AI Paper Atlas

Research map / Video / Video generation

PRIMAL: Physically Reactive and Interactive Motor Model for Avatar Learning

Yan Zhang, Yao Feng, Alpár Cseke, Nitin Saini, Nathan Bajandas, Nicolas Heron, Michael J. Black

ICCV 2025 · Video › Video generation · approach: Diffusion-based human image animation · 5 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 in-context conditioning instead of AdaLN (ablation)PRIMAL · HumanEva/SFU motion realismARD x1e-3: 0.147 -> 0.074Improved
predict 15 frames rather than 8 frames (ablation)PRIMAL InContext · SFUASR: 0.073 -> 0.027Improved
add Gaussian noise to joint locations and velocities (ablation)PRIMAL InContext · HumanEva/SFUASR/ARD: 0.027 -> 0.022 ASR (SFU); ARD 0.081 -> 0.098No clear effect
replace SiLU with ReLU (ablation)PRIMAL InContext · SFUASR: 0.027 -> 0.042Hurt
increase attention latent dim from 256 to 512 (ablation)PRIMAL InContext · SFUARD x1e-3: 0.081 -> 0.105No clear effect
add inertialization at test time (ablation)PRIMAL InContext · HumanEva ASRASR: 0.022 -> 0.015Improved
add joint re-projection at test time (ablation)PRIMAL InContext · HumanEva ASRASR: 0.022 -> 0.034Hurt
use separate-token conditioning (CAMDM style) (ablation)PRIMAL InContext · HumanEvaASR: 0.023 -> 0.037Hurt
use ControlNet-based adaptor instead of direct finetuningPRIMAL · Few-shot action generationR-precision: 0.87 -> 0.96Improved
use proposed adaptor instead of OmniControlNet for spatial target reachingPRIMAL · Spatial target reachingerr. dist.: 0.106 -> 0.031; ASR 0.249 -> 0.338Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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