Junpeng Jing

Thanks for your valuable work! I would like to know that whether the CNS module is used in the image version model? How to embed this module in the code?...

Hi, I trained the model using the given command on sceneflow dataset on 1 A6000. I found the GPU memory cost is about 39G. Just a double-check with you: is...

Hi, very interesting work! Is it possible to access the "662 HDR images obtained from Poly Haven" ?

ConfiguringInfinigen Setting Questions

14

Hi, I want to generate a large scale of diversified stereo videos on separate A100(80GB) machines. My command is currently as follows on: ``` python -m infinigen.datagen.manage_jobs --output_folder outputs/my_videos --num_scenes...

Error: Failed to create CUDA context

4

I am trying to install infinigen on a cluster. I follow the command to install it. Since the `nvcc `location is not in `nvcc_location="/usr/local/cuda/bin/nvcc"`, if I simply run `make terrain`,...

During compositing, the process is killed during this error attached as follows. [67594677489_0_log.err.txt](https://github.com/princeton-vl/infinigen/files/15247589/67594677489_0_log.err.txt) [67594677489_0_log.out.txt](https://github.com/princeton-vl/infinigen/files/15247591/67594677489_0_log.out.txt) It seems wired since for `./frames_0_0_0209_0/` there should be frames from 209~216, but it says 'No...

Hi, very interesting work! As the title says, I wonder how can I use this model to inpaint an image with holes without a text prompt.

Fluid Installiation error

1

I am trying to install fluid following: `bash scripts/install/compile_flip_fluids.sh` but: ``` FLIP Fluids addon successfully built and compiled to: ./infinigen Installing Flip Fluids into ./anaconda3/envs/infinigen/lib/python3.10/site-packages/bpy/3.6/scripts/addons Error: Not freed memory blocks:...

Hi, I am trying to use Infinigen Nature to generate images. I see the ground truth depth could be a very large range, for example, Min depth: 4.4815592765808105, Max depth:...

Hi, very interesting work! I also have a question related to temporal loss (Eq.4 in the main paper): the predicted disparity D and RGB images are (0~255) or normalized to...