A new algorithm allows video editors to modify talking head videos as if they were editing text – copying, pasting, or adding and deleting words.
In television and film, actors often flub small bits of otherwise flawless performances. Other times they leave out a critical word. For editors, the only solution so far is to accept the flaws or fix them with expensive reshoots.
Imagine, however, if that editor could modify video using a text transcript. Much like word processing, the editor could easily add new words, delete unwanted ones or completely rearrange the pieces by dragging and dropping them as needed to assemble a finished video that looks almost flawless to the untrained eye.
A team of researchers from Stanford University, Max Planck Institute for Informatics, Princeton University and Adobe Research created such an algorithm for editing talking-head videos – videos showing speakers from the shoulders up.
The work could be a boon for video editors and producers but does raise concerns as people increasingly question the validity of images and videos online, the authors said. However, they propose some guidelines for using these tools that would alert viewers and performers that the video has been manipulated.
“Unfortunately, technologies like this will always attract bad actors,” said Ohad Fried, a postdoctoral scholar at Stanford. “But the struggle is worth it given the many creative video editing and content creation applications this enables.”
Reading lips
The application uses the new transcript to extract speech motions from various video pieces and, using machine learning, convert those into a final video that appears natural to the viewer – lip-synched and all.
“Visually, it’s seamless. There’s no need to rerecord anything,” said Fried, who is first author of a paper about the research published on the pre-publication website arXiv. It will also be in the journal ACM Transactions on Graphics. Fried works in the lab of Maneesh Agrawala, the Forest Baskett Professor in the School of Engineering and senior author of the paper. The project began when Fried was a graduate student working with computer scientist Adam Finkelstein at Princeton, more than two years ago.
Should an actor or performer flub a word or misspeak, the editor can simply edit the transcript and the application will assemble the right word from various words or portions of words spoken elsewhere in the video. It’s the equivalent of rewriting with video, much like a writer retypes a misspelled or unfit word. The algorithm does require at least 40 minutes of original video as input, however, so it won’t yet work with just any video sequence.
As the transcript is edited, the algorithm selects segments from elsewhere in the recorded video with motion that can be stitched to produce the new material. In their raw form these video segments would have jarring jump cuts and other visual flaws.
To make the video appear more natural, the algorithm applies intelligent smoothing to the motion parameters and renders a 3D animated version of the desired result. However, that rendered face is still far from realistic. As a final step, a machine learning technique called Neural Rendering converts the low-fidelity digital model into a photorealistic video in perfect lip-synch.
To test the capabilities of their system the researchers performed a series of complex edits including adding, removing and changing words, as well as translations to different languages, and even created full sentences as if from whole cloth.
In a crowd-sourced study with 138 participants, the team’s edits were rated as “real” almost 60 percent of the time. The visual quality is such that it is very close to the original, but Fried said there’s plenty of room for improvement.
“The implications for movie post-production are big,” said Ayush Tewari, a student at the Max Planck Institute for Informatics and the paper’s second author. It presents for the first time the possibility of fixing filmed dialogue without reshoots.
Ethical concerns
Nonetheless, in an era of synthesized fake videos such capabilities raise important ethical concerns, Fried added. There are very valuable and justifiable reasons to want to edit video in this way, namely the expense and effort required to rerecord or repair such flaws in video content, or to customize existing audio-visual video content by audience. Instructional videos might be fine-tuned to different languages or cultural backgrounds, for instance, or children’s stories could be adapted to different ages.
“This technology is really about better storytelling,” Fried said.
Fried acknowledges concerns that such a technology might be used for illicit purposes, but says the risk is worth taking. Photo-editing software went through a similar reckoning, but in the end, people want to live in a world where photo-editing software is available.
As a remedy, Fried says there are several options. One is to develop some sort of opt-in watermarking that would identify any content that had been edited and provide a full ledger of the edits. Moreover, researchers could develop better forensics such as digital or non-digital fingerprinting techniques to determine whether a video had been manipulated for ulterior purposes. In fact, this research and others like it also build the essential insights that are needed to develop better manipulation detection.
None of the solutions can fix everything, so viewers must remain skeptical and cautious, Fried said. Besides, he added, there are already many other ways to manipulate video that are much easier to execute. He said that perhaps the most pressing matter is to raise public awareness and education on video manipulation, so people are better equipped to question and assess the veracity of synthetic content.
Learn more: Stanford engineers make editing video as easy as editing text
The Latest on: Synthetic content
[google_news title=”” keyword=”synthetic content” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Synthetic content
- Marriage of synthetic biology and 3D printing produces programmable living materialson May 4, 2024 at 10:24 am
Scientists are harnessing cells to make new types of materials that can grow, repair themselves and even respond to their environment. These solid 'engineered living materials' are made by embedding ...
- ‘Stronger than fentanyl’: The surge in seizures of a deadly new synthetic opioidon May 3, 2024 at 12:15 pm
Australian authorities are intercepting more shipments of super-potent nitazenes and medical professionals fear it could lead to a wave of overdoses.
- Researchers develop 'founding document' on synthetic cell developmenton May 3, 2024 at 1:01 am
Cells are the fundamental units of life, forming the variety of all living things on Earth as individual cells and multicellular organisms. To better understand how cells perform the essential ...
- Google restricts promotion of deep fake sexual contenton May 2, 2024 at 8:04 am
Google introduced new restrictions on deep fake sexual content for Shopping ads. Google also updated its general content policy prohibiting promoting synthetic content that has been altered or ...
- Google Ads To Disallow Services For Deepfake Sexual Contenton May 2, 2024 at 4:05 am
Google Ads, Shopping Ads, Admob, and other Google Ads products will soon disallow deepfake sexual content, synthetic sexually explicit content, or synthetic content containing nudity services. I mean, ...
- Programmable Living Materials Created Using Synthetic Biology and 3D Printingon May 2, 2024 at 2:07 am
Scientists are harnessing cells to make new materials that can grow, repair themselves and even respond to their environment.
- Researchers turn to two crops to tackle environmental harm of apparel made with synthetic fiberson May 1, 2024 at 11:49 am
From risottos to sauces, mushrooms have long been a staple in the kitchen. Now fungi are showing the potential to serve up more than just flavor—as a sustainable, bendy material for the fashion ...
- NIST launches a program to benchmark generative AI tech and identify AI-generated contenton April 30, 2024 at 8:30 am
The program will try to figure out whether content is generated by AI or created by humans, and promote AI tech that is a net good for society.
- You should rethink using AI-generated images if you're in the trust-building businesson April 30, 2024 at 7:00 am
including labeling synthetic content as such. Doing so can better protect the integrity of the customer relationship, according to the report. Additionally, if a campaign uses authenticity as a ...
- Is synthetic data the key to better market research?on April 29, 2024 at 7:58 am
Market researchers hope that AI can make their work easier by mimicking niche population groups and boosting sample sizes with synthetic data ...
via Bing News