AI Paper Atlas

Research map / 3D vision / 3D generation

Diffusion Models are Geometry Critics: Single Image 3D Editing Using Pre-Trained Diffusion Priors

Ruicheng Wang, Jianfeng Xiang, Jiaolong Yang, Xin Tong

ECCV 2024 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 11 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 diffusion-based 3D editing with depth warping instead of OBJect-3DIT, Zero123 or Stable-Zero123Ours · Single-image 3D editing benchmarkLPIPS: 0.132 -> 0.102Improved
run iteration 3 instead of stopping at iteration 1 (ablation)Ours · Single-image 3D editing benchmarkConfident Area: 0.235 -> 0.356Improved
run iteration 3 instead of stopping at iteration 1 (ablation)Ours · Single-image 3D editing benchmarkPerceptual Similarity: 0.890 -> 0.905Improved
add LoRA tuning to the undistortion phase (ablation)Ours · undistortion ablation (first iteration)visual layout and consistencyImproved
use noise-free DDIM inversion instead of noise addition in undistortion (ablation)Ours · undistortion ablation (first iteration)appearance consistencyImproved
user study versus other three methodsOurs · User studypreference rate (%): 71.36%Improved

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