DebSDF: Delving into the Details and Bias of Neural Indoor Scene Reconstruction

(TPAMI 2024)

Yuting Xiao1*, Jingwei Xu1*, Zehao Yu2, Shenghua Gao1†,
1ShanghaiTech University 2University of Tübingen
( * denotes the equal contribution, † denotes the corresponding author)
Paper arXiv Supplementary Code
DebSDF

DebSDF: We can observe that our method can reconstruct the indoor scene with more detailed structures, such as the chair legs and bracket of the desk lamp. Our method can accurately generate the uncertainty map, which can localize the inaccurate priors and reduce the bias in SDF-based rendering with a proposed bias-aware SDF to density transformation approach so that our method can reconstruct the indoor scene significantly better than previous works.

Interactive Video Comparison

(Please refresh if you don't see the video)

MonoSDF    VS    Ours



Click for more interactive comparison

BibTeX

@article{debsdf2024,
    title={DebSDF: Delving into the Details and Bias of Neural Indoor Scene Reconstruction},
    author={Yuting Xiao and Jingwei Xu and Zehao Yu and Shenghua Gao},
    journal={IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
    year={2024}
}