AI Paper Atlas

Research map / 3D vision / 3D generation

Lafite: A Generative Latent Field for 3D Native Texturing

Chia-Hao Chen, Yuan-Chen Guo, Zi-Xin Zou, Ze Yuan, Guan Luo, Xiaojuan Qi, Ding Liang, Yan-Pei Cao, Song-Hai Zhang

CVPR 2026 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 7 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
encode colored point cloud directly instead of projected DINO features (TRELLIS-RF128)LaFiTe VAE · VAE reconstruction 128PSNR: 23.07 -> 34.62Improved
encode colored point cloud directly instead of projected DINO features (TRELLIS-GS64)LaFiTe VAE · VAE reconstruction 64PSNR: 21.37 -> 33.57Improved
encode colored point cloud directly instead of projected DINO featuresLaFiTe VAE · VAE reconstruction 64LPIPS: 0.116 -> 0.053Improved
increase input points from 20,480 to 2,048,000 (ablation)LaFiTe VAE · Reconstruction, 128 resolutionPSNR: 26.07 -> 34.30Improved
increase input points from 204,800 to 2,048,000 (ablation)LaFiTe VAE · Reconstruction, 64 resolutionPSNR: 32.22 -> 33.49Improved
increase points from 2,048,000 to 4,096,000 (ablation)LaFiTe VAE · Reconstruction, 128 resolutionPSNR: 34.30 -> 34.45Improved
fine-tune VAE at 128 resolution instead of using 64 model (starred)LaFiTe VAE · VAE reconstructionPSNR: 34.48 -> 34.62Improved
use LaFiTe instead of UniTEXLaFiTe · Image-conditioned (unshaded)FID: 106.45 -> 107.46Hurt
use LaFiTe instead of MaterialMVPLaFiTe · Image-conditioned (shaded)FD_CLIP: 48.71 -> 46.28Improved
use LaFiTe instead of MaterialMVPLaFiTe · Image-conditioned (shaded)FID: 101.66 -> 101.91Hurt
use LaFiTe instead of SeqTexLaFiTe · Image-conditioned (shaded)KD_DINO: 0.032 -> 0.027Improved
condition on geometry latent from monochrome point cloud instead of 2D projected mapsLaFiTe · Texture generationqualityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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