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.”
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.
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.
The Latest on: Synthetic content
via Google News
The Latest on: Synthetic content
- Phycocyanin Market to be $245.5 million by 2027- Exclusive Report Covering Pre and Post COVID-19 Market Analysis by Meticulous Research® & EABAon October 7, 2020 at 5:48 am
According to a new market research report titled “Phycocyanin Market by Form (Liquid, Powder), by Grade (Food Grade, Cosmetic Grade, Reagent Grade, Analytical Grade) by Application (Food and Beverages ...
- Sen. Warner Urges Facebook, Twitter & Google to Reinforce Efforts Against Political Content Abuse Ahead of November Electionon October 7, 2020 at 4:30 am
The following press release is from Sen. Mark Warner's office. As Sen. Warner wrote on his Facebook page last night:"Just this morning, I encouraged Facebook to take the threat of QAnon more serious ...
- Biosecurity Is Synthetic Biology’s Most Crucial Allyon October 6, 2020 at 10:24 pm
Synthetic biology has made it easier than ever to engineer organisms to serve our needs. But as the technology becomes widespread, concerns about its potential misuse arise. How can we ensure ...
- Sen. Mark Warner urges social media platforms to reinforce efforts against political abuse ahead of electionon October 6, 2020 at 2:58 pm
Sen. Mark Warner urged Facebook, Twitter, and Google to help raise accountability and transparency ahead of Election Day. The move from Sen. Warner to highlight the spread of ...
- Warner urges Facebook, Twitter, Google to reinforce efforts against political content abuseon October 6, 2020 at 12:36 pm
U.S. Sen. Mark Warner (D-VA) is highlighting the need for accountability and transparency standards on social media ahead of the November election.
- CFN Enterprises Inc. Adds CB Therapeutics to Rapidly Growing Psychedelic Client Rosteron October 6, 2020 at 5:00 am
CFN Enterprises Inc. (OTCQB: CNFN), owner and operator of CFN Media, the leading media network and agency dedicated to the global legal cannabis, CBD and psychedelics industries, today announced the ...
- Synthetic Biologics Provides Update on Investigator-Sponsored Phase 2b Clinical Study of SYN-010 in IBS-C Patientson October 2, 2020 at 7:37 am
PRNewswire/ -- Synthetic Biologics, Inc. (NYSE American: SYN), a diversified clinical-stage company leveraging the ...
- Synthetic identity fraud: What is it and how can we stop it?on September 29, 2020 at 9:57 am
The latest tactic these bad actors are turning to is synthetic identity fraud. In the US, it’s already the fastest growing type of financial crime according to McKinsey – and it won’t be long until it ...
- Synthetic Biology Market Huge Growth Opportunities and Trends to 2026on September 29, 2020 at 6:30 am
The Synthetic Biology Market Perspective, Comprehensive Analysis along with Major Segments and Forecast, 2020-2026. The Synthetic Biology market report is a valuable source of data for business ...
- Synthetic Soda Ash Market Growing Demand, Supply and Revenue 2020 to 2026on September 28, 2020 at 1:11 am
Global Synthetic Soda Ash Market Insights, Forecast to 2026 Sep 28, 2020 (Market Insight Reports) -- The Synthetic Soda Ash Market report helps identify ...
via Bing News