AI Paper Atlas

Research map / 3D vision / Face and shape

3D Reconstruction of Objects in Hands without Real World 3D Supervision

Aditya Prakash, Matthew Chang, Matthew Jin, Ruisen Tu, Saurabh Gupta

ECCV 2024 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 5 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 multiview 2D mask supervision and shape priors instead of 3D lab supervisionAC-SDF / AC-OCC · MOW object generalizationF-score@5mm: 0.108 -> 0.121Improved
add HO3D and HOI4D lab 3D data to AC-SDF training (ablation)AC-SDF · MOW object generalizationF-score@5mm: 0.108 -> 0.095Hurt
add multiview occupancy loss L_occ (ablation)HORSE · MOW object generalizationChamfer distance (mm): 8.69 -> 7.26Improved
add consistency loss L_consis alone (ablation)HORSE · MOW object generalizationChamfer distance (mm): 8.69 -> 12.75Hurt
add L_consis on top of L_occ (ablation)HORSE · MOW object generalizationChamfer distance (mm): 7.26 -> 6.93Improved
add shape prior loss L_shape (ablation)HORSE · MOW object generalizationChamfer distance (mm): 6.93 -> 6.76Improved
add automated filtering of frames with inaccurate hand poses (ablation)HORSE · HO3D view generalizationF-score@5mm: 0.213 -> 0.234Improved
use ground truth hand pose instead of predicted (ablation)HORSE · HO3D view generalizationF-score@5mm: 0.234 -> 0.243No clear effect
use mask-guided rejection sampling instead of uniform sampling (ablation)HORSE · MOW object generalizationChamfer distance (mm): 10.29 -> 6.93Improved
add negative points from hand masks (ablation)HORSE mask-guided sampling · MOW object generalizationChamfer distance (mm): 7.69 -> 6.93Improved
use 2D slice discriminator instead of 3D volume discriminator (ablation)HORSE · MOW object generalizationChamfer distance (mm): 7.83 -> 6.76Improved
add 2D-slice discriminator (ablation)HORSE · MOW object generalizationF-score@5mm: 0.117 -> 0.121Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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