AI Paper Atlas

Research map / 3D vision / 3D generation

AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer

Lingting Zhu, Shengju Qian, Haidi Fan, Jiayu Dong, Zhenchao Jin, SiweiZhou, Dong Gen, Xin Wang, Lequan Yu

ICLR 2026 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 1 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
replace PCG with AssetFormerAssetFormer · modular building assetsFID: 108.476 -> 55.186Improved
use top-k sampling instead of greedy search (ablation)AssetFormer · modular building assetsFID: 63.351 -> 55.186Improved
use top-k sampling instead of beam search (ablation)AssetFormer · modular building assetsFID: 63.333 -> 55.186Improved
re-order tokens with DFS instead of raw order (ablation)AssetFormer · modular building assetsFID: 65.215 -> 55.186Improved
re-order tokens with DFS instead of BFS (ablation)AssetFormer · modular building assetsFID: 61.620 -> 55.186Improved
use randomized token order (RAR) instead of DFS (ablation)AssetFormer · modular building assetsFID: 55.186 -> 83.561Hurt
add real collected data to synthesized data (ablation)AssetFormer · modular building assetsFID: 113.560 -> 55.186Improved
add synthesized PCG data to collected data (ablation)AssetFormer · modular building assetsFID: 63.381 -> 55.186Improved
SlowFast decoding with small draft model vs target aloneAssetFormer-B · modular building assetsspeed (token/s): 80.62 -> 119.02Improved
SlowFast decoding vs target alone on qualityAssetFormer-B · modular building assetsFID: 55.186 -> 55.831No clear effect
choice of sampling method on CLIP score (ablation)AssetFormer · modular building assetsCLIP: 0.319 / 0.321 / 0.320No 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