AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Generative Refinement Network for Visual Synthesis

Jian Han, Jinlai Liu, Jiahuan Wang, BINGYUE PENG, Zehuan Yuan

ECCV 2026 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling

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 global refinement instead of mask-based generation (ablation)GRN · ImageNet 256 class-conditionalFID: 18.13 -> 3.63Improved
add global refinement with identical decoding hyperparameters (ablation)GRN · ImageNet 256 class-conditionalFID: 185.62 -> 3.63Improved
use random selection map instead of confidence-based selection (ablation)GRN · ImageNet 256 class-conditionalFID: 10.64 -> 3.63Improved
add complexity-aware entropy-guided sampling (ablation)GRN_bit-B · ImageNet 256 class-conditionalFID: 3.56 -> 3.47Improved
increase HBQ rounds from 4 to 8 (16 channels) (ablation)HBQ tokenizer · Video tokenizer reconstructionrFVD: 163.6 -> 144.9Improved
increase latent channels from 16 to 64 (ablation)HBQ (M=4) tokenizer · Video tokenizer reconstructionPSNR: 30.40 -> 33.97Improved
train longer with tuned GAN weight (HBQ*) (ablation)HBQ (M=4, 64 ch) · Video tokenizer reconstructionrFVD: 50.6 -> 26.3Improved
raise GAN loss weight from 0.001 to 0.02 (ablation)HBQ tokenizer (64 ch) · Video tokenizer reconstructionrFVD / PSNR: rFVD 48.6 -> 28.6; PSNR 34.05 -> 33.73Mixed
use HBQ M=4 instead of M=2 when scaling from GRN-B to GRN-L (ablation)GRN · ImageNet 256 class-conditionalFIDMixed
predict bits instead of indices (GRN-L) (ablation)GRN · ImageNet 256 class-conditionalFID: 2.64 -> 2.47Improved
predict bits instead of indices (GRN-B) (ablation)GRN · ImageNet 256 class-conditionalFIDNo clear effect
predict absolute bits instead of relative bits (flip) (ablation)GRN_bit · ImageNet 256 class-conditionalstructural stabilityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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