Comments (2)
@yyeboah, thank you for your interest in our work!
The use of the VGG loss, as well as other perceptual losses, was motivated as a replacement of L1 which encourages the predicted image to be perceptually close to the ground truth image. In contrast to VGG, L1 only enables the convergence of the low-frequency component, which results in a blurry image. We've also tried a sum of VGG and L1 but have not noticed any apparent change. Perhaps, the quality can be increased if the perceptual loss is combined with other losses, such as adversarial, as suggested in many related works. Though, the use of GAN-based loss can be tricky, as the discriminator must see a large enough dataset of real images to avoid overfitting. We would appreciate if the community enhances our results by introducing loss functions that result in sharper renderings and fewer artifacts.
In this regard, the concurrent work of Huang et al. 2020 investigates the application of the adversarial loss for a highly related task of texture mapping (fitting a color texture for a mesh reconstructed from the set of photographs). In fact, VGG baseline from that work is similar to our Texture+Mesh baseline in the paper text (though, their VGG results suffer from strange out-of-range artefacts which we don't have).
from npbg.
@seva100 , Your prompt and detailed explanation is very much appreciated.
Indeed the L1 and its counterpart L2 loss have both been consistently proven to be ill-suited for image generation tasks, specifically w.r.t. capturing and encouraging the high-frequency components. I also agree that a GAN-style loss, as you have suggested may be better suited for encouraging some additional crispness in the renderings. This claim has been further backed by the results reported by Huang et al. 2020.
I'll be closing this issue for now, with the hope of resuming discussions at a later point in time when I've had some luck with figuring out a suitable discriminator.
from npbg.
Related Issues (20)
- Questions about remote rendering HOT 1
- Something wrong about the docker image? HOT 1
- How to train from scratch or fine-tune with multiply scenes datasets? HOT 12
- How to generate data on server ? HOT 1
- Rendering problem HOT 2
- The viewer's results were not as good as the training HOT 4
- Rotate novel view HOT 1
- How can I get the 3-channel (RGB) picture of point-descriptors rasterizer result? HOT 3
- Generation HOT 2
- How to set num_sample HOT 2
- Viewer renders only a triangular half of the texture HOT 2
- Headless render on remote servers without Xorg? HOT 1
- Eval mode=True during training HOT 5
- How to render one of the fitted scenes on Ubuntu 22.04 LTS: A comprehensive guide. HOT 6
- When running view.py, how to limit the range of movement (or zoom) HOT 1
- Multi-GPU support for training? HOT 2
- question about camera.xml
- How to render the output from viewer as video?
- There was a problem with scene stitching
- Question about extrinsics
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 npbg.