AI Paper Atlas

Research map / 3D vision / 3D generation

Associative3D: Volumetric Reconstruction from Sparse Views

Shengyi Qian, Linyi Jin, David F. Fouhey

ECCV 2020 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 25 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 stitching stage with joint reasoning over objects and cameras (ablation)Feedforward · SUNCG testAP (all errors): 21.2 -> 23.3Improved
add stitching stage (ablation)Feedforward · SUNCG testAP (translation only): 31.7 -> 38.4Improved
add stitching stage (ablation)Feedforward · SUNCG test (top 25%)AP (all errors): 41.6 -> 48.3Improved
merge duplicate objects with NMS (ablation)Feedforward · SUNCG testAP (all errors): 21.2 -> 21.1No clear effect
merge objects by raw top-1 affinity instead of stitching (ablation)Feedforward · SUNCG testAP (all errors): 21.2 -> 15.0Hurt
add stitching stage to affinity-based correspondence (ablation)affinity top-1 · SUNCG test object correspondenceAP: 49.4 -> 60.0Improved
use top-1 affinity with stitching confidence instead of raw affinity (ablation)affinity · SUNCG test object correspondenceAP: 38.8 -> 49.4Improved
pick camera pose by stitching rather than top-1 camera branch prediction (ablation)relative camera pose · SUNCG testtranslation error <= 1m (%): 41.26 -> 54.89Improved
pick camera pose by stitching rather than top-1 (ablation)relative camera pose · SUNCG testrotation error <= 30 deg (%): 77.56 -> 78.31No clear effect
use two views instead of a single view3D-RelNet vs Associative3D · SUNCG testAP (all errors): 13.7 -> 23.3Improved
average rotation of matched objects instead of random pick (ablation)stitching stage · SUNCG test (top 50%)AP (all errors): 38.8 -> 31.4Hurt
average shape vector of matched objects instead of random pick (ablation)stitching stage · SUNCG test (top 50%)AP (all errors): 38.8 -> 38.8No clear effect

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