dfsfsf
dfsfsf
> It is "distillation". Have you follow https://github.com/weiyithu/LiDAR-Distillation/blob/main/docs/GETTING_STARTED.md to train the model? First, I trained the PooointPillars for waymo 64-beam, and found the best model. Then, the best model is...
> my torch version is 1.10, python 3.6, cuda 11.6, cudnn 8.6, and that's error is when run 'python setup.py bdist_wheel' for installing spconv1.2.1 It may be because your python...
> Hi, @CBY-9527 You can achieve sampling 1% of the Waymo dataset using the following code. Please specify the corresponding paths in the code: > > ```python > ori_root =...
> Dear Author, > > I have reviewed the code you provided regarding the pose evaluation section. > > MonoGS\utils\eval_utils.py： > > ``` > def eval_ate(frames, kf_ids, save_dir, iterations, final=False,...
> 你可直接改成对所有帧进行评估，我的结果是tum数据集确实是比论文里的指标差的，replica是差不多的 @CBY-9527 还有个问题就是论文用图像评价指标是优化前还是后的呢，我看优化前的指标比论文低很多，但优化后的指标比比论文里面高很多
> [@CBY-9527](https://github.com/CBY-9527) 我感觉是color_refinement后的，如果是优化之前的话，那差的实在是太多了，优化之后的话，我这边的平均数据是跟原文数据的差不多，你可以算一下平均值，你的微信号好像不对，可以给个Q号吗？ 不好意思，之前微信验证设置里面关闭了微信号添加，现在可以用微信号添加了（ycb2468）。
I have the same interest as well.
> e, what is `r_0xx.png`? in my colmap process, the generated image will be like this:  I used "bash colmap.sh data/dynerf/cook_spinach llff" to generate a point cloud, but found...