Yehui Shen

Great work, but after reading your paper. I have a question: how is the aggregation of local features fi,j with vi,j achieved to compute alpha values and color c? While...

A quesiton about load_state_dict

5

pretrained_weights_path = 'lightvit_tiny_78.7.ckpt' pretrained_state_dict = torch.load(pretrained_weights_path) lightvit = lightvit_tiny(pretrained=False) lightvit.load_state_dict(pretrained_state_dict) I use about code to use pretrained lightvit_tiny model, but it's useless, how can i pretrained lightvit_tiny model correctly?

Can I use the provided pre-trained model to track objects in a video recorded by myself? Or do I need to retrain the model based on the content of the...

How to get setup_world.json for a new dataset?

1

Dear author, I want to train nerf-h using my dataset. However, it only have transformer.json, how can i get setup_world.json for it?

Thank you for the open source, but the width and height of the trevi dataset images in the dataset you provided are not fixed, can you please provide a version...

Thanks for your dataset, but for my work (localization) I need to know the distance between two camera frames in the world coordinate system, how can I calculate the distance...

Code of construction of NuScenes-QA dataset

1

Thank you for your great work! Will the code to make the NuScenes-QA dataset be made public?