2026
Debiasing Diffusion Priors via 3D Attention for Consistent Gaussian Splatting
AAAI 2026technical
Versatile 3D tasks (e.g., generation or editing) distilling Text-to-Image (T2I) diffusion models have attracted significant research interest for not relying on extensive 3D training data. However, T2I models exhibit limitations resulting from prior view bias, which produces conflicting appearances