AI Paper Atlas

Research map / Video / Video generation

Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer

Hyunsoo Cha, Byungjun Kim, Hanbyul Joo

ICLR 2026 · Video › Video generation · approach: Diffusion-based human image animation · 2 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
use Dual ReferenceNet instead of a single shared ReferenceNet (ablation)Durian · Self-attribute transferPSNR: 17.95 -> 18.83Improved
add attribute-aware mask expansion (ablation)Durian · Self-attribute transferPSNR: 17.16 -> 18.83Improved
add reference image augmentation (ablation)Durian · Self-attribute transferPSNR: 16.97 -> 18.83Improved
add binary mask input to ReferenceNets (ablation)Durian · Self-attribute transferPSNR: 18.60 -> 18.83Improved
use complementary masked references instead of full unmasked reference images (ablation)Durian · Self-attribute transferPSNR: 19.47 -> 18.83Mixed
Durian single-stage vs best two-stage baseline on cross-attribute transferportrait animation with attribute transfer · Cross-attribute transfermDINO: 0.7271 -> 0.7801Improved
Durian vs two-stage baselines on temporal realism (VFID ResNeXt)portrait animation with attribute transfer · Cross-attribute transferVFID (ResNeXt): 1.4672 (StableHair+MegActor) vs 2.4052Hurt

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