magicleap/SuperPointPretrainedNetwork
PyTorch pre-trained model for real-time interest point detection, description, and sparse tracking (https://arxiv.org/abs/1712.07629)
PythonNOASSERTION
Issues
- 2
Binary descriptor
#23 opened by ceccocats - 0
Matching Score Metric - Hard to understand
#31 opened by shreyasr-upenn - 0
Code Source
#30 opened by CoderYangQi - 4
time cost of superpoint feature extraction
#9 opened by Jemmagu - 0
- 2
How to infer batch images at one time?
#28 opened by PapaMadeleine2022 - 2
Improvising the speed
#18 opened by Zumbalamambo - 1
About BatchNorm
#21 opened by litingsjj - 1
Onnx Inference
#19 opened by Zumbalamambo - 0
illumination change problem
#27 opened by LSK0821 - 0
Any other training data except CoCo?
#26 opened by xuyongzhi - 0
About pixel shuffle
#24 opened by P66094125 - 1
Rubustness against Rotation
#22 opened by adamas-v - 1
train custum superpoint or superglue
#15 opened by roboticsai - 0
Application of NMS
#20 opened by jeethesh-pai - 2
Custom Point Tracking
#17 opened by rnag5076 - 0
how to create .pt file?
#16 opened by Y-pandaman - 7
wrong keypoint coordinates
#12 opened by christian-rauch - 1
demo wrong
#13 opened by laisimiao - 1
PyTorch 1.4+ and grid_sample behavior
#10 opened by mihaidusmanu - 1
Why the size of descriptor is 256 float ?
#11 opened by lijianglong2018 - 1
Results on rotated images
#7 opened by trungpham2606 - 0
Interest Point Detector Loss
#8 opened by PatrickRowsomeMovidius - 1
MagicPoint
#6 opened by thomasstats - 1
- 1
How to create the .pth file?
#4 opened by chaiein - 1
the experiment between SuperPoint and ORB
#3 opened by cs-heibao - 2
repeatability on HPatches Dataset
#2 opened by mfaisal59 - 1
Missing two dashes from line 581 in the first argument of the add_argument() method
#1 opened by justfortheNSFW