-
您好，我想請教一下，就是在訓練過程我們訊練檔的 input 是 2 張圖 (RGB圖、RGBD 深度圖)，output 為 RGBD 深度圖。
以 NYU Dataset 來講，這樣我要先轉換 mat 檔案成 RGB圖、RGBD 深度圖，然後才可以訓練嗎？還是只要拿 mat 檔案就好？
謝謝！
Hello, I would like to ask. During the training…
-
any plan for the release of weights for small and base used for metric depth (indoor & outdoor)?
-
I used the provided model for depth prediction on the NYU dataset with the SC Depth V3 model, but found that the depth range of the network output is still 0-80m as in the KITTI dataset. What went wro…
-
Friends, may I ask, can you download the parameters file trained by the author? I can't open the website here
-
Hello,
I want to reproduce the depth estimation results of NYU_depth_V2 in the paper. But I found the output depth scale is totally different from the NYU data. What post-process am I supposed to do?…
-
Hello! Could you please tell me how to scale the depth estimation if my focal length is 1101.8513?
I use the nyu pretrained model and this scaling equation:
`pred_depth_scaled = pred_depth * 518…
-
The data set I use is nyu depth v2. I encountered the same error with both depthformer（depthformer_swinl_22k_w7_nyu.py） and binsformer（binsformer_swinl_22k_w7_nyu.py）. My execution command is
pyt…
-
十分感谢作者的脚本。跑了下mat_image.py，里面img = img.rotate(270)，是把图旋转了270度，图的长宽没有变，然后上下空出来个黑边。img = img.transpose(Image.ROTATE_270)才是这种效果吧。
-
Hello! I would like to ask how the results of NYUv2 can be converted into images? And how do you train the data of NYUv2? This is clearly an image rather than a point cloud. Looking forward to your re…
-
안녕하세요. 현재 진행하고 있는 프로젝트에 `BTS model`을 적용을 해보려고 합니다.
Indoor Dataset중 TUM dataset으로 직접 Training을 시켜보려고 하는데요.
NYU V2 depth dataset과는 다르게,
TUM dataset은 `focal length = 517.30648`, `depth scale =…