Temporal Consistency News
The latest Temporal Consistency coverage curated for game developers.
LightCrafter tackles video relighting by feeding a diffusion model a PBR-rendered proxy instead of the raw footage. That shift aims to keep long-form shots temporally stable while giving artists more …
The interesting bit here is not just better video relighting, but a way to keep it stable across long clips instead of breaking at chunk boundaries. HorizonRelight treats the problem …
A new paper combines 2D instruction-guided diffusion with 3D Gaussian splatting to edit dynamic head videos into coherent avatars. The practical angle for animation and tech-art teams is better control …
A new video-editing model tackles a hard production problem: instance-level edits that stay coherent across frames. AlbedoEdit uses a user-edited first-frame albedo map to drive object insertion, removal, and texture …
A new reconstruction method tackles a nasty edge case for graphics teams: scenes that change across long time spans instead of moving smoothly. ChronoGS uses a temporally modulated Gaussian representation …
A new video relighting system can keep full-body human performances temporally stable while changing lighting, which is the hard part most relighting demos still struggle with. BodyReLux is trained on …
For teams shipping wide-aspect or long-form video, this paper tackles a real pain point: outpainting that stays coherent over large spatial expansion and long sequences. HL-OutPaint uses a two-stage coarse-to-fine …