InstantMesh
InstantMesh copied to clipboard
InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
Thanks for your great job!!! I really got good mesh with your method. However now I have difficulty in getting mesh with resonable direction with image token with unkown camera...
Why did I render the resulting mesh, get 30 images to use as a training set for training Gaussians, train for 3w iterations, but the results are not good? Is...
Thank you for your great work, recently I want to test the InstantNeRF training code, but I encounter a problem. I loaded the weights of InstantNeRF and trained the model...
Hello developer, I have a problem now. When I got to 1000 steps, ValueError: Expected both input arguments to be normalized tensors with shape [N, 3, H, W]. Got input...
Hi, First of all, thank you for your incredible work on this project! I am working on training the LRM model, but I am having some trouble with the dataset...
I needed onnxruntime to run this. Alternatively if it doesn't belong in requirements perhaps the instructions can be updated to include `pip install onnxruntime`
`(instantmesh) kush@Kushal:~/miniconda3/envs/instantmesh$ python app.py Traceback (most recent call last): File "/home/kush/miniconda3/envs/instantmesh/app.py", line 12, in from diffusers import DiffusionPipeline, EulerAncestralDiscreteScheduler File "/home/kush/miniconda3/envs/instantmesh/lib/python3.10/site-packages/diffusers/__init__.py", line 3, in from .configuration_utils import ConfigMixin File "/home/kush/miniconda3/envs/instantmesh/lib/python3.10/site-packages/diffusers/configuration_utils.py",...
Error message provided: ``` $ winpty docker run -it -p 43839:43839 --platform=linux/amd64 --gpus all -v $MODEL_DIR:/workspace/instantmesh/models instantmesh ========== == CUDA == ========== CUDA Version 12.4.1 Container image Copyright (c) 2016-2023,...
Hi, thanks for your great work! I wonder is there any method to reconstruct the target with its real-world size If I can input the camera parameters and depth information...
I saw the message, "Note: The downloaded .obj model will be flipped. Export .glb instead or manually flip it before usage." Could you explain why it happens fundamentally?