Seeking Advice on Sparse View CT Reconstruction

[Edward-HE]

Thank you for your excellent work and for sharing the code of your paper. I am very interested in this project and truly appreciate your contribution to the community.

I tried running the Aseq_DIP_Sparse_view_CT.py script, but the results I got were very blurry and far from ideal reconstruction. I’ve followed the instructions, but my outputs don’t seem to match. My settings were:

• learning rate: 2e-4
• network: MediumUNet
• K: 2000
• N: 20
• $\lambda$: 1

Do you have any advice or tips on how to get better results? Maybe I missed some key settings or steps. Any help would be appreciated!

[sjames40]

Sorry for the late response. I have changed the code and you can have a try again.

…

________________________________ From: Chenhe Du ***@***.***> Sent: Thursday, June 12, 2025 1:57 PM To: sjames40/Aseq_DIP ***@***.***> Cc: Subscribed ***@***.***> Subject: [sjames40/Aseq_DIP] Seeking Advice on Sparse View CT Reconstruction (Issue #3) [https://avatars.githubusercontent.com/u/45442673?s=20&v=4]Edward-HE created an issue (sjames40/Aseq_DIP#3)<https://urldefense.com/v3/__https://github.com/sjames40/Aseq_DIP/issues/3__;!!HXCxUKc!1eTBcvyiWH7JCjUgwadfNRdgug-zofJPM8r2NXtUpFlFJo5JxJvdOg-5UGy6LbarwOgQ5shXm6J-iqQ_dYFDXUKYyA$> Thank you for your excellent work and for sharing the code of your paper. I am very interested in this project and truly appreciate your contribution to the community. I tried running the Aseq_DIP_Sparse_view_CT.py script, but the results I got were very blurry and far from ideal reconstruction. I’ve followed the instructions, but my outputs don’t seem to match. My settings were: * learning rate: 2e-4 * network: MediumUNet * K: 2000 * N: 20 * $\lambda$: 1 Do you have any advice or tips on how to get better results? Maybe I missed some key settings or steps. Any help would be appreciated! — Reply to this email directly, view it on GitHub<https://urldefense.com/v3/__https://github.com/sjames40/Aseq_DIP/issues/3__;!!HXCxUKc!1eTBcvyiWH7JCjUgwadfNRdgug-zofJPM8r2NXtUpFlFJo5JxJvdOg-5UGy6LbarwOgQ5shXm6J-iqQ_dYFDXUKYyA$>, or unsubscribe<https://urldefense.com/v3/__https://github.com/notifications/unsubscribe-auth/ANC7N6GKKNB4Q3CJALAJSZL3DG5PNAVCNFSM6AAAAAB7GDL7XOVHI2DSMVQWIX3LMV43ASLTON2WKOZTGE2DCMJVHAYDCNI__;!!HXCxUKc!1eTBcvyiWH7JCjUgwadfNRdgug-zofJPM8r2NXtUpFlFJo5JxJvdOg-5UGy6LbarwOgQ5shXm6J-iqQ_dYF0gD-akQ$>. You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>