Kavli Affiliate: Yi Zhou | First 5 Authors: Desai Xie, Jiahao Li, Hao Tan, Xin Sun, Zhixin Shu | Summary: Recent advancements in the text-to-3D task leverage finetuned text-to-image diffusion models to generate multi-view images, followed by NeRF reconstruction. Yet, existing supervised finetuned (SFT) diffusion models still suffer from multi-view inconsistency and the resulting NeRF […]
Continue.. Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning