Parskatt/DeDoDe

Issues

• How to use the DeDoD v2-L+RoMa ?

  #36 opened a month ago by zhengshunkai
  0

• setup problems

  #35 opened a month ago by wuzelei123
  0

• question about detector and discriptor

  #34 opened a month ago by ye450450
  5

• Possible bug ?

  #33 opened 2 months ago by fratopa
  2

• Unsure how to use the S-Version

  #32 opened 3 months ago by geoeo
  3

• Could you release small/tiny/nano version of detector and descriptor?

  #30 opened 5 months ago by zhongqiu1245
  12

• DeDoDe doesn't produce absolute confidence?

  #31 opened 5 months ago by nnop
  2

• consulting

  #29 opened 5 months ago by cuffsword
  2

• No Change in Descriptor Network Training Curve after 6000 Steps

  #27 opened 8 months ago by wangerniuniu
  1

• What does the inv_temp variable mean?

  #26 opened 8 months ago by hnyll
  1

• Scores for keypoints?

  #25 opened 8 months ago by hnyll
  2

• about ‘prep_scene_info’

  #24 opened 8 months ago by wangerniuniu
  3

• about ‘prep_scene_info’

  #23 opened 8 months ago by wangerniuniu
  5

• the performance of dedode with superglue?

  #22 opened 10 months ago by hkd724
  2

• run demo_match.py ​​but don't get any matches

  #21 opened 10 months ago by GavinYang5
  20

• How to train on my data

  #20 opened 10 months ago by GavinYang5
  2

• "W" not in this function

  #19 opened 10 months ago by gersonsolaris
  4

• Any reason for dual softmax matcher for inference?

  #18 opened a year ago by ducha-aiki
  1

• Training on own data set without groundtruths

  #17 opened a year ago by Meda2997
  1

• Question about DeDoDe fine-tuning

  #16 opened a year ago by haksorus
  1

• hloc integration?

  #11 opened a year ago by catid
  5

• About the parameter in detector and match?

  #15 opened a year ago by ghoshaw
  1

• Update mega-1500 results

  #13 opened a year ago by Parskatt
  2

• Code cleanup

  #14 opened a year ago by Parskatt
  0

• Issue with samples

  #10 opened a year ago by pmoulon
  6

• Unable to Reproduce Megadepth-1500 Evaluation Results

  #12 opened a year ago by AbyssGaze
  35

• getting 0 image matching correspondences for some image pair when giving whole video as consecutive image frames

  #4 opened a year ago by Meda2997
  3

• Is there a way to finetune my own task?

  #8 opened a year ago by 52THANOS
  6

• Ablation experiments on joint and individual learning?

  #7 opened a year ago by Devoe-97
  7

• this is a error ,please help me ,thank you!

  #1 opened a year ago by LooperzZ
  3