AI Paper Atlas

Research map / 3D vision / Face and shape

Hierarchically Structured Neural Bones for Reconstructing Animatable Objects from Casual Videos

Subin Jeon, In Cho, Minsu Kim, Woong Oh Cho, Seon Joo Kim

ECCV 2024 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 0 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
use the hierarchy (3 depths, 24 bones) instead of 24 bones in a single depth (ablation)hierarchical neural bones · Samba reconstructionChamfer distance: 7.16 -> 6.15Improved
use the hierarchy instead of a single depth with 24 bones (ablation)hierarchical neural bones · Swing reconstructionChamfer distance: 8.83 -> 7.11Improved
use bone occupancy regularization instead of Sinkhorn divergence (single depth, 24 bones) (ablation)hierarchical neural bones · Samba reconstructionChamfer distance: 7.17 -> 7.16Improved
add bone regularization on a single-depth model (ablation)hierarchical neural bones · Samba reconstruction (1 depth, 24 bones)Chamfer distance: 6.84 -> 7.16Hurt
use hierarchical bones instead of BANMo with fewer videos (4 vs 8)Samba reconstruction · Samba, number of input videosChamfer distance: BANMo 8 vids 7.22 vs Ours 4 vids 7.05Improved
use hierarchical bones instead of skeleton-based RAC on Swingreconstruction · Swing reconstructionF-score F2: 70.33 -> 65.88Hurt
use hierarchical bones instead of BANMo for retargeting at 50 stepsreanimation · Samba retargetingChamfer distance: 2.75 -> 2.15Improved
use tree-structured bones for manipulation instead of unstructured BANMo bonesmanipulation · User study (12 participants), averagetime to reach target pose: 5m 5s -> 3m 50sImproved

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