RenderOcc

RenderOcc copied to clipboard

Inquiry on Applying IDA to Generated Rays in NeRF-based Models

6

I hope you're doing well. I'm writing to express my appreciation for your research on NeRF and its rendering techniques, particularly the application to OCC models. Your work has inspired...

SPA-junghokim

Occ GT and prediction

1

Hi, Did you notice that the drivable surface in the prediction is a bit higher than the GT. Do you have a theory on what might be the reason. ![Screenshot...

abualhanud

Question about the pretrained checkpoint

1

Hi, thanks for your excellent job. However, I found that you adopted a pretrained checkpoint on the objection detection trained in supervised manner? Is it reasonable for a self-supervised task?

pkqbajng

Hi, when attempting to train RenderOcc using `camera_mask`, my results can only reach a maximum mIoU of $30.53$, instead of the $40-50$ reported by UniOcc. Could you please share how...

getterupper

I'm confused why I have to edit my code to run correctly.

1

I have to add the following code in renderocc.py's function 'simple_test' and 'forward_train' to run the training process without error: RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be...

Ira569

Hi, when i change nerfhead config to a smaller version, i cant get expected rendering results. Config has been modified according to #20. Could you give some suggestion or more...

yutao98

What is the IoU of RenderOcc

2

Hi there, loved your work. I was wondering what is the IoU of RenderOcc on SemanticKITTI. I noticed in your paper only mIoU is shown

haiphamcse

Thanks for your great work. But when the occupancy gt is used (use_3d_loss=True), NerfHead seems make no contributions. If I set weight_depth=1.0 and weight_semantic=1.0, the performance drops a lot. And...

drilistbox

Hi! Really cool project - wanted to suggest a slightly more fleshed out ReadMe to help new users and bump that SEO too ;) let me know if it's useful!...

luisxcosta

``` def sample_ray(ori_rays_o, ori_rays_d, step_size, scene_center, scene_radius, bg_len, world_len, bda, **render_kwargs): rays_o = (ori_rays_o - scene_center) / scene_radius # normalization rays_d = ori_rays_d / ori_rays_d.norm(dim=-1, keepdim=True) N_inner = int(2 /...

chenshi3