AI Paper Atlas

Research map / 3D vision / 3D generation

Counting Stacked Objects

Corentin Dumery, Noa Etté, Aoxiang Fan, Ren Li, Jingyi Xu, Hieu Le, Pascal Fua

ICCV 2025 · 3D vision › 3D generation · approach: Monocular 3D object reconstruction · 7 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 ground-truth depth maps in training instead of estimated ones (ablation)3DC · Counting, 100 synthetic scenesNAE: 0.22 -> 0.28Hurt
use ground-truth depth maps in both training and evaluation (ablation)3DC · Counting, 100 synthetic scenesNAE: 0.22 -> 0.31Hurt
use ground-truth depth maps in training instead of estimated ones (ablation)3D C occupancy network · Occupancy ratio estimationR2: 0.79 -> 0.52Hurt
use ground-truth depth maps in both training and evaluation (ablation)3DC occupancy network · Occupancy ratio estimationR2: 0.79 -> 0.32Hurt
replace depth map input with RGB image for the gamma-network (ablation)3DC · Counting, 45 real scenesNAE: 0.36 -> 0.57Hurt
replace depth map input with RGB image for the gamma-network (ablation)3DC · Counting, 45 real scenessMAPE: 53.31 -> 74.33Hurt
decompose counting into volume and occupancy ratio vs direct count regression (ViT+H)3DC · Counting, 45 real scenesNAE: 0.94 -> 0.36Improved
decompose counting vs direct regression (ViT+H)3DC · Counting, 100 synthetic scenesNAE: 0.42 -> 0.22Improved
learned occupancy network vs depth-ratio baseline with linear correction (DepthCorrected)occupancy ratio estimation · Occupancy ratio estimationMAE: 0.10 -> 0.06Improved
learned network vs mean estimator for occupancy ratiooccupancy ratio estimation · Occupancy ratio estimationR2: 0.00 -> 0.79Improved
3DC vs averaged human guesses (Human-Vote)3DC · Counting, 45 real scenesNAE: 0.60 -> 0.36Improved
3DC vs 2D counters evaluated on visible objects onlyBMNet+ · Counting, 45 real scenessMAPE: 51.28 vs 53.31Mixed

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