AI Paper Atlas

Research map / 3D vision / Face and shape

Learning Joint 2D-3D Representations for Depth Completion

Yun Chen, Bin Yang, Ming Liang, Raquel Urtasun

ICCV 2019 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 179 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 stride-1 2D conv branch to the fuse block (ablation)FuseNet · KITTI val (C=32, N=12)RMSE (mm): 840 -> 803Improved
add stride-2 2D conv branch to the fuse block (ablation)FuseNet · KITTI val (C=32, N=12)RMSE (mm): 826 -> 803Improved
add 3D continuous convolution branch to the fuse block (ablation)FuseNet · KITTI val (C=32, N=12)RMSE (mm): 817 -> 803Improved
vary number of nearest neighbors K from 3 to 15 in continuous conv (ablation)FuseNet · KITTI val (C=32, N=9)RMSE (mm): 813, 810, 810, 816, 812No clear effect
train with smooth l1 instead of l2 loss (ablation)FuseNet · KITTI val (C=64, N=12)MAE (mm): 232 -> 197Improved
train with smooth l1 instead of l2 loss (ablation)FuseNet · KITTI val (C=64, N=12)RMSE (mm): 790 -> 839Hurt
fine-tune l2 model with l2 + smooth l1 loss (ablation)FuseNet · KITTI val (C=64, N=12)RMSE (mm): 790 -> 785Improved
fine-tune l2 model with l2 + smooth l1 loss (ablation)FuseNet · KITTI val (C=64, N=12)MAE (mm): 232 -> 217Improved

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