正在加载视频...

视频加载失败

#iPhone users - here’s my method for capturing lunar images during tonight’s #LunarEclipse 🌕 Might vary a bit by model/OS.

44,704 次观看 • 1 个月前 •via X (Twitter)

12 条评论

Eagleman 的头像
Eagleman1 个月前

Should have done this tonight, a little tip for the future though. Not bad photos still.

IDK 的头像
IDK1 个月前

If only I had seen this earlier

Joshua Wright 的头像
Joshua Wright1 个月前

lol -android user

Owls Nest 的头像
Owls Nest1 个月前

Samsung Ultra 23 photo, not a video clip.

Rachel Pitzel 的头像
Rachel Pitzel1 个月前

I used this exact method over and over last night, but sadly couldn’t overcome the conditions in San Diego at the time (86% humidity 72 dew points and cloud cover up high). And yes, I kept wiping my lens too Thankfully we could see it well but couldn’t capture it. Glad it worked for you and others!

Meteorologist Will Haenni WWMT 的头像
Meteorologist Will Haenni WWMT1 个月前

Cool to hear this video reached that far! Sorry you didn't get better conditions. Funny we were more clear here in Michigan than in San Diego!

🎿✝️kstewskisAZ🌵🐾 的头像
🎿✝️kstewskisAZ🌵🐾1 个月前

Thank you this was helpful!

KittraKittra 的头像
KittraKittra1 个月前

Cool!

Phelps County Missouri Weather And News. 的头像
Phelps County Missouri Weather And News.1 个月前

Unedited at the moment. I hope everybody got some good shots.

cuca ☠️🎀(^_-) huesos Judith DPR 的头像
cuca ☠️🎀(^_-) huesos Judith DPR1 个月前

👌

Alma Gutierrez 的头像
Alma Gutierrez1 个月前

I did notice my video was better than my photo.. wish I had seen you tip on exposure last night.. it’s very cloudy herein San Antonio

Barbara not from Burbank 的头像
Barbara not from Burbank1 个月前

Thank you 🙌

相关视频

📢📢 𝐀𝐯𝐚𝐭𝟑𝐫 📢📢 Avat3r creates high-quality 3D head avatars from just a few input images in a single forward pass with a new dynamic 3DGS reconstruction model. Video: Project: Our core idea is to make Gaussian Reconstruction Models animatable. We find that a simple cross-attention to an expression code sequence is already sufficient to model complex facial expressions. We then incorporate position maps from DUSt3R and feature maps from Sapiens to facilitate the prediction task. While DUSt3R's position maps act as a pixel-aligned initialization for the Gaussians' positions, the Sapiens feature maps help the cross-view transformer to match corresponding image tokens in the 4 input images. One major challenge in creating a 3D head avatar from smartphone images comes from inconsistent facial expressions when the subject could not remain perfectly static during the capture. We eliminate this static requirement by simply showing our model input images with different facial expressions during training. This technique makes our model robust to inconsistent input images later on. Finally, we show that despite the model has been trained with 4 input images, one can even create a 3D head avatar when only a single image is available. To achieve this, we employ a pre-trained 3D GAN to lift the single image to 3D and then render the 4 input images for our model. This allows us to create 3D head avatars from single images and even highly out-of-distribution examples like AI generated faces, paintings or statues. Great work by Tobias Kirschstein from his internship at Meta with Javier Romero, Artem Sevastopolsky, and Shunsuke Saito

Matthias Niessner

74,863 次观看 • 1 年前