H2O-SDF: Two-phase Learning for 3D Indoor Reconstruction using Object Surface Fields

Minyoung Park, Mirae Do, Yeon Jae Shin, Jaeseok Yoo, Jongkwang Hong, Joongrock Kim, Chul Lee

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: 3D reconstruction, Neural implicit surface learning

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: For 3D indoor scene reconstruction, we present a novel two-phase learning approach, which comprises holistic surface learning and object surface learning.

Abstract: Advanced techniques using Neural Radiance Fields (NeRF), Signed Distance Fields (SDF), and Occupancy Fields have recently emerged as solutions for 3D indoor scene reconstruction. We introduce a novel two-phase learning approach, H2O-SDF, that discriminates between object and non-object regions within indoor environments. This method achieves a nuanced balance, carefully preserving the geometric integrity of room layouts while also capturing intricate surface details of specific objects. A cornerstone of our two-phase learning framework is the introduction of the Object Surface Field (OSF), a novel concept designed to mitigate the persistent vanishing gradient problem that has previously hindered the capture of high-frequency details in other methods. Our proposed approach is validated through several experiments that include ablation studies.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: representation learning for computer vision, audio, language, and other modalities

Submission Number: 4361