AI Paper Atlas

Research map / 3D vision / Face and shape

EvAC3D: From Event-Based Apparent Contours to 3D Models via Continuous Visual Hulls

Ziyun Wang, Kenneth Chaney, Kostas Daniilidis

ECCV 2022 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 18 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
carve per event with ACEs instead of 24-view mask visual hullvisual hull carving · MOEC-3D, ground-truth ACEs (mean)Chamfer distance: 3.2652 -> 2.4267Improved
carve per event with ACEs instead of 12-view mask visual hullvisual hull carving · MOEC-3D, ground-truth ACEs (mean)Chamfer distance: 4.3856 -> 2.4267Improved
use ACE-based carving instead of 24-view mask carvingvisual hull carving · MOEC-3D, ground-truth ACEs (mean)normal consistency: 0.9377 -> 0.9487Improved
use EvAC3D with network-predicted ACEs instead of Mask 24visual hull carving · MOEC-3D real objects (mean)Chamfer distance: 3.614 -> 2.551Improved
use EvAC3D instead of Mask 12 on real objectsvisual hull carving · MOEC-3D real objects (mean)Chamfer distance: 8.312 -> 2.551Improved
use EvAC3D instead of masks from reconstructed images (24 views)visual hull carving · MOEC-3D real objects (mean)Chamfer distance: 3.602 -> 2.551Improved
use EvAC3D instead of E3D silhouette optimizationevent-based reconstruction · MOEC-3D real objects (mean)Chamfer distance: 8.837 -> 2.551Improved
use EvAC3D instead of 24-view carving to cut operationsvisual hull carving · MOEC-3D real objects (mean)number of carving operations: 6,661,111 -> 1,921,976Improved
increase mask views from 12 to 24 (ablation)mask-based carving · MOEC-3D real objects (mean)Chamfer distance: 8.312 -> 3.614Improved
ACEs versus 24-view mask carving on individual objects with ground-truth ACEsEvAC3D · MOEC-3D per objectChamfer distance: Jello (b) 5.9083 vs 4.4409; Vitamin 2.6190 vs 1.4478Mixed

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