AI Paper Atlas

Research map / 3D vision / 3D generation

Any2Any 3D Diffusion Models with Knowledge Transfer: A Radiotherapy Planning Study

Yuhan Wang, Zihan Li, Han Liu, Simon Arberet, Martin Kraus, Yuyin Zhou, Florin-Cristian Ghesu, Dorin Comaniciu, Ali Kamen, Riqiang Gao

CVPR 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 pretrained Wan weights (ablation)DiffKT3D DiT · GDP-HMM validationMAE / Score: 2.58 / 119.82 -> 2.07 / 135.41Improved
switch from conditional to Any2Any training (ablation)DiffKT3D DiT · GDP-HMM validationMAE / Score: 2.07 / 135.41 -> 1.90 / 136.22Improved
add role embedding (ablation)Any2Any DiT · GDP-HMM validationMAE / Score: 2.01 / 134.04 -> 1.90 / 136.22Improved
add full attention (ablation)Any2Any DiT · GDP-HMM validationMAE / Score: 2.15 / 130.80 -> 1.90 / 136.22Improved
add modality-specific patch embedding (ablation)Any2Any DiT · GDP-HMM validationMAE / Score: 2.02 / 134.71 -> 1.90 / 136.22Improved
add 4D RoPE (ablation)Any2Any DiT · GDP-HMM validationMAE / Score: 1.96 / 135.27 -> 1.90 / 136.22Improved
add ScardNFT RL post-training (ablation)Any2Any DiT · GDP-HMM validationScorecard: 136.22 -> 138.17Improved
add ScardNFT RL post-training (ablation)Any2Any DiT · GDP-HMM testMAE: 1.93 -> 1.93No clear effect
use v-prediction instead of x-prediction (1 step) (ablation)Any2Any DiT · GDP-HMM validationMAE / Score: 2.45 / 117.64 -> 2.12 / 133.59Improved
increase sampling from 1 to 10 steps (ablation)Any2Any v-pred · GDP-HMM validationMAE / Score: 2.12 / 133.59 -> 1.91 / 138.17Improved
use v-prediction instead of eps-prediction (10 steps) (ablation)Any2Any DiT · GDP-HMM validationMAE / Score: 1.93 / 137.82 -> 1.91 / 138.17Improved
fine-tune full VAE instead of frozen VAE (ablation)Any2Any DiT · GDP-HMM validationMAE / Score: 1.91 / 138.17 -> 2.54 / 121.76Hurt

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