AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Advancing Text-to-3D Generation with Linearized Lookahead Variational Score Distillation

Yu Lei, Bingde Liu, Qingsong Xie, Haonan Lu, Zhijie Deng

ICCV 2025 · Image generation › Fast diffusion sampling · approach: Distributional control of diffusion · 0 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
update the LoRA model more steps per iteration (gamma 1 to 10) (ablation)VSD · hamburger prompt, NeRF stagequalitative 3D quality: gamma = 1, 2, 5, 10No clear effect
add lookahead (update LoRA before the 3D model)VSD · DreamFusion gallery (20 prompts)Averaged FID: 301.54 -> 496Hurt
add lookahead (update LoRA before the 3D model)VSD · DreamFusion gallery (20 prompts)Averaged CLIP angle: 0.324 -> 0.337Hurt
add lookahead (update LoRA before the 3D model) (ablation)VSD · hamburger prompt, NeRF stagespeed of geometry and texture formationMixed
increase LoRA steps gamma to 2 and 5 in lookahead VSD (ablation)L-VSD · hamburger prompt, NeRF stagequalitative 3D quality: gamma = 2, 5Hurt
scale LoRA learning rate by 0.1 (ablation)L-VSD · hamburger prompt, NeRF stagequalitative 3D quality: learning rate x 0.1Mixed
add linearization of the lookahead correction (first-order term only)L-VSD · DreamFusion gallery (20 prompts)Averaged FID: 496 -> 284.06Improved
replace VSD with L2-VSDVSD · DreamFusion gallery (20 prompts)Averaged FID: 301.54 -> 284.06Improved
replace VSD with L2-VSDVSD · DreamFusion gallery (20 prompts)Averaged CLIP angle: 0.324 -> 0.285Improved
use high-order term instead of linear term for correction (HL-VSD) (ablation)L2-VSD · qualitative prompts (telephone, exercise bike)qualitative 3D qualityHurt
vary lookahead scale eta, down to 1e-3 (ablation)L2-VSD · hamburger promptqualitative 3D quality: eta = 1e-3No clear effect
use last-layer approximation for the correction (ablation)L2-VSD · threestudio coarse stagetime cost (s/iteration): 1.0 -> 0.8 s/iteration; total time 2.7 -> 2.5 hrsMixed

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