AI Paper Atlas

Research map / 3D vision / 3D generation

LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation

Yushi Lan, Fangzhou Hong, Shuai Yang, Shangchen Zhou, Xuyi Meng, Bo Dai, Xingang Pan, Chen Change Loy

ECCV 2024 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 43 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 2D conv decoder with ViT block (ablation)LN3Diff++ VAE · Objaverse subset 7KPSNR@100K: 17.46 -> 18.92Improved
use DiT block with latent injected via adaLN instead of ViT block (ablation)LN3Diff++ VAE decoder · Objaverse subset 7KPSNR@100K: 18.92 -> 20.61Improved
add Plucker camera embedding to encoder input (ablation)LN3Diff++ VAE · Objaverse subset 7KPSNR@100K: 20.61 -> 21.29Improved
add cross-plane attention (ablation)LN3Diff++ VAE decoder · Objaverse subset 7KPSNR@100K: 21.29 -> 21.70Improved
add self-plane attention (ablation)LN3Diff++ VAE decoder · Objaverse subset 7KPSNR@100K: 21.70 -> 21.95Improved
add novel-view discriminator for monocular data (ablation)LN3Diff++ VAE · FFHQnovel-view plausibility (qualitative)Improved
add DINO features to CLIP for image conditioning (ablation)LN3Diff++ image-conditioned diffusion · Objaversefaithfulness (qualitative)Improved
diffuse in compact VAE latent space instead of latent-free neural fieldsLN3Diff++ · Sampling speed, 1 V100seconds per instance: 5.7 vs 8.1 (SSDNeRF), 15.8 (RenderDiffusion), 18.7 (DiffRF)Improved
train with only V=2 views instead of 50 viewsLN3Diff++ vs SSDNeRF · ShapeNet Car COVCOV (%): 43.12 vs 67.82 (SSDNeRF V=50)Hurt
fine-tune VAE with Flexicubes SDF for mesh extractionLN3Diff++ · Objaverse image-to-3DFID: 23.01 -> 36.28Hurt
reduce GAN weight of novel-view discriminator to limit background artifactsLN3Diff++ on FFHQ · FFHQ3D plausibilityMixed

Earlier methods this paper compares with

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