chenk

A question about the event_map.

2

Here is the code source: import os import torch import h5py import numpy as np hdf5_name = r"D:\Code\CV\Deblurring\E-CIR\data\REDS\train_0.hdf5" data = h5py.File(hdf5_name, 'r') idx = 0 event_map = data['event_map'][idx] print(event_map.max()) When...

Some questions a about the CurveIntegrator code.

4

integral = 2 * coeffs[:, 1] / 3 for i in range(3, n_deg, 2): integral = integral + 2 * coeffs[:, i] / (i + 2) baseline = (2 *...

EDI dataset ?

2

Hello chensong1995: Thanks for your great work. Could you please provide the EDI dataset as REDS? Thanks a lot.

The rendered img has a large area of blank ?

2

 I adjusted the white background of the Lego to black during training, and encountered this issue in the training process. What could be the possible cause? (Here, I commented...

The result is low ?

1

Hi @zwx8981 @guspan-tanadi , i use the following code to test the LIQE metric, though the img is sharp, the liqe result seems relatively low, can you be kindly explain...

BAD-Gaussians's performance on the nerf 360 dataset.

7

Hi @LingzheZhao , thanks for your great work. While applying the BAD-Gaussian on the 360 scene like lego, I encounter the following problems and I am looking for your help....

Share enviroments working.

1

certifi 2024.8.30 charset-normalizer 3.3.2 contourpy 1.3.0 cycler 0.12.1 fonttools 4.53.1 idna 3.8 importlib_resources 6.4.4 kiwisolver 1.4.7 matplotlib 3.9.2 numpy 1.26.4 onnx 1.12.0 opencv-python 4.10.0.84 packaging 24.1 pandas 1.2.0 pillow 10.4.0...

Scene collapse and gpu memory increases after 3000 steps.

3

Hi @LingzheZhao, Thank you for your contributions to the BAD-Gaussian and your dedication to open-source development. I've been working on extending BAD-Gaussian for a new project, and I've encountered an...