AI Paper Atlas

Research map / 3D vision / Human pose estimation

SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model

Yukai Shi, Weiyu Li, Zihao Wang, Hongyang Li, Xingyu Chen, Ping Tan, Lei Zhang

CVPR 2026 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 12 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 self-attention (GSA) (ablation)SceneMaker pose model · Pose estimation ablation (GT meshes, 3D-Front, trained from scratch)CD-S: 0.0340 -> 0.0242Improved
add global self-attention (GSA) (ablation)SceneMaker pose model · Pose estimation ablation (GT meshes, 3D-Front, trained from scratch)F-Score-O: 0.6293 -> 0.8121Improved
add local self-attention (LSA) (ablation)SceneMaker pose model · Pose estimation ablation (GT meshes, 3D-Front, trained from scratch)CD-O: 0.0901 -> 0.0294Improved
add local self-attention (LSA) (ablation)SceneMaker pose model · Pose estimation ablation (GT meshes, 3D-Front, trained from scratch)IoU-B: 0.7733 -> 0.7555Mixed
add decoupled local cross-attention (LCA) (ablation)SceneMaker pose model · Pose estimation ablation (GT meshes, 3D-Front, trained from scratch)CD-O: 0.0429 -> 0.0294Improved
add decoupled local cross-attention (LCA) (ablation)SceneMaker pose model · Pose estimation ablation (GT meshes, 3D-Front, trained from scratch)IoU-B: 0.7882 -> 0.7555Mixed
give complete point clouds instead of single-image estimate (ablation)SceneMaker pose model · Pose estimation ablation (GT meshes, 3D-Front, trained from scratch)CD-S: 0.0242 -> 0.0064Improved
add 200K open-set scene dataset (ablation)SceneMaker · Open-set test (1K scenes)CD-S: 0.1538 -> 0.0285Improved
add 200K open-set scene dataset (ablation)SceneMaker · 3D-Front indoor test (1K scenes, severe occlusion)CD-S: 0.0381 -> 0.0470Hurt
fine-tune image editing model on 10K de-occlusion dataset (vs Flux Kontext)De-occlusion model · De-occlusion validation (1K images, 500 classes)PSNR: 13.91 -> 15.03Improved
decouple de-occlusion from 3D generation (vs Amodal3R)SceneMaker · Occluded object generation (3D-Front renders)Chamfer distance: 0.0443 -> 0.0409Improved
SceneMaker vs MIDI on MIDI test setSceneMaker · MIDI test set (1K scenes)CD-S: 0.080 -> 0.051Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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