DIFIX3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

https://research.nvidia.com/labs/toronto-ai/difix3d Nerfacto Ours Ours 3DGS Nerfacto Ours Nerfacto Ours Figure 1. We demonstrate DIFIX3D+ on both in-the-wild scenes (top) and driving scenes (bottom). Recent Novel-View Synthesis methods struggle in sparse-input settings or when rendering views far from the input camera poses. DIFIX distills the priors of 2D generative models to enhance reconstruction quality and can further act as a neural-renderer at inference time to mitigate the remaining inconsistencies. Notably, the same model effectively corrects NeRF [37] and 3DGS [20] artifacts.