AI Paper Atlas

Research map / 3D vision / 3D generation

Single Image to Textured 3D Object Generation in Frequency Domain: From Theory to Pipeline

Qisen Wang, Yifan Zhao, Jia Li

IJCV 2026 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 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
add high-pass 2D prior guidance (frequency bound r=0.6) to the 3D prior (ablation)Morpheus3D · Realfusion15CLIPIQA: 0.707 -> 0.748Improved
add high-pass 2D prior guidance (r=0.6) (ablation)Morpheus3D · Realfusion15MANIQA: 0.433 -> 0.454Improved
add high-pass 2D prior guidance (r=0.6) (ablation)Morpheus3D · MorpheusObj30CLIP-Similarity: 0.816 -> 0.835Improved
use high-pass filtering (r=0.6) instead of full-pass 2D prior (ablation)Morpheus3D · Realfusion15MANIQA: 0.401 -> 0.454Improved
use high-pass filtering (r=0.6) instead of full-pass 2D prior (ablation)Morpheus3D · MorpheusObj30MANIQA: 0.438 -> 0.487Improved
vary frequency bound r across the middle range 0.2 to 0.8 (ablation)Morpheus3D · Realfusion15CLIP-Similarity: 0.824 -> 0.838No clear effect
increase 2D prior weight k2D from 3.0 to 5.0 (ablation)Morpheus3D · Realfusion15CLIPIQA: 0.748 -> 0.763No clear effect
add the 2D prior with weight k2D=1.0 versus none (ablation)Morpheus3D · Realfusion15CLIP-Similarity: 0.824 -> 0.835Improved
use Morpheus3D instead of Magic123Morpheus3D · MorpheusObj30MANIQA: 0.315 -> 0.487Improved
use Morpheus3D instead of Magic123Morpheus3D · Realfusion15MANIQA: 0.316 -> 0.454Improved
use Morpheus3D instead of Magic123 for training costMorpheus3D · banana casetraining time (minutes): 341.083 -> 111.981Improved
fine-tune the 3D prior with LoRA (VSD) instead of using SDS (ablation)Morpheus3D · MorpheusObj30reconstruction qualityHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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