BenchmarkBecomingLit数据集
BecomingLit
A public dataset used to evaluate virtual human tasks such as novel-view reenactment.
Timeline (last 90 days)
Oct 19
On the novel-view reenactment task, VDAs on the BecomingLit dataset reduces facial LPIPS by 29% and improves JOD by 66% compared with the strongest single-image 3D avatar method.
Unverified50%