Hi,
Thank you for this excellent work.
I evaluated SF3D and SPAR3D on the full OmniObject3D dataset following the settings in ZeroShape, but the results I obtained were significantly lower compared to methods like LRM and InstantMesh. I was wondering if there are any specific evaluation details or tricks that might explain the discrepancy.
Also, do you have any plans to release the evaluation lists for the OmniObject3D and GSO datasets?
It would be very helpful if the evaluation code and the rendering script could be shared as well.
Thank you again, and I look forward to your response.
Best regards,
Ahyun Seo
Hi,
Thank you for this excellent work.
I evaluated SF3D and SPAR3D on the full OmniObject3D dataset following the settings in ZeroShape, but the results I obtained were significantly lower compared to methods like LRM and InstantMesh. I was wondering if there are any specific evaluation details or tricks that might explain the discrepancy.
Also, do you have any plans to release the evaluation lists for the OmniObject3D and GSO datasets?
It would be very helpful if the evaluation code and the rendering script could be shared as well.
Thank you again, and I look forward to your response.
Best regards,
Ahyun Seo