Graphics Ai News
The latest Graphics Ai coverage curated for game developers.
A study of video diffusion models found they can linearly expose physical plausibility in their internal states, even though that signal is missing from the VAE input. On IntPhys and …
SelfBootTok splits image tokens into global and local groups, cutting redundant detail from the generator’s job. The paper reports roughly 40% less generator computation while improving reconstruction and generation quality. …
A new compound AI pipeline claims to push brand-compliant video generation from 42% to 89% by adding retrieval-based brand extraction and a multi-agent QC loop. For teams using generative media …
One-step diffusion is being pushed into real-world video super-resolution, which matters if you care about upscaling cutscenes, replays, or streamed footage without the usual temporal wobble. OSDEnhancer combines a linear …