AI Paper Atlas

Research map / 3D vision / Human pose estimation

I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image

Gyeongsik Moon, Kyoung Mu Lee

ECCV 2020 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 398 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 lixel heatmap target (with uncertainty) over direct coordinate regression (ablation)MeshNet · Human3.6MMPJPE: 114.3 -> 92.6Improved
add spatial relationship preservation (fully-convolutional heatmaps) (ablation)lixel heatmap MeshNet · Human3.6MMPJPE: 92.6 -> 86.2Improved
use lixel heatmap instead of SMPL parameter regression (ablation)MeshNet · Human3.6MMPJPE: 100.3 -> 86.2Improved
increase lixel heatmap resolution from 8 to 64 (ablation)MeshNet · Human3.6MMPJPE: 100.2 -> 94.8 -> 86.2Improved
use lixel heatmap instead of voxel heatmap at 8 resolution (ablation)MeshNet · Human3.6MGPU memory: voxel 4.3 GB at 8x8x8 vs lixel 3.4 GB at 8,8,8Improved
add PoseNet cascaded before MeshNet (ablation)I2L-MeshNet · Human3.6MMPJPE: 86.2 -> 81.8Improved
feed ground-truth 3D pose to MeshNet (ablation)I2L-MeshNet · Human3.6MMPJPE: 86.2 -> 25.5Improved
marginalize at the last upsampling output instead of on ResNet output (ablation)MeshNet · Human3.6MMPJPE: 93.5 -> 86.2Improved
use average pooling for marginalization instead of max pooling (ablation)MeshNet · Human3.6MMPJPE: 93.5 -> 86.2Improved
use average pooling instead of learned weighted sum (ablation)MeshNet · Human3.6MMPJPE: 89.4 -> 86.2Improved
use lixel 1D heatmap instead of 2.5D heatmap (ablation)MeshNet · Human3.6MMPJPE: 100.4 -> 94.8 at 32 resolutionImproved
add MeshNet pose loss L_pose (ablation)I2L-MeshNet · Human3.6MMPJPE: 84.5 -> 81.8Improved

Later papers that compared with this method

12 later accepted papers report I2L-MeshNet as a baseline in their results tables; 12 of them report a better number on most of the results they share with it.

4 more not listed.

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