AI Paper Atlas

Research map / 3D vision / 3D generation

StructLDM: Structured Latent Diffusion for 3D Human Generation

Tao Hu, Fangzhou Hong, Ziwei Liu

ECCV 2024 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 21 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
use structure-aligned normalization in latent diffusion instead of none (ablation)StructLDM diffusion · UBCFashionFID@4K: 20.13 -> 19.58Improved
use standard normalization in diffusion (ablation)StructLDM diffusion · UBCFashionFID@4K: 20.13 -> 24.86Hurt
use part-aware normalization in diffusion (ablation)StructLDM diffusion · UBCFashionFID@4K: 20.13 -> 25.02Hurt
use structured 2D latent instead of global 1D latent (ablation)auto-decoder · UBCFashion reconstructionLPIPSImproved
increase 2D latent resolution or channels (ablation)auto-decoder · UBCFashion reconstructionLPIPSImproved
increase 2D latent from 64x64x32 to 128x128x16 (ablation)auto-decoder · UBCFashion reconstructionLPIPSNo clear effect
add adversarial training to auto-decoder (ablation)auto-decoder · UBCFashion qualitativereconstruction qualityImproved
add latent noising and denoising (Diff-Render) to compositional blending (ablation)StructLDM · compositional generationcolor blending qualityImproved
add mapping network to smooth latents on single-view DeepFashion (ablation)auto-decoder · DeepFashiongeneration quality vs reconstruction fidelityMixed
StructLDM versus EVA3D on THUman2.0StructLDM · THUman2.0FID@50K: 124.54 -> 25.22Improved
StructLDM on single-view DeepFashion versus AG3DStructLDM · DeepFashionFID: 10.93 -> 20.82Hurt

Later papers that compared with this method

1 later accepted paper reports StructLDM as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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