AI Paper Atlas

Research map / Video / Video generation

DIMO: Diverse 3D Motion Generation for Arbitrary Objects

Linzhan Mou, Jiahui Lei, Chen Wang, Lingjie Liu, Kostas Daniilidis

ICCV 2025 · Video › Video generation · approach: Diffusion-based human image animation · 4 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 neural keypoint motion factorization (ablation)DIMO · Ablation (Consistent4D-style metrics)FVD: 851.83 -> 587.09Improved
add neural keypoint motion factorization (ablation)DIMO · Ablation (Consistent4D-style metrics)LPIPS: 0.134 -> 0.126Improved
add motion latent space (ablation)DIMO · Ablation (Consistent4D-style metrics)FVD: 1077.19 -> 587.09Improved
add motion latent space (ablation)DIMO · Ablation (Consistent4D-style metrics)LPIPS: 0.163 -> 0.126Improved
add motion pre-training (ablation)DIMO · Ablation (Consistent4D-style metrics)FVD: 890.26 -> 587.09Improved
add motion pre-training (ablation)DIMO · Ablation (Consistent4D-style metrics)CLIP: 0.90 -> 0.93Improved
add multi-motion joint training (ablation)DIMO · Ablation (Consistent4D-style metrics)FVD: 693.49 -> 587.09Improved
add multi-motion joint training (ablation)DIMO · Ablation (Consistent4D-style metrics)LPIPS: 0.131 -> 0.126Improved
use DIMO instead of SV4DSV4D · Video-to-4D (Consistent4D benchmark)FVD: 732.40 -> 625.30Improved
use DIMO instead of SV4DSV4D · Image-to-4D (Animate124, Objaverse)CLIP-I: 0.9372 -> 0.9505Improved
use DIMO for diverse motions instead of DG4DDG4D · Image-to-4D (Animate124, Objaverse)motion diversity: 10.2% -> 59.4%Improved
use DIMO instead of 4D-fy for text-guided motion4D-fy · Text-to-4D (Animate124 examples)motion amplitude: 0.254 -> 4.319Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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