AI Paper Atlas

Research map / 3D vision / 3D generation

Monocular Avatar Reconstruction via Cascaded Diffusion Priors and UV-Space Differentiable Shading

Hong Li, Minqi Meng, Yanjun Liang, Chongjie Ye, Houyuan Chen, Weiqing Xiao, Xianda Guo, Guojun Lei, Xuhui Liu, Chaojie Yang, Yanlun Peng, HAO ZHAO and 1 more

ECCV 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 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 multi-scale fusion with frozen DINOv3 to the ConvNeXt encoder (ablation)geometry encoder · REALYNMSE (mm): 1.806 -> 1.490Improved
add enhanced 88-point landmark loss (ablation)geometry encoder · REALY mouth regionNMSE (mm): 1.670 -> 1.376Improved
add enhanced landmark loss (ablation)geometry encoder · REALY overallNMSE (mm): 1.518 -> 1.490 overall; mouth 1.670 -> 1.376; nose 1.457 -> 1.619; cheeks 1.140 -> 1.181Mixed
replace ConvNeXt baseline with full geometry model (ablation)geometry encoder · REALYNMSE (mm): 2.514 -> 1.490Improved
use linear 3DMM with DINOv3 priors vs nonlinear MoSARgeometry · REALYNMSE (mm): 1.500 -> 1.490Improved
compare with HiFace and 3DDFA-V3geometry · REALYNMSE (mm): 1.275 / 1.435 vs 1.490Hurt
use Inpainting LoRA vs UV-IDM/HRNtexture inpainting · UV texture inpaintingPSNR: 19.39 -> 22.44 (vs UV-IDM)Improved
use Light-Homogenization LoRA vs FFHQ-UVlight homogenization · light homogenizationCSIM: 0.1340 -> 0.4667Improved
add light homogenization stage before material estimation (ablation)material estimation · avatar materialsmaterial qualityImproved
use joint cross-intrinsic attention with differentiable BRDF loss instead of separate LoRAs (ablation)material estimation · normal mapsqualitativeImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 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