AI Paper Atlas

Research map / 3D vision / 3D generation

Unsupervised Monocular 3D Keypoint Discovery from Multi-View Diffusion Priors

Subin Jeon, In Cho, Junyoung Hong, Woong Oh Cho, Seon Joo Kim

CVPR 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 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 multi-view diffusion features instead of DINOv2 features (ablation)KeyDiff3D · Human3.6MMPJPE: 136.17 -> 121.34Improved
use multi-view diffusion features instead of ResNet50 features (ablation)KeyDiff3D · Human3.6MMPJPE: 138.97 -> 121.34Improved
use multi-view diffusion features instead of CLIP features (ablation)KeyDiff3D · Human3.6MMPJPE: 143.23 -> 121.34Improved
lift via 3D feature volume instead of 2D keypoints plus triangulation (ablation)KeyDiff3D · Human3.6MMPJPE: 129.63 -> 121.34Improved
add generated virtual views beyond the input view (1 to 4) (ablation)KeyDiff3D · Human3.6MMPJPE: 166.29 -> 121.34Improved
increase virtual views from 4 to 5 (ablation)KeyDiff3D · Human3.6MMPJPE: 121.34 -> 119.77No clear effect
increase keypoints from 16 to 48 (ablation)KeyDiff3D · Human3.6MMPJPE: 127.99 -> 116.45Improved
use diffusion timestep 500 instead of 900 (ablation)KeyDiff3D · Human3.6MMPJPE: 131.26 -> 121.34Improved
increase training images from 2,200 to 8,800 (ablation)KeyDiff3D · Human3.6MMPJPE: 134.26 -> 121.34Improved
add random affine transformation to the input of reconstruction network (ablation)KeyDiff3D · Human3.6MMPJPE: 134.54 -> 121.34Improved
add camera rotation noise of 1.0 degree (ablation)KeyDiff3D · Human3.6MMPJPE: 121.34 -> 133.88Hurt
add camera rotation noise of 0.2 degree (ablation)KeyDiff3D · Human3.6MMPJPE: 121.34 -> 121.30No clear effect

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