AI Paper Atlas

Research map / 3D vision / 3D generation

Towards High-Fidelity Single-View Holistic Reconstruction of Indoor Scenes

Haolin Liu, Yujian Zheng, Guanying Chen, Shuguang Cui, Xiaoguang Han

ECCV 2022 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 32 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add global instance feature to pixel-aligned feature (ablation)InstPIFu · 3D-FUTURE objectsChamfer distance (x10^-3): 17.95 -> 16.42Improved
add attentional channel filtering to C0 (ablation)InstPIFu · 3D-FUTURE objectsChamfer distance (x10^-3): 16.42 -> 15.54Improved
add spatial-guided mask supervision to C0 (ablation)InstPIFu · 3D-FUTURE objectsChamfer distance (x10^-3): 16.42 -> 15.28Improved
combine channel filtering and mask supervision (ablation)InstPIFu · 3D-FUTURE objectsF-Score: 58.62 -> 61.32Improved
predict objects in canonical coordinates instead of camera coordinates (ablation)InstPIFu · 3D-FUTURE objectsChamfer distance (x10^-3): 41.64 -> 14.46Improved
use predicted 2D detections instead of GT boxes at test time (ablation)InstPIFu · 3D-FUTURE objectsChamfer distance (x10^-3): 14.46 -> 15.35Hurt
use instance-aligned implicit background instead of Adabins depthroom background · 3D-FRONTChamfer distance: 0.573 -> 0.481Improved
use InstPIFu instead of MGN (explicit mesh)object reconstruction · 3D-FUTUREChamfer distance (x10^-3): 14.07 -> 14.46Hurt
use InstPIFu instead of MGNobject reconstruction · 3D-FUTUREF-Score: 55.64 -> 61.32Improved
use InstPIFu instead of MGN on prior splitobject reconstruction · Pix3D (split of prior work)Chamfer distance (x10^-3): 6.84 -> 13.60Hurt
use InstPIFu instead of MGN on unseen shapesobject reconstruction · Pix3D (non-overlapped split)Chamfer distance (x10^-3): 44.32 -> 24.65Improved
use InstPIFu instead of baseline for whole sceneholistic scene · 3D-FRONT whole sceneChamfer distance: 0.290 -> 0.172Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy