For those who don’t know the tool: Beeble Background Remover is a Cloud roto and matte extractor for comps, now offering CorridorKey or MatAnyone before upload, so your key tests can happen before your pipeline meeting turns into a sequel.

What changed in Background Remover

Beeble‘s Background Remover now lets you choose between MatAnyone and CorridorKey before you upload footage. MatAnyone stays positioned as the general-purpose option. CorridorKey is positioned as the green screen option, aimed at cleaner edges and more accurate keying on chroma key shots. Background Remover runs only in the Cloud app and does not run in the desktop product.

The fastest way to try it without committing

CorridorKey has the kind of momentum that makes people want to try it immediately, and also the kind of setup that can make them postpone it indefinitely. If you do not want to download code, install dependencies, and explain to your producer why your machine is now compiling something called a model, running CorridorKey inside the Background Remover toolkit gives you a low-friction way to test it on your own footage first. That includes testing it against your current keys, and checking whether your exports land cleanly in your comp toolchain, without rebuilding that toolchain just to run an experiment.

How CorridorKey was invented

CorridorKey started as a response to a workload problem. A greenscreen-heavy show needed a lot of shots, and the team wanted an automated way to cut subjects out so they could spend time on the creative side of VFX instead of hand-cleaning keys frame after frame.

The design focus landed on a specific compositing headache: a greenscreen edge pixel often contains a mix of foreground and background light. A matte can be good and the color can still be wrong, because the plate already baked the screen contribution into semi-transparent detail. The CorridorKey approach targets a straight color foreground output paired with an alpha output, so semi-transparent materials, motion blur, and hair can keep behaving like actual transparency instead of looking like tinted cutouts.

Training data was coming from CG so the model could learn from mathematically clean answers. The workflow renders greenscreen plates, then renders the same foreground without the background and with a perfect alpha, giving the model ground truth for both color and transparency. Scale was coming from procedural variation, including procedural scene generation work in tools like Houdini and Blender to produce many variations in lighting, materials, objects, and motion without rebuilding each shot by hand.

Early results were treated as tests and iterated on through retraining. One tactic for pushing quality was to composite results over random backgrounds and neutral gray during testing, so leftover contamination becomes obvious and gets punished during training. The tool is being used as a first step in a broader pipeline, with outputs intended to drop into comp and realtime contexts in apps like Adobe After Effects and Unreal Engine.

What you get out of Beeble after a run

If you are testing CorridorKey for greenscreen work, this matters because the outputs determine how painful your handoff is. A quick trial that ends in a format conversion detour still counts as pain. It just wears a different hat.

Background Remover is built around alpha extraction for compositing and VFX workflows. You can upload a video, an image sequence, or a single image, then download results intended to slot into a comp.

On the Cloud pricing page, export options are listed as RGBA exports in MOV or PNG sequence and alpha exports in MP4 or PNG sequence. MOV here refers to the QuickTime container, PNG refers to the PNG format, and MP4 refers to the MPEG family container.

Pricing, credits, and practical limits

Background Remover usage is credit-based. The Cloud pricing is around image uploads as consuming one credit per image and video uploads as consuming one credit per second of video.

The plans listed include a free Starter tier that includes ninety credits per month and is labeled non-commercial. Two paid tiers have Background Remover included. “Creator” is listed at nineteen US dollars per month or sixteen US dollars per month when billed annually, with five hundred forty credits per month. “Professional” is listed at seventy-five US dollars per month or sixty US dollars per month when billed annually, with two thousand four hundred credits per month.

Per-upload maximums for video length are thirty seconds on the five hundred forty credit tier and one minute on the two thousand four hundred credit tier. There is also a batch upload up to twenty files at once on the paid tiers.

A production reality check

CorridorKey is a model option, not a replacement for judgement. Every keying tool behaves differently across compression, sensor noise, spill, lens artifacts, and the very special chaos of talent wardrobe choices. Test CorridorKey on your own porudction plates before you trust it with a deadline, and keep your existing approach ready for the shots that refuse to behave.

If the results look good, treat the first integration step as a controlled experiment: run a small batch, validate edge stability, validate color behavior in the semi-transparent areas, validate the exports in your comp, then scale up. That is less romantic than a revolution, but it is how tools earn their place in compositnig pipelines.

https://docs.beeble.ai/beeble/background-remover

https://github.com/nikopueringer/CorridorKey

https://beeble.ai

The post Beeble adds CorridorKey green screen model first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

Boris FX Continuum 2026 continues the developer’s long-running effort to automate routine postproduction work through machine learning. The 2026 release strengthens AI masking, compositing, and keying features while speeding up overall processing across multiple effects.

Masking and isolation

The PixelChooser, Continuum’s core masking and isolation framework, has been overhauled with AI segmentation tools. The new Face ML model automatically detects and isolates facial regions such as eyes, lips, teeth, and surrounding skin. By defining specific facial areas, users can target effects precisely or exclude them entirely, reducing the need for manual rotoscoping.

Complementing this, Matte Refine ML analyses existing mattes to restore or enhance fine edge detail. Elements such as hair strands and semi-transparent surfaces are now easier to preserve in composites. The PixelChooser also gains six additional matte and mask modes—Pre, Post, Both, Stacked Composite, Alpha Masked, and Alpha Composite—offering flexible control over whether masks are applied before, after, or alongside effects. Both Face ML and Matte Refine ML are available inside Beauty Studio, within the PixelChooser itself, and as standalone filters in the Key & Blend category.

Smarter face detection

Face Detection via Mocha adds automatic recognition and tracking of multiple faces within a clip. The feature integrates Mocha’s planar tracking, allowing individual faces to be followed accurately across frames. Once detected, Continuum effects can be selectively applied to specific tracked regions, streamlining retouching or compositing tasks that previously required separate mask layers.

Updated Primatte Studio

The Primatte Studio keying module has been rebuilt for Continuum 2026. According to Boris FX, it now employs a new 3D keying algorithm combined with integrated AI Denoise for cleaner source plates. Expanded Light Wrap and Spill Suppression controls offer greater realism when blending foregrounds into new backgrounds. The new Colour Link function automatically adjusts the hue and luminance of the keyed subject to match the underlying background input, reducing manual colour correction work. The redesigned custom toolbar centralises keying parameters, creating a more efficient, single-pane workspace for editors and compositors.

A persponal Note: We do love Ben’s tutorals but for this one: Turn on the automatic german translation, and enjoy a very hearty giggle – the confidences of the synthetic voice (that sounds nothing like Ben) talks about primates is… top-not unintentional comedy!

AI-powered transitions

Two new machine-learning transitions extend Continuum’s effects library. Jump Cut Fixer ML uses AI-based optical-flow analysis to generate seamless dissolves between two adjacent shots. By reconstructing motion between frames, the tool can mask timing gaps or abrupt cuts, preserving narrative flow without additional editing. Built-in colour adjustment parameters and interactive on-screen widgets enable further control over the dissolve timing and strength.

Depth Wipe ML, the second new transition, uses AI-generated depth maps to move beyond flat 2D wipes. Instead of a simple horizontal or vertical reveal, the effect creates a transition that passes dynamically through the 3D space of the image, wiping from foreground to background. The effect includes more than fifteen presets for rapid setup and provides controls for animation, blending, and dissolve shaping.

Enhanced legacy tools

Continuum 2026 revisits several of its longstanding effects. The Scanline effect recreates the appearance of vintage CRT displays, now adding adjustable parameters for glow, noise, and vignette intensity to deliver more authentic analogue texture. Lens Blur expands to support full HDR workflows and introduces a Depth Mask ML option that allows defocus or rack-focus effects to respond accurately to depth information.

The Colour Link filter, also available as a standalone effect, gains a Diffuse Colour Displacement texture option that improves colour blending and realism when integrating keyed subjects into complex backgrounds. Particle Illusion benefits from smoother animation interpolation, a reverse-animation toggle, and a newly curated emitter library designed for modern compositing environments. Meanwhile, Lens Flare has been optimised for performance and now renders up to four times faster than before. Title Studio improves type handling with expanded font-family support and more stable character rendering across different hosts.

Faster AI models

Continuum’s existing AI-based effects have been refactored for speed and quality. Retimer ML can now accommodate mixed frame-rate sources within After Effects, avoiding frame mismatch issues in complex sequences. UpRes ML incorporates NVIDIA Super Scale models, offering higher-quality image enlargements for up-conversion tasks. Depth Map ML produces cleaner, more consistent mattes suitable for grading or selective blurring operations. Motion Blur ML introduces adaptive sampling and synchronisation with Beat Reactor, enabling rhythm-driven motion-blur intensities. Frame Fixer ML receives refinements for handling trimmed or incomplete frames in Avid Media Composer projects, improving overall frame reconstruction reliability.

Continuum honoured with an Engineering Emmy

In October 2025, the Television Academy presented Boris FX Continuum with an Engineering, Science & Technology Emmy Award. Founder and CEO Boris Yamnitsky accepted the award together with long-time team members Peter McAuley, Jason Clement, and Mike Escola. The accolade recognises Continuum’s three-decade contribution to visual-effects and compositing workflows, marking it as one of the industry’s most influential non-linear-editing plug-in suites.

Yamnitsky described the award as both humbling and affirming, recalling the product’s beginnings as code written in his parents’ basement and its early adoption within emerging NLE systems such as Media 100 and Adobe Premiere. The Emmy recognition also highlights Boris FX’s commitment to broad platform support. Continuum has long maintained compatibility across Avid, Premiere Pro, DaVinci Resolve, Vegas, Filmora, and Final Cut Pro, reflecting the company’s belief that every editor deserves access to the same toolset regardless of host application.

For the record

Boris FX presents the 2026 release as a continuation of this Emmy-recognised legacy, extending Continuum’s compositing foundation with new AI-driven technologies. As always, postproduction teams are advised to test AI-masking accuracy and stability within their own workflows before integrating the update into production pipelines.

borisfx.com

The post Continuum 2026: AI masks, fixes, and faces first appeared on DIGITAL PRODUCTION and was written by Bela Beier.