tcourat
tcourat
Hi, It would be nice to compare your results with DMD ( [Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Model](https://diffusion-vision.github.io/dmd/) ) which also claim to be SOTA for zero...
Has somebody tried to see if the scaling and translation parameters (related to the affine invariant depth) are stable accross a video, at least if there is no notable change...
I'd like to finetune the model pretrained on MegaDepht (outdoor). I somehow managed to obtain depth maps for my custom data. However they are true depth whereas megadepth uses relative...
Hi, I'd like to know if it is expected behavior that the example code in the notebook does not work if we give an input image size which is not...
Hi, First of all thanks for your job. I noticed that according to the code, the patch_size from DINOv2 is expected to be 16 : https://github.com/mhamilton723/FeatUp/blob/c04e4c19945ce3e98a5488be948c7cc1fdcdacc6/featup/featurizers/util.py#L27 However, to my knowledge,...
## 🚀 Feature Add Unimatch semi supervised framework : https://github.com/LiheYoung/UniMatch ### Motivation This seem to be a SOTA semi supervised framework in many domains. Thanks
Hi, Where can I access the DepthFormer pre-trained checkpoint ? Also, is there a convenient way to use torchhub to load it like for the 3 other models (Define, Zerodepth...
Hi, I was reading the last paper from "Scalable Pre-training of Large Autoregressive Image Models " ( Apple https://arxiv.org/abs/2401.08541 ) and they made the observation that the best features to...
Hi, I am doing keypoint matching with 1280x720 images, with a GTX 1080 Ti ( 11.2 GiB of memory ) and found that LightGlue is slower than LoFTR, while it's...
Would it be possible to use lightglue in order to match keypoints obtained from LoFTR (or other semi-dense/dense matchers, not only sparse) ? I know they already provided the matches...