AI Paper Atlas

Research map / Video / Video generation

OmniVDiff: Omni Controllable Video Diffusion for Generation and Understanding

Dianbing Xi, Jiepeng Wang, Yuanzhi Liang, Xi Qiu, Yuchi Huo, Rui Wang, Chi Zhang, Xuelong Li

AAAI 2026 · Video › Video generation · approach: Efficient video diffusion models · 23 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 modality embedding for generation vs conditioning roles (ablation)OmniVDiff · VBench text-to-videoweighted average: 71.54 -> 72.78Improved
add adaptive modality control strategy (AMCS) (ablation)OmniVDiff · VBench text-to-videoweighted average: 71.21 -> 72.78Improved
add modality-specific projection heads (MSPH) (ablation)OmniVDiff · VBench text-to-videoweighted average: 71.35 -> 72.78Improved
joint multi-modal training vs rgb-only CogVideoXCogVideoX1.5-5B · VBench text-to-videoweighted average: 72.25 -> 72.78Improved
joint multi-modal training vs rgb-only CogVideoXCogVideoX1.5-5B · VBench text-to-videodynamic degree: 53.98 -> 49.69Hurt
add 10k synthetic ground-truth depth samples to training (ablation)OmniVDiff · ScanNet zero-shot video depthAbsRel: 0.125 -> 0.100Improved
train with pseudo labels from VDA-S instead of expert directlyOmniVDiff · ScanNet zero-shot video depthAbsRel: VDA-S 0.110 vs OmniVDiff 0.125Hurt
unified model vs expert segmentation modelOmniVDiff · COCO Val 2017 point-based segmentation1-IoU (Max): 57.0 -> 56.0No clear effect
add two extra modalities (segmentation, depth) to output vs rgb-only CogVideoXOmniVDiff · inference timetime (s): 41s -> 44sNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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