AI Paper Atlas

Research map / 3D vision / Face and shape

AUTO3D: Novel view synthesis through unsupervisely learned variational viewpoint and global 3D representation

Xiaofeng Liu, Tong Che, Yiqun Lu, Chao Yang, Site Li, Jane You

ECCV 2020 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 22 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 AdaIN conditioning of the pose code in the decoder (ablation)AUTO3D · ShapeNet Chair (single input)SSIM: 0.83 -> 0.87Improved
add AdaIN conditioning of the pose code in the decoder (ablation)AUTO3D · ShapeNet Chair (single input)L1 error: 12.65 -> 12.62No clear effect
add adversarial (GAN) loss (ablation)AUTO3D · ShapeNet Chair (single input)SSIM: 0.83 -> 0.87Improved
add tensor slides (ablation)AUTO3D · ShapeNet Chair (single input)SSIM: 0.85 -> 0.87Improved
add tensor slides for training speed (ablation)AUTO3D · ShapeNettraining speed: 1.5 timesImproved
add spatial correlation module (SCM) with a single input (ablation)AUTO3D · ShapeNet Chair (single input)L1 error: 12.62 -> 12.62No clear effect
add SCM with multiple input views (ablation)AUTO3D · ShapeNet Chair (4 input views)L1 error: 0.112 -> 0.106Improved
add SCM with multiple input views (ablation)AUTO3D · ShapeNet Chair (4 input views)SSIM: 0.929 -> 0.938Improved
add spatial-aware Gaussian term to SCM (ablation)AUTO3D SCM · ShapeNet Chair (4 input views)L1 error: 0.110 -> 0.106Improved
add local diffusion-based complementary-aware formulation to SCM (ablation)AUTO3D SCM · ShapeNet Chair (4 input views)L1 error: 0.108 -> 0.106Improved
pre-train the encoder with unsupervised AUTO3D before 3D landmark training3D face landmark estimator · AFLW2000-3D 3D landmark estimationmean NME (%): 12.7% -> 6.9%Improved
increase the number of input views from 1 to 4AUTO3D · ShapeNet ChairL1 error: 0.182 -> 0.106Improved

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