AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Transformer Based Pluralistic Image Completion With Reduced Information Loss

Qiankun Liu, Yuqi Jiang, Zhentao Tan, Dongdong Chen, Ying Fu, Qi Chu, Gang Hua, Nenghai Yu

TPAMI 2024 · Image generation › Autoregressive and latent generation · approach: Hierarchical VQ-VAE generation · 40 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 patch-based encoder (vs CNN encoder) (ablation)PUT conference config · Places2 256x256 (mask 10-60%)FID: 179.294 -> 22.121Improved
add dual-codebook (ablation)PUT conference config · Places2 256x256 (mask 10-60%)FID: 28.634 -> 22.121Improved
add dual-codebook (ablation)PUT conference config · FFHQ 256x256 (mask 10-60%)FID: 13.960 -> 14.554Hurt
add reference-branch guidance in decoder (ablation)PUT conference config · Places2 256x256 (mask 10-60%)FID: 25.084 -> 22.121Improved
feed un-quantized features to UQ-Transformer (ablation)PUT conference config · Places2 256x256 (mask 10-60%)FID: 75.625 -> 22.121Improved
add random quantization during training (ablation)PUT conference config · Places2 256x256 (mask 10-60%)FID: 44.588 -> 22.121Improved
increase codebook K from 512 to 8192 (ablation)PUT · Places2 256x256 (mask 10-60%)FID: 22.696 -> 23.921Hurt
add Gumbel-softmax relaxation and mask embedding (ablation)PUT K=8192 · Places2 256x256 (mask 10-60%)FID: 23.921 -> 21.538Improved
add mask embedding (ablation)PUT K=8192 with Gumbel-softmax · Places2 256x256 (mask 10-60%)FID: 24.179 -> 21.538Improved
train with conditions, give semantic and structural maps (ablation)PUT · ImageNet 256x256 (mask 10-60%)FID: 26.402 -> 17.916Improved
train with conditions but give none at inference (ablation)PUT · Places2 256x256 (mask 10-60%)FID: 21.234 -> 21.851No clear effect
replace 20 removed categories with unknown categories (ablation)PUT Sem.113 · ImageNet 256x256 (mask 10-60%)FID: 24.877 -> 23.674Improved

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