AI Paper Atlas

Research map / 3D vision / 3D generation

Learn to Optimize Denoising Scores: A Unified and Improved Diffusion Prior for 3D Generation

Xiaofeng Yang, Yiwen Chen, Cheng Chen, Chi Zhang, Yi Xu, Xulei Yang, Fayao Liu, Guosheng Lin

ECCV 2024 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 5 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 LODS (learnable null embedding) instead of VSD loss in ProlificDreamertext-to-3D with Stable Diffusion · T3Bench (all categories)Average: 43.3 -> 47.3Improved
use LODS (LoRA) instead of VSD losstext-to-3D with Stable Diffusion · T3Bench (all categories)Average: 43.3 -> 45.4Improved
use embedding-based LODS instead of LoRA-based LODS (ablation)LODS · T3Bench (all categories)Average: 45.4 -> 47.3Improved
replace SDS loss with LODS inside Magic123 for the Stable Diffusion priorMagic123 · NeRF4 image-to-3DPSNR: 24.62 -> 24.83No clear effect
replace SDS loss with LODS inside Magic123Magic123 · RealFusion15 image-to-3DLPIPS: 0.10 -> 0.09No clear effect
start with low classifier-free guidance weight (30) in embedding LODS (ablation)LODS (Emb) · text-to-3D qualitativetexture detailHurt
increase initial CFG weight beyond 1000 up to infinity (ablation)LODS (Emb) · text-to-3D qualitative3D qualityHurt
combine embedding-based and LoRA-based LODS (ablation)LODS · 3D generationgeneration qualityNo clear effect
gradually decrease the CFG weight during optimization (ablation)SDS loss · text-to-3Dgeneration qualityNo clear effect

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