Ref-NeRF Real dataset

[minseong0106]

Hi,

Thank you all for the great work and the release of the code. I want to try the RefNeRF in real datasets, starting by reproducing the results in the scenes from the paper.

I used the following command to execute the code.
python3 run.py --ginc configs/refnerf/refnerf_real.gin --scene gardenspheres

But the rendering result is not good.

I'm not sure how I can get the results of the real data of refnerf.

Thank you.

[kimjanchaeng]

I also have same problem.
Did you solve this problem?

[minseong0106]

I think i solve the problem. How about run code with llff.gin? 2023년 10월 26일 (목) 오후 4:05, kimjanchaeng ***@***.***>님이 작성:

…

I also have same problem. Did you solve this problem? — Reply to this email directly, view it on GitHub <#39 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AL6VSI7KD3GXFV3X4SIA36DYBIDTPAVCNFSM6AAAAAAYBBGTGWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTOOBQGUZTEMJUGA> . You are receiving this because you authored the thread.Message ID: ***@***.***>

[kimjanchaeng]

Thank you for your prompt response. Did you get the almost close rendering results in Ref-NeRF paper( 23.40 / 0.620 / 0.125 : PSNR/SSIM/LPIPS ) by running code with llff.gin? 2023년 10월 26일 (목) 오후 5:44, Minseong Kim ***@***.***>님이 작성:

…

I think i solve the problem. How about run code with llff.gin? 2023년 10월 26일 (목) 오후 4:05, kimjanchaeng ***@***.***>님이 작성: > I also have same problem. > Did you solve this problem? > > — > Reply to this email directly, view it on GitHub > < #39 (comment)>, > or unsubscribe > < https://github.com/notifications/unsubscribe-auth/AL6VSI7KD3GXFV3X4SIA36DYBIDTPAVCNFSM6AAAAAAYBBGTGWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTOOBQGUZTEMJUGA> > . > You are receiving this because you authored the thread.Message ID: > ***@***.***> > — Reply to this email directly, view it on GitHub <#39 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/BBDPFINYPSPU6AXMJ3ZUFKTYBIPFVAVCNFSM6AAAAAAYBBGTGWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTOOBQGY3TIMRQGY> . You are receiving this because you commented.Message ID: ***@***.***>

[minseong0106]

No I didn't get the results from paper. I tried extracting the normal map, but it doesn't come out exactly. 2023년 10월 27일 (금) 오전 11:01, kimjanchaeng ***@***.***>님이 작성:

…

Thank you for your prompt response. Did you get the almost close rendering results in Ref-NeRF paper( 23.40 / 0.620 / 0.125 : PSNR/SSIM/LPIPS ) by running code with llff.gin? 2023년 10월 26일 (목) 오후 5:44, Minseong Kim ***@***.***>님이 작성: > I think i solve the problem. > How about run code with llff.gin? > > 2023년 10월 26일 (목) 오후 4:05, kimjanchaeng ***@***.***>님이 작성: > > > I also have same problem. > > Did you solve this problem? > > > > — > > Reply to this email directly, view it on GitHub > > < > #39 (comment)>, > > > or unsubscribe > > < > https://github.com/notifications/unsubscribe-auth/AL6VSI7KD3GXFV3X4SIA36DYBIDTPAVCNFSM6AAAAAAYBBGTGWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTOOBQGUZTEMJUGA> > > > . > > You are receiving this because you authored the thread.Message ID: > > ***@***.***> > > > > — > Reply to this email directly, view it on GitHub > < #39 (comment)>, > or unsubscribe > < https://github.com/notifications/unsubscribe-auth/BBDPFINYPSPU6AXMJ3ZUFKTYBIPFVAVCNFSM6AAAAAAYBBGTGWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTOOBQGY3TIMRQGY> > . > You are receiving this because you commented.Message ID: > ***@***.***> > — Reply to this email directly, view it on GitHub <#39 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AL6VSI2Y4GFYQWWRDARSV7DYBMIZNAVCNFSM6AAAAAAYBBGTGWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTOOBSGE3TGNRSGA> . You are receiving this because you authored the thread.Message ID: ***@***.***>