Lots of noise in output ply in tnt dataset

[CC9310]

Thanks for the author's great work.
Following the tnt test instruction, Lots of noise in the output ply

bash:
CUDA_VISIBLE_DEVICES=0 python test.py --dataset tt --batch_size 1 --testpath /data/tankandtemples/intermediate/
--testlist ./lists/tanksandtemples/intermediate.txt
--resume "/home/methods/MVSFormer/pretrained_weights/MVSFormer/best.pth"
--outdir /data4/trained_models/MVSFormer_tnt_nview10/
--interval_scale 1.0 --num_view 10 --numdepth 256 --max_h 1088 --max_w 1920
--filter_method dpcd --prob_threshold 0.5,0.5,0.5,0.5
--use_short_range --combine_conf --tmps 5.0,5.0,5.0,1.0
Do the author has any idea to solve the problem?

[ewrfcas]

Hi, we recommend using MVSFormer-blended to evaluate Tanks and Temples.

[CC9310]

Thanks for quick reply :-). While, after using MVSFormer-Blended/best.pth with src_view 10, the recons point cloud also very noise(I didn't modify any parameter in the code).

[ewrfcas]

Sorry for the confusing code. We used --conf for T&T and --prob_threshold for DTU. I will unify them latter.

[ewrfcas]

Codes are updated.

[CC9310]

Codes are updated.

it's very kind of you :-)

[mazeyu]

Hi. I am wondering what is the final prob_threshold/conf in your setting (and possibly other setting changes?). I couldn't find good enough settings. I also asked similar questions in MVSFormer++ repo to reproduce the T&T results.