FFB6D Can not reproduce the result of ICP(97%)

@ethnhe This is really a nice work, however, when I tried to reproduce the result of FFB6D+ICP using the ICP code from PVN3D I can not reproduce the result, can you give me a hand?

Mar 02 '22 16:03 CodeLHY

https://github.com/ethnhe/PVN3D/blob/9a5481a82af4eb89fa8e0ab10ba22b9077b4652e/pvn3d/eval_icp.py#L124 It seems that you are using the ground truth mask for ICP refinement.

Mar 03 '22 16:03 CodeLHY

No, as illustrated in A.3. Implementation: PVN3D+ICP in our paper, we use the post-processed predicted mask for the whole images, using the fill label function. https://github.com/ethnhe/PVN3D/blob/9a5481a82af4eb89fa8e0ab10ba22b9077b4652e/pvn3d/eval_icp.py#L429 This procedure is slow so we pre-process and store it in a data structure. We use CPU clusters to speed up.

Mar 03 '22 16:03 ethnhe

No, as illustrated in A.3. Implementation: PVN3D+ICP in our paper, we use the post-processed predicted mask for the whole images, using the fill label function. https://github.com/ethnhe/PVN3D/blob/9a5481a82af4eb89fa8e0ab10ba22b9077b4652e/pvn3d/eval_icp.py#L429 This procedure is slow so we pre-process and store it in a data structure. We use CPU clusters to speed up.

Thank you for your quick reply, and I really appreciate PVN3D and FFB6D, both of them are excellent and solid. Good night.

Mar 03 '22 17:03 CodeLHY

Hi @ethnhe , I followed your instruction but still get a lower result, so I reopened this issue. Average of all object: ***************add: 87.39481105187926 ***************adds: 95.32809689468347 ***************add(-s): 91.22332797027117 All object (following PoseCNN): ***************add: 87.82876641272729 ***************adds: 95.32953369790825 ***************add(-s): 90.4528140615951

could you please provide the files needed for eval_icp.py?

Mar 04 '22 01:03 CodeLHY