KevinCain
KevinCain
In 'model.py', the tensor shape is set to 1/4 of the declared maximum height and width, e.g.: `feature_shape = [FLAGS.batch_size, FLAGS.max_h/4, FLAGS.max_w/4, 32]` When we change this, how can we...
Since all DTU scenes share nearly identical intrinsics and the robotic camera arm targeted the same camera poses in each scene yielding the nearly identical extrinsics, does IGEV-MVS training on...
Would you advise extending IGEV-Stereo for the special case of a trifocal tensor estabishing the geometric projection between three views, or would IGEV-MVS be a more natural choice? In the...
In what file is TEST_DATA_FOLDER set? Similarly, could you please clarify what is intended by "Set MODEL_FOLDER to ckpt and model_ckpt_index to checkpoint_list."? That is, what files should be modified?
I'd like to try inference with a model trained on metric data. I've exported the [DA NYU indoor pretrained model](https://huggingface.co/spaces/LiheYoung/Depth-Anything/blob/main/checkpoints_metric_depth/depth_anything_metric_depth_indoor.pt) trained on metric indoor data to ONNX and run inference,...
I added [fisheye calibration to my fork of SimpleStereo (master)](https://github.com/KevinCain/SimpleStereo/tree/master/simplestereo), following notes [here](https://github.com/decadenza/DirectStereoRectification/issues/4) and [also here](https://github.com/decadenza/DirectStereoRectification/issues/9). In 'chessboardStereo' there are two new calling parameters which allow you to call the...