SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.08605 · ICCV · 2023

RICO: Regularizing the Unobservable for Indoor Compositional Reconstruction

Yong Liu, Yiyi Liao, Zizhang Li, Xiaoyang Lyu, Mengmeng Wang, Yuanyuan Ding

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
kyleleey/RICO — 2 of 5
copy not recorded — 2 of 2
FunctionStatusWhere it lives
alpha_to_w Ran kyleleey/RICO/code/model/network_rico.py
code served (permissive licence) · get_code("71a7649f2baba014")
cdf_Phi_s Ran this paper's copy was not recorded; identical code first harvested from ventusff/neurecon
pointer only · get_code("967d31403271a227")
sample_pdf Ran kyleleey/RICO/code/model/network_rico.py
code served (permissive licence) · get_code("acf7388f597b707b")
sdf_to_alpha Ran this paper's copy was not recorded; identical code first harvested from ventusff/neurecon
pointer only · get_code("7bf297619343c144")
RICONetwork Not yet run kyleleey/RICO/code/model/network_rico.py
code served (permissive licence) · get_code("802dcfdaf2b02962")
RenderingNetwork Not yet run kyleleey/RICO/code/model/network_rico.py
code served (permissive licence) · get_code("0953b4aa75c07444")
SemImplicitNetwork Not yet run kyleleey/RICO/code/model/network_rico.py
code served (permissive licence) · get_code("50f059ada318d29a")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recently, neural implicit surfaces have become popular for multi-view reconstruction. To facilitate practical applications like scene editing and manipulation, some works extend the framework with semantic masks input for the object-compositional reconstruction rather than the holistic perspective. Though achieving plausible disentanglement, the performance drops significantly when processing the indoor scenes where objects are usually partially observed. We propose RICO to address this by regularizing the unobservable regions for indoor compositional reconstruction. Our key idea is to first regularize the smoothness of the occluded background, which then in turn guides the foreground object reconstruction in unobservable regions based on the object-background relationship. Particularly, we regularize the geometry smoothness of occluded background patches. With the improved background surface, the signed distance function and the reversedly rendered depth of objects can be optimized to bound them within the background range. Extensive experiments show our method outperforms other methods on synthetic and real-world indoor scenes and prove the effectiveness of proposed regularizations. The code is available at https://github.com/kyleleey/RICO

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.08605")
get_code_for_paper("2303.08605")
have("2303.08605")

Connect an agent — have() is free.