Lets talk it out. NP3| Camera | Zoom | Moon

ArnimZola · 2025-09-11T20:55:06+00:00

Has anyone tried it, yet ? I did, here are the results. [upl-image-preview uuid=9c5ce6a0-eaa9-4bdd-92b5-93df28fb1096 url=https://cdn.nothing.community/2025-09-11/1757622791-861039-img-20250908-220458281.jpg alt={TEXT?}] [upl-image-preview uuid=39251c57-3dff-4b01-bab3-6ddd0ead69b3 url=https://cdn.nothing.community/2025-09-11/1757622792-321039-img-20250908-220544703.jpg alt={TEXT?}] [upl-image-preview uuid=d77a7d19-ed5b-4da9-89f1-7f1e7ea02bf9 url=https://cdn.nothing.community/2025-09-11/1757622792-745293-img-20250908-220823810.jpg alt={TEXT?}] Images on the day after the recent eclipse. (Moon wasn't red at the time of capture. Apologies for that.) The moon's image is replaced in real time, like when you tap to focus on the moon, it would change. And when the picture is clicked, another optimization makes it such. These are from zoom levels where pro res turns on(two images are on full 60x and one is lower, I don't remember). I do understand what A.I does, being a data scientist. But, but, but, hear me out. There needs to be some sort of filtering to the optimization. I know there might be pre-trained models to which the captured vectors goes through the model to output the optimizations. No doubt they do work well in some general environments. My solution to this problem would be to, either fine-tune the model with some hand-tuned images of the moon, given the true input. This would greatly leverage the manually tuning variations for the model, but I don't think this would be in the hands of the team as it might be using some thirtd party proprietary model. I know previously some samsung phones did it, but they listened and corrected it to an extent that the moon doesn't look replaced. I'm not a pro in photography, therefore, I'd love to hear some opinions on it. However, it was a jaw dropper when I saw the clicked images for a few seconds, till my neurons fired.😆

CMF1_hacker

You can’t just bust a button and expect it to work.

Also, it’s AI/ML that you’re seeing great photos.of.

You need to be zoomed over 20x (were you?) and other things need to be over thresholds for the ML/AI to kick in. (Those photos you’re seeing arent real and are post-processed for the consumer.)

This is shutter speed and how it makes things blurry: https://www.kaylabrint.com/fixing-blurry-photos-shutter-speed-explained/

Dushyant_BPpgJ29xmr

@“CMF1_hacker”#p221924I’m aware of the post-processing, but that’s my concern. I tried several shots at 30x, 50x, and 60x, but the processing quality wasn’t close to what I’ve seen, even in this thread. I’m doubtful about what the AI is generating as the final output and why is it varying so much for me. I haven’t updated to the beta os yet, I’m still on the stable 3.5 . I was also facing some issues with the presets. is there a device problem here?

CMF1_hacker

make a video like this and post the results and we’ll know. that’s handheld by me through a double-paned glass window (20mm gap between panes).

AlexWong_0uUp43EN5l

I just shoot on expert mode + raw

Shot on NP3.

« Previous Page