Comments (5)
Hi @aiyb1314 , I have implemented a Differential Gaussian Rasterization with forward depth pass diff-gaussian-rasterization-extentions modified to Scaffold-GS. This is an independent repo that has the same contents with my another repo folked from official diff-gaussian-rasterization.
The only change you need to make is to include depth in the return values of gaussian_renderer/__init__.py
:
rendered_image, radii, depth = rasterizer(
means3D=xyz,
means2D=screenspace_points,
shs=None,
colors_precomp=color,
opacities=opacity,
scales=scaling,
rotations=rot,
cov3D_precomp=None)
I did not include depth backward pass in that branch. It just outputs the depth. Feel free to use it.
from scaffold-gs.
Hi, two ways can generate the depth map:
- Override the
color
withdistance from xyz to camera_center
and do rasterization:
xyz_dist = torch.norm(xyz - viewpoint_camera.camera_center, dim=-1, keepdims=True)
color = xyz_dist.repeat([1, 3])
- Modify the CUDA rasterization according to https://github.com/graphdeco-inria/diff-gaussian-rasterization/pull/5/files
from scaffold-gs.
Hi, two ways can generate the depth map:
- Override the
color
withdistance from xyz to camera_center
and do rasterization:xyz_dist = torch.norm(xyz - viewpoint_camera.camera_center, dim=-1, keepdims=True) color = xyz_dist.repeat([1, 3])
- Modify the CUDA rasterization according to https://github.com/graphdeco-inria/diff-gaussian-rasterization/pull/5/files
I tried both methods mentioned above. The middle image corresponds to method 1, and the right image corresponds to method 2. These two are quite similar. However, the image on the left is obtained from a monocular depth model, and compared to that, neither of these methods produces correct depth maps. Here, I used cv2.COLORMAP_JET for the color space of depth mapping. Could you give me some guidance? Thanks
from scaffold-gs.
'blue' denotes 'far' in the right two images, but denotes 'near' in the left image. Are there some misaligned rules?
from scaffold-gs.
'blue' denotes 'far' in the right two images, but denotes 'near' in the left image. Are there some misaligned rules?
Thanks, I got it. The depth estimated by midas(the pretrained model I use) is the inverse depth maps
from scaffold-gs.
Related Issues (20)
- How to initialization with a random point cloud in my own datasets? HOT 5
- How did you configure your test set? HOT 2
- ply issues HOT 6
- error about the prebuild viewer on window HOT 10
- Why the training effect is good on my own data, but the testing effect is poor? HOT 1
- filled install diff-gaussian-rasterization HOT 1
- error about building SIBR in the project HOT 4
- can't see the generated result HOT 1
- error about SIBR_viewer HOT 7
- question about appearance embedding HOT 4
- Train Error ! missing 2 arguments: 'kernel_size' and 'subpixel_offset' HOT 1
- Training on 4K resolution HOT 2
- Question for get the size HOT 3
- The downloaded viewer folder does not contain a CMakeLists.txt file. HOT 1
- Wrong in saving for checkpoint HOT 1
- How to view ply in supersplat
- Testing accuracy gap HOT 2
- train without mlp HOT 3
- SIBR can't render ellipsoids from the floating menu HOT 2
- self.use_feat_bank's impact on the results HOT 1
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 scaffold-gs.