AI Paper Atlas

Research map / Video / Video generation

MTVCraft: Tokenizing 4D Motion for Arbitrary Character Animation

Yanbo Ding, Xirui Hu, Guo Zhi Zhi, Yan Zhang, Xinrui Wang, Zhixiang He, Chi Zhang, Yali Wang, Xuelong Li

ICLR 2026 · Video › Video generation · approach: Diffusion-based human image animation

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 vector quantization to motion tokens (ablation)MTVCraft-6B · TikTokFVD: 332.97 -> 317.21Improved
use differential (first-frame-relative) joint coordinates (ablation)MTVCraft-6B · TikTokFVD: 325.40 -> 317.21Improved
add z-axis (3D) quantization over 4D (ablation)MTVCraft-6B · TikTokFVD: 329.86 -> 317.21Improved
use 4D RoPE in motion attention instead of no positional encoding (ablation)MTVCraft-6B · TikTokFVD: 548.31 -> 317.21Improved
use 4D RoPE instead of 3D spatial RoPE (ablation)MTVCraft-6B · TikTokFVD: 435.80 -> 317.21Improved
use 4D RoPE instead of learnable PE (ablation)MTVCraft-6B · TikTokFVD: 397.64 -> 317.21Improved
scale backbone from CogVideoX-5B (6B) to Wan-2.1-14B (18B)MTVCraft · TikTokFVD: 317.21 -> 276.65Improved
motion CFG scale 3.0 vs other scales (ablation)MTVCraft-6B · TikTokFVDImproved
replace zero-padding with linear/MLP projection for 18B (ablation)MTVCraft-18B · TikTokconvergenceHurt

Earlier methods this paper compares with

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