Metric3D
Metric3D copied to clipboard
YvanYin
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
Hi, How to fine tune the metric3d on a custom dataset as I want to check the improvement in generalization of this model. For the custom dataset the following information...
Hi there, is there any way to speed up inference by increasing the batch size for larger datasets?
So far as per the suggestions in issue #78, I have provided the intrinsic values of the camera. Since the test images have no ground truth depth, I am trying...
Is there any way to convert the DINO2reg-ViT model to an ONNX model?
Hi @JUGGHM, Thank you all for your great work with MMDE. I would like to know if you have some inference time or speed data available on any GPUs or...
I wondered what camera-related parameters matter most when using the `vit` models and if there are any guidelines to set those parameters.
Hello, thanks again for the great work! Your model uses `torch.bfloat16` which is only supported by the newer GPUs. https://github.com/YvanYin/Metric3D/blob/7b5440dcbc17ef5e09805169a5f0b2d6bfe59161/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5.py#L218-L229 May I ask you to kindly support older ones by...
Hi, thanks for your great work! My in the wild rgb images were captured by camera with fx=fy=731.5, cx=cy=512, and width=height=1024. In this condition, how should I adjust the config...
