RoMa

RoMa copied to clipboard

How to wrap image on another image based on current code base

1

hi-zhangjie

Failure to generate 3D reconstruction with unknown pose of the cameras

1

Hi Roma contributors, I find RoMa model works extremely well on my dataset, as evidenced by the graphs I have drawn according to the points RoMa matched together. Yet it...

royw99

jimazeyu

Value of `coarse_res` and `upsample_res` for ScanNet

3

Hi @Parskatt , I am trying to run an evaluation of `roma_indoor` on ScanNet, like what you have used for `roma_outdoor` in `RoMa/experiments/eval_roma_outdoor.py`. Could you please tell me what values...

justachetan

The Difference Between "forward_symmetric" and "forward"

4

Hello, great job! I have a question to ask. What is the difference between "forward_symmetric" and "forward"? Looking forward to your reply.

fighterzzzh

Pairing Of Any Custom Points

3

You guys are doing a great job, I noticed you said you will support pairing of any custom points, when can I get a demo out please!

cxb1998

Finding matches with arbitrary query points

10

Hi @Parskatt , Any ETA on when the demo for matching arbitrary keypoints will be released? The README says that it is possible and the demo will be released soon....

justachetan

Small fix for avoiding re-reading an image path when you already have it.

dgcnz

RuntimeError: "LayerNormKernelImpl" not implemented for 'Half

4

``` return super().forward(x_or_x_list) File "/Users/rkothari/Documents/Projects/compalg_horizon/src/extern/RoMa/roma/models/transformer/layers/block.py", line 105, in forward x = x + attn_residual_func(x) File "/Users/rkothari/Documents/Projects/compalg_horizon/src/extern/RoMa/roma/models/transformer/layers/block.py", line 84, in attn_residual_func return self.ls1(self.attn(self.norm1(x))) File "/Users/rkothari/anaconda3/envs/horizon/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args,...

RSKothari

small model backbone

4

Hi, I've modified the code to load a DinoV2 small model, but i realized that the `embed_dim` of the vit_small model ``` def vit_small(patch_size=16, **kwargs): model = DinoVisionTransformer( patch_size=patch_size, embed_dim=384,...

gc625-kodifly