Adobe Photoshop CS5: Content-Aware Fill Sneak Peek
Channel:AdobePhotoshopFB · Length:5:06 · Published:2010-03-23 · Views:5211373
Summary
Adobe's sneak-peek demo of Content-Aware Fill ahead of Photoshop CS5, showing objects being removed and areas repaired seamlessly with the delete key.
Why HN recommends it
Referenced as the original demo that stunned people when object-removal and image-inpainting algorithms come up.
This was the video that blew everyone — HN, 2017
Computer vision, speech & NLP · Design & graphics (other)
Subtitles (excerpt)
Hi. My name is Bryan O'Neil Hughes. I'm one of the product managers on the Photoshop team. Today, I'd like to give you a sneak peek of just some of what we're working on here in our labs. We haven't released this yet, but we wanted to give you an idea of what we're up to. Here's an image we shot for a client, and it looked great when we took it, but in looking at it a little more closely now, we realized that uh we've got some lens flare here, and there are a couple of pieces of trash on the ground. And of course, this is the one they've chosen for print. Uh so, we realized that we really need to give it some scrutiny and clean up some of the trash and the distracting elements in the image. They've also asked that we go ahead and remove this tree in the left-hand side of the image because they want to put text and a logo up there, and they don't want it to conflict with the background. So, we have a lot of work ahead of us. Uh let's first look at some tools that we have available to us right now uh in CS4. Spot Healing Brush is a really great tool, but if I were to try to use it on something like this, you see I pick up artifacts from the background. And if I try to cross a shadow like this right here, same thing.
On Hacker News
Adobe calls it "Content Aware Fill" which is likely what you're thinking of. This was the video that blew everyone's mind, but its 7 years old at this point: [VIDEO] — mikeyouse, 2017-05
The "remove an object" image transformation reminds me of the Photoshop new feature "content-aware fill" featured here: [VIDEO] — niels_bom, 2011-08
Here is how it's done in photoshop: [VIDEO] (2:45) It seems someone decided to remove the banner from the video frame. Have a look at the left guys hat, there is a little "v" from where the banner was (in the top red oval). Edited: [LINK] Original: [LINK] — hmottestad, 2011-05
Related videos
- Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning · Google TechTalks · 48:10
- "Voice Driven Development: Who needs a keyboard anyway?" by Emily Shea · Strange Loop Conference · 41:17
- Andrej Karpathy - AI for Full-Self Driving at Tesla · Matroid · 30:08
- Tensorflow and deep learning - without a PhD by Martin Görner · Devoxx · 2:35:53
- JPEG DCT, Discrete Cosine Transform (JPEG Pt2)- Computerphile · Computerphile · 15:11
- Fourier Optics used for Optical Pattern Recognition · Huygens Optics · 18:30
- Let's build the GPT Tokenizer · Andrej Karpathy · 2:13:34
- Massive-scale online collaboration | Luis von Ahn · TED · 16:40
- Breaking The Creepy AI in Police Cameras · Benn Jordan · 35:49
- !!Con 2017: HDR Photography in Microsoft Excel?! by Kevin Chen · Confreaks · 11:46
- Dasher: information-efficient text entry · Google TechTalks · 53:45
- LSTM is dead. Long Live Transformers! · Seattle Applied Deep Learning · 28:48
- Dual Photography · mm648230 · 5:10
- Lecture 1 | Natural Language Processing with Deep Learning · Stanford University School of Engineering · 1:11:41
- Stealing Baseball Signs with a Phone (Machine Learning) · Mark Rober · 13:30
- [CVPR'21 WAD] Keynote - Andrej Karpathy, Tesla · WAD at CVPR · 31:31