Low Weng Fei

icon indicating a website link wengflow.github.io

icon location Singapore icon location 3D Vision. Robotics. Personal account.

Results 4 issues of Low Weng Fei

No concatenation of chunks of `extras` in `render_image_with_propnet()`

Shouldn't chunks of `extras` be concatenated prior output [here in `render_image_with_propnet()`](https://github.com/KAIR-BAIR/nerfacc/blob/433130618da036d64581e07dc1bf5520bd213129/examples/utils.py#L234C10-L234C10), so that it reflects the entire batch during evaluation?

ShapeNet Dataset

In Section 4 (Data) of the manuscript, you mentioned that the training and testing splits used are in accordance to 3D-R2N2. However upon inspection of the [pre-processed point cloud samples...

Difference between sampled_faces.npy and pointcloud.npz

Hi, I would like to ask what is the difference between the two files. From what I know, `pointcloud.npz` (as well as `model.binvox`, `points.npz` and `img_choy2016`) was originally from the...

Calculation of μ_E & μ_G

https://github.com/bednarikjan/differential_surface_representation/blob/44b19b8ea0a6579cf6531cd21ed6104d33f43214/model.py#L223-L242 Given that each batch contains `B` different instances of shapes, shouldn't `muE` & `muG` be computed separately for each instance, instead of over the entire batch?