CVPR2025

Decompositional Neural Scene Reconstruction with Generative Diffusion Prior

Junfeng Ni, Yu Liu, Ruijie Lu, Zirui Zhou, Song-Chun Zhu, Yixin Chen, Siyuan Huang

Abstract

Ours with 10 views ObjectSDF++ with 10 views ObjectSDF++ with 100 views Number of Views Object geometry editing Object appearance editing VFX editing Scene stylization Reconstructed mesh in Blender "Chinese style" "A round table" "Freeze it!" "Pokemon style" Figure 1 . We propose DP-RECON, which capitalizes on pre-trained diffusion models for complete and decompositional neural scene reconstruction. This approach significantly improves reconstruction quality in less captured regions, where previous methods often struggle. Additionally, our method enables flexible text-based editing of geometry and appearance, as well as photorealistic VFX editing.