier and an object classifier to perform full analysis on all images. At the moment, since there are not enough models for so many types of scenes, universal models are selected for some domains. In the future, when some variety of models is added, auto-selection will be rewritten for the better.
It will refine the segmentation mask before passing it to the matting network. This should provide more accurate background removal for objects and people. (Check repo from CREDITS.md for more details)
Updated README.md
Updated Russian README.md
Optimized FBA input image size
Changelog
1.  Added ISNet segmentation network
2. Added object classifier YOLOv4.
3. Added AutoInterface to automatically select the best methods for images with different scene types.
AutoInterface uses a scene classifier and an object classifier to perform full analysis on all images. At the moment, since there are not enough models for so many types of scenes, universal models are selected for some domains. In the future, when some variety of models is added, auto-selection will be rewritten for the better.
4.  Updated metrics
5. Added CascadePSP segmentation refinement network.
It will refine the segmentation mask before passing it to the matting network. This should provide more accurate background removal for objects and people. (Check repo from CREDITS.md for more details)
6. Fixed trimap generator `unknown` area value as FBA Matting expect.  
7. Added noise filter switch (needed for smooth mask prediction on the final stage)
8. Updated alpha composition algorithm
RC-4.5.0: AutoInterface introduce
@MrFox131
Copy link

MrFox131 commented Feb 9, 2023

Fixes #119

@robinlindhout
Copy link

Hi @OPHoperHPO when will this be released? Excited for this :)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants