Wooqy

Hi Zhouky1, Thanks for your interest in our paper. I get the label mapping file by calculating all instances from the current scene. You can refer to [here](https://github.com/QianyiWu/objsdf/blob/main/code/datasets/scannet_label.py) for some...

Hi Sorry for the late reply. It might be the insufficient shared memory when you start load the training dataset. You can try to add ```--shm-size 16G``` or even larger...

Hi, I am sorry I didn't save the checkpoint for each scene. If you need the reconstructed mesh, you can refer to [here](https://github.com/QianyiWu/objectsdf_plus/blob/main/scripts/download_meshes.sh).

You might refer to this [script](https://github.com/QianyiWu/objectsdf_plus/blob/main/preprocess/scannet_to_objsdfpp.py). The scan ID list is given at [here](https://github.com/QianyiWu/objectsdf_plus/blob/98e84ebc9f6ca68d711fdedb6e9f8a279c79bc98/preprocess/scannet_to_objsdfpp.py#L86C5-L86C5). Remember to modify the [path to the ScanNet CSV file](https://github.com/QianyiWu/objectsdf_plus/blob/98e84ebc9f6ca68d711fdedb6e9f8a279c79bc98/preprocess/scannet_to_objsdfpp.py#L91C5-L91C5) on your side.

I have updated the training code as in [here](https://github.com/QianyiWu/objectsdf_plus/blob/a4058834990a9730564b22748453cd8e0047380f/code/training/objectsdfplus_train.py#L96). You don't need to run 2000 epochs on ObjectSDF++. In the original experiments, we set the total iteration as 200k and...

You can refer to [here](https://github.com/QianyiWu/objectsdf_plus/blob/main/scripts/download_meshes.sh).

Hi, this result looks strange. I checked my previous notes and found the reconstruction quality of scene_1 usually wouldn't meet such a low ACC value. But the environment would be...

The basic idea of editing objects rigidly by ObjectSDF is similar to the ObjectNeRF (Eqn.(5) in https://arxiv.org/pdf/2109.01847.pdf). Editing can be treated as a compositional rendering of density and color from...

Hi, Thanks for you interest in our work. I don't have any idea of the compile bug from this log. Would you mind providing more information of the log and...

Hi, would you mind providing more information about your OS, GPU and your own CUDA version?