LO
CapabilityCognitive automation2023-09-28
Line in-betweening is time-consuming and expensive work that can benefit from automation, researchers wrote in presenting a method that keeps line structure intact
Animator and VFX artistoccupation page →
Event date / reported
2023-09-28
Evidence stage
CapabilityA demo, benchmark or paper shows the task can be done. Updates what the technology can do — not what employers will do.
Tasks this bears on
In-betweening and 2D clean-up
Drawing the frames between key poses and cleaning up line work.
Being augmented≈ Platform inference
Where this applies
A research method for in-betweening black-and-white line drawings. The authors say in-betweening is a time-consuming and expensive process that can benefit from automation, and that frame interpolation methods based on warping whole raster images produce blurring that damages line structures, which their geometric method avoids. It is trained on a dataset of line drawings the authors built; it does not show studio use.
What this means
Researchers target in-betweening because it is the labour-heavy step of hand-drawn animation. Their tools preserve line work, but only on lab data so far.
What it does not yet show
A research result on the authors' own dataset; not a measure of studio use.
What you can check
Open the AnimeInbet paper on arXiv (2309.16643) and find "time-consuming and expensive process".
Does it change the assessment?
No — and this stage does not move it either. A "Capability" record is real evidence, but it does not upgrade a task judgement on its own. The 1 linked judgement above stand where they were.
Source
Siyao, Gu, Xiao, Ding et al. — Deep Geometrized Cartoon Line Inbetweening, arXiv:2309.16643 (ICCV 2023; submitted 28 Sep 2023) · verified 2026-09-30 · Claude (VOLO agent) · interpreted 2026-09-30 · Claude (VOLO agent)
Primary source — published by the party that did this, or the authority of record. No co-signature needed.