AI Paper Atlas

Research map / 3D vision / 3D generation

Make-It-3D: High-fidelity 3D Creation from A Single Image with Diffusion Prior

Junshu Tang, Tengfei Wang, Bo Zhang, Ting Zhang, Ran Yi, Lizhuang Ma, Dong Chen

ICCV 2023 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 315 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
add texture-enhancement refine stage (textured point cloud) after coarse NeRF (ablation)Make-It-3D · Test benchmark (400 images)LPIPS: 0.2354 -> 0.0780Improved
add refine stage on DTU (ablation)Make-It-3D · DTUCLIP score: 87.50% -> 95.65%Improved
use timestep-split SDS/CLIP-D (threshold 400) instead of simultaneous SDS+CLIP-D (ablation)Make-It-3D coarse stage · Test benchmark (400 images)Contextual distance: 2.32 -> 1.74Improved
optimize SDS and CLIP-D simultaneously rather than switching by timestep (ablation)Make-It-3D coarse stage · Test benchmark (400 images)CLIP score: 87.50% -> 84.01%Hurt
use only SDS loss without CLIP-D (ablation)Make-It-3D coarse stage · Test benchmark (400 images)LPIPS: 0.1427 -> 0.3045Hurt
use only CLIP-D loss without SDS (ablation)Make-It-3D coarse stage · Test benchmark (400 images)CLIP score: 87.50% -> 80.27%Hurt
vary timestep threshold between SDS and CLIP-D (300, 400, 500) (ablation)Make-It-3D coarse stage · Test benchmark (400 images)Contextual distance: 2.19 / 1.74 / 2.23Mixed
add depth prior (Pearson correlation) at reference view (ablation)Make-It-3D coarse stage · qualitativegeometry plausibilityImproved
use learnable point descriptors and NeRF texture initialization in refine stage (ablation)Make-It-3D refine stage · qualitativetexture qualityImproved
sample timesteps only from 200 to 600 in SDS (ablation)Make-It-3D coarse stage · qualitativegeometry and alignmentImproved

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