AI Paper Atlas

Research map / 3D vision / 3D generation

RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Models

Bowen Zhang, Yiji Cheng, Chunyu Wang, Ting Zhang, Jiaolong Yang, Yansong Tang, Feng Zhao, Dong Chen, Baining Guo

ECCV 2024 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 32 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 task replay (switch avatars more often) when fitting the shared decoder (ablation)Rodin (512) triplane fitting · Triplane fitting ablationPSNR: 30.56 -> 30.93Improved
add identity-aware weight consolidation regularizer (ablation)Rodin (512) with task replay and weight decay · Triplane fitting ablationPSNR: 31.00 -> 31.45Improved
add weight decay (ablation)Rodin (512) with task replay · Triplane fitting ablationPSNR: 30.93 -> 31.00Improved
naively increase triplane resolution to 512 without fixing forgetting (ablation)Rodin fitting · Triplane fitting ablationPSNR: 30.31 -> 30.56No clear effect
naively scale triplane diffusion to 512x512x32 without changing noise schedule (ablation)Rodin diffusion · Conditional avatar generationFID: 33.20 -> 35.84Hurt
add stronger noise schedule for triplane diffusion (ablation)RodinHD at 512 triplane · Conditional avatar generationFID: 35.84 -> 27.74Improved
replace CLIP image encoder with single-scale VAE encoder conditioning (ablation)RodinHD · Conditional avatar generationFID: 27.74 -> 27.13Improved
use multi-scale instead of single-scale VAE feature conditioning (ablation)RodinHD · Conditional avatar generationFID: 27.13 -> 26.49Improved
avoid 2D refinement (keep rendering directly from triplane)RodinHD vs Rodin* · 3D consistency (NeuS fit)PSNR: 31.73 -> 35.46Improved
2D refiner applied to Rodin outputRodin · Unconditional avatar generationFID: 45.70 -> 30.29Improved
increase triplane channels and resolution (ablation)triplane fitting of one subject · Triplane res/channel sweepPSNR: 30.15 -> 31.71Improved
RodinHD without refiner vs Rodin with 2D refinement on visual fidelity rankingRodinHD · User studyVisual fidelity rank: 1.26 vs 2.13Hurt

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