The early-stage technology previews focus on expanding flat media into immersive formats and automating repetitive post-production tasks. Tools like Project Sight Span turn static images into navigable 3D spaces, while Project Screen Test allows creators to interview animated characters via a call-like interface to shape their personas. Additionally, Project Sound Bender synchronizes generated audio to video, allowing creators to blend corner sound elements in real time across a square canvas.
Key points
Adobe is testing new artificial intelligence capabilities that may eventually integrate i…: Adobe is testing new artificial intelligence capabilities that may eventually integrate into its Firefly platform and Creative Cloud apps.
Production workflows could be streamlined through automated visual adjustments and text-p…: Production workflows could be streamlined through automated visual adjustments and text-prompted audio synchronization for video clips.
The experimental tools showcase a transition toward interactive character creation and th…: The experimental tools showcase a transition toward interactive character creation and the conversion of 2D art into navigable 3D scenes.
Sources checked by our analysis pipeline: 1
Some of the most impressive tech that Adobe showcases at its annual Max conference each year is the experimental features it’s developing, and the latest of those tools are being announced today: they can transform images into explorable 3D scenes, design AI characters by talking to them, and turn photo editing into a copy/paste process.
Adobe’s AI experiments let you walk around in photos and interview your characters
Here are some of the experimental ‘sneaks’ being showcased at Adobe Max.
Here are some of the experimental ‘sneaks’ being showcased at Adobe Max.
The first (and weirdest, in my opinion) is Project Screen Test, which is designed to make AI-generated characters easier to develop and use for video content. Instead of just describing how the character should sound and behave in text prompts, the tool lets you talk to the character and direct them in an audition-like environment. You start by describing some base personality traits, such as “anxious, shy, awkward,” and giving the character a voice, either by selecting a preset, describing how it sounds in a prompt, or uploading…
Founded by former Nexar employees, the startup secured $13 million in seed funding to resolve persistent reliability issues in enterprise artificial intelligence deployments. By applying autonomous driving simulation concepts, the platform maps out corporate systems to stress-test software against complex edge cases. This methodology helps organizations overcome severe real-world failure rates seen in leading foundation models while lowering downstream operational expenses.
Fresh capital will support the company as it advances dedicated technology designed specifically for computing infrastructure. The substantial half-billion-dollar commitment highlights accelerating financial support for power and hardware solutions tailored to modern processing needs. This major investment is positioned to drive further technical progress across high-demand enterprise computing facilities.
Conducted every five years by an international expert panel, the latest long-term assessment addresses twelve standing questions tracking technical progress, societal impacts, and ethical concerns. Robotics has integrated multimodal models and simulations, but bridging the divide between constrained demonstrations and unpredictable real-world environments remains a critical obstacle. Researchers continue to debate whether current statistical learning techniques can independently overcome foundational bottlenecks i…