AI Paper Atlas

Research map / 3D vision / Face and shape

Transformers As Meta-Learners for Implicit Neural Representations

Yinbo Chen, Xiaolong Wang

ECCV 2022 · 3D vision › Face and shape · approach: Implicit neural representation design · 60 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
increase weight groups G from 1 to 64 (ablation)Transformer meta-learner · CelebA image regressionPSNR: 25.63 -> 31.96Improved
increase weight groups from 1 to 4 (ablation)Transformer meta-learner · CelebA image regressionPSNR: 25.63 -> 27.89Improved
increase weight groups from 4 to 16 (ablation)Transformer meta-learner · CelebA image regressionPSNR: 27.89 -> 29.93Improved
increase weight groups from 16 to 64 (ablation)Transformer meta-learner · CelebA image regressionPSNR: 29.93 -> 31.96Improved
replace gradient-based Learned Init with Transformer hypernetworkINR image regression · CelebAPSNR: 30.37 -> 31.96Improved
replace Learned Init with Transformer hypernetworkINR image regression · ImagenettePSNR: 27.07 -> 29.01Improved
replace Learned Init with Transformer hypernetworksingle-view NeRF · ShapeNet chairsPSNR: 18.85 -> 19.66Improved
replace Learned Init with Transformer hypernetworksingle-view NeRF · ShapeNet carsPSNR: 22.80 -> 23.78Improved
replace Learned Init with Transformer hypernetworksingle-view NeRF · ShapeNet lampsPSNR: 22.35 -> 22.76Improved
add 100 test-time optimization steps (ablation)Transformer meta-learner · ShapeNet lamps (1-view)PSNR: 22.76 -> 24.71Improved
add 100 test-time optimization steps (ablation)Transformer meta-learner · ShapeNet chairs (2-view)PSNR: 21.10 -> 23.59Improved
add a second input view (ablation)Transformer meta-learner · ShapeNet chairs (no test-time opt.)PSNR: 19.66 -> 21.10Improved

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