Lei Li

Thank you for your interest in our work! I have uploaded the TnT dataset to Google Drive, and you can access it [here](https://drive.google.com/file/d/1TB2-3cUC-5BtKIeYsICBmHv-YlwBUr9n/view?usp=sharing). As mentioned in our Limitations part, our...

For scenes with good 3D meshes, like Replica, we render them into 2D images using the target camera extrinsics and intrinsics, similar to the approach in [this script](https://github.com/autonomousvision/monosdf/blob/main/render/render_tntvideos_open3d.py). For our...

Thanks for your question. Our method takes 2d edge maps as inputs and outputs parameterized representations of 3d lines and curves (using endpoint coordinates and Bézier curves, respectively), rather than...

Thanks for your good questions! 1. As mentioned in [that issue](https://github.com/yunfan1202/NEF_code/issues/1#issuecomment-1512993269), they scale and shift the real CAD models before rendering images. This means the images in the ABC_NEF dataset...

We have updated the dataset and evaluation code. You can check them.

Hey, for your first question, the CAD models are scaled by dividing each axis by the length of the largest side of the bounding box, resulting in a range within...