NeRF-SLAM
NeRF-SLAM copied to clipboard
ToniRV
NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields. https://arxiv.org/abs/2210.13641 + Sigma-Fusion: Probabilistic Volumetric Fusion for Dense Monocular SLAM https://arxiv.org/...
I see the depth in `tsdf_fusion.py` or `nerf_fusion.py` is the `cam0_idepth_up` rather than `gt_depth`. I encountered a problem while running my own RGBD dataset. The depth map in `tsdf_fusion.py` is...
I can't find the code about using droid-slam frontend, different from the paper causing me confused.
Hi, thanks for your great work, which also includes the implementation of sigma-fusion. In the NeRF-SLAM paper, Table 1 shows a quite large difference in depth L1 metric between the...
Hi Toni, great work, I find the `ref_frame` has not been updated for evaluation. Wonder when it will be added ? Thanks
Hi, I am interested in training this model on different data (KITTI) Could you guide me, please? I can't find training script Thanks
Hi! It's a really good job, based on the project description, I'm guessing you're running this project on a desktop, so I'd like to know if it can run on...
I run the code in server with a rtx A6000 48GB.But i met a error.So i debug the code.I found when run the line in corr.py and get that error.Can...
First, thank you for sharing this awesome work. looks amazing! just trying to understand what is the output of your process - is it a point cloud? a mesh? just...
self.ctx = mujoco.MjrContext( TypeError: __init__(): incompatible constructor arguments. The following argument types are supported: 1. mujoco._render.MjrContext() 2. mujoco._render.MjrContext(arg0: mujoco._structs.MjModel, arg1: int) Invoked with: , 150 Anyone know how to fix...
