NeuralRecon icon indicating copy to clipboard operation
NeuralRecon copied to clipboard

Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral

Results 63 NeuralRecon issues
Sort by recently updated
recently updated
newest added

Hi @JiamingSuen @Burningdust21 Thanks for sharing the great work! Could you please explain the use of the transformation `"world_to_aligned_camera"` at the following two places for the Scannet dataset: - https://github.com/zju3dv/NeuralRecon/blob/cd047e2356f68f60adfb923f33572d712f64b57a/datasets/transforms.py#L64...

Hi, Why intrinsic is different for each image in the sample dataset. I assume one camera only have one intrinsic at a time. `1612099151.512330,0,1455.059570,1455.059570,956.688232,692.592407 1612099151.545653,1,1459.042847,1459.042847,955.986572,693.707703 1612099151.578977,2,1457.904785,1457.904785,956.351501,692.896729 1612099151.612300,3,1457.904785,1457.904785,956.180359,693.358337 1612099151.678947,4,1455.628662,1455.628662,956.031311,693.236450 1612099151.712270,5,1456.766602,1456.766602,956.246460,693.202209 1612099151.745594,6,1456.766602,1456.766602,956.072388,692.978027`

The fragment volume is defined as the cubic volume that encloses the view frustums (with each frustum having a max distance). Thus, this volume can change based on the specific...

Hello there! First of all, thank you for open-sourcing your work! Would you be interested in sharing your model on the [Hugging Face Hub](http://hf.co/models)? The Hub makes it easy to...

Hi, I am a big fan of this project. So I'm trying to study NeuralRecon code. I have some questions about [tranforms.py](https://github.com/zju3dv/NeuralRecon/blob/master/datasets/transforms.py) First, What is the [self.random_rotation](https://github.com/zju3dv/NeuralRecon/blob/master/datasets/transforms.py#L179) and [self.random_translation](https://github.com/zju3dv/NeuralRecon/blob/master/datasets/transforms.py#L211) becoms...

Thank you for sharing your great work. Could you please explain how we can use the pose generated by ORB_SLAM method as the input for NeuralRecon. Because as I read...

Thanks for fantastic work but it not work with ar core data set from android please give hint what we need to do achieve we have use below code for...

Thank you for the great work and for sharing the code. How should we modify the code to generate "single-layered mesh" as shown in Figure 2 in Supplementary Material? Thank...

I followed the Training on ScanNet in README. _Phase 1 (the first 0-20 epoch), training single fragments. MODEL.FUSION.FUSION_ON=False, MODEL.FUSION.FULL=False,_ the model cannot work and got the error. Traceback (most recent...

Hi, after getting the mesh, how to create AR demo like shown in your project page?