AI Paper Atlas

Research map / 3D vision / 3D generation

Photo3D: Advancing Photorealistic 3D Generation through Structure-Aligned Detail Enhancement

Xinyue Liang, Zhiyuan Ma, Lingchen Sun, Yanjun Guo, Lei Zhang

CVPR 2026 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 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
fine-tune Trellis on Photo3D-MV with realism lossTrellis · ImageNet testMUSIQ: 69.108 -> 72.385Improved
fine-tune Step1X-3D texturing on Photo3D-MVStep1X-3D · ImageNet testMUSIQ: 70.471 -> 72.215Improved
fine-tune TexGaussian on Photo3D-MVTexGaussian · ImageNet testMUSIQ: 65.003 -> 70.273Improved
fine-tune Trellis on Photo3D-MVTrellis · ImageNet testGemini winning rate %: 68.1 -> 95.0Improved
fine-tune Trellis on Photo3D-MVTrellis · Real 3D datasetsHuman realism score: 3.9 -> 4.8Improved
fine-tune Step1X-3D on Photo3D-MVStep1X-3D · Real 3D datasetsMANIQA: 0.416 -> 0.424Improved
fine-tune TexGaussian on Photo3D-MVTexGaussian · Real 3D datasetsMANIQA: 0.441 -> 0.444No clear effect
add perceptual feature adaptation loss Ladapt (ablation)Photo3D (Trellis) · ImageNet testMANIQA: 0.308 -> 0.470Improved
add semantic structure matching loss Lmatch (ablation)Photo3D (Trellis) · ImageNet testMUSIQ: 71.069 -> 72.385Improved
use L2 loss instead of realism loss (ablation)Photo3D (Trellis) · ImageNet testMUSIQ: 72.385 -> 55.281Hurt
use Gram loss instead of realism loss (ablation)Photo3D (Trellis) · ImageNet testMUSIQ: 72.385 -> 69.646Hurt
use GAN loss instead of realism loss (ablation)Photo3D (Trellis) · ImageNet testMUSIQ: 72.385 -> 72.058Mixed

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