search

RaymondJiangkw / COGS

[SIGGRAPH'24] A Construct-Optimize Approach to Sparse View Synthesis without Camera Pose
https://raymondjiangkw.github.io/cogs.github.io/
Other
59 stars 6 forks source link

The render result are completely black images #5

Closed murmurelo111 closed 2 months ago

murmurelo111 commented 2 months ago

Sorry to bother you, but I ran the following commands and got black images as the result:

python train.py -s Tanks/Museum --eval --num_images 6

python eval.py -m "output/2024-07-02_00-46-53_Museum_6/" --load_iteration 9000

python render.py -m "output/2024-07-02_00-46-53_Museum_6/" -s "COGS/Tanks/Museum/"

Could you please help me check what might be the problem? Thank you very much! image

murmurelo111 commented 2 months ago 
python train.py -s "demo" --eval --num_images 2

python eval.py -m "COGS/output/2024-07-02_10-20-26_demo_2/"  --load_iteration 9000

python render.py -m "COGS/output/2024-07-02_10-20-26_demo_2/" -s "demo"

Even with the provided demo dataset, the result is still a completely black image.

RaymondJiangkw commented 2 months ago

Sure. I will look at it. Black images are indeed weird… I haven’t experienced that in my own experiments. Will check it soon.

RaymondJiangkw commented 2 months ago

Hi, sorry for the problem. Seems that the problem arises after I specify the newest glm in the rasterizer. If you check, you will see that the official gaussian splatting rasterizer also gives complete black images, and if you use convert_SHs_to_color = True, the images will show out.

The solution is to replace one line in the forward.cu for both rasterizers, which I have committed the changes. Please pull the changes and reinstall both rasterizers to see whether the problem still exists. Hopefully, there aren't additional bugs after specifying the newest glm...

If you encounter other problems, feel free to let me know!

murmurelo111 commented 2 months ago

Thank you for your response! After pulling the changes, I got the correct results.