AI Paper Atlas

Research map / Video / Video generation

Video Generation Models are General-Purpose Vision Learners

Letian Wang, Chuhan Zhang, Rishabh Kabra, Jasper Uijlings, Steven Waslander, Andrew Zisserman, Joao Carreira, Kaiming He, Mykhaylo Andriluka, Eduard Gabriel Bazavan, Andrei Zanfir, Cristian Sminchisescu

ECCV 2026 · Video › Video generation · approach: Compositional text-to-video diffusion · 9 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 video diffusion (WAN 2.1) pretraining instead of VideoMAE V2 G (ablation)GenCeption · Depth (Sintel, KITTI, ETH3D average)average AbsRel: 0.154 -> 0.093Improved
use video diffusion (WAN 2.1) pretraining instead of V-JEPA H (ablation)GenCeption · Depth (Sintel, KITTI, ETH3D average)average AbsRel: 0.281 -> 0.093Improved
initialize DiT with more pretrained text-to-video layers (ablation)GenCeption · DepthperformanceImproved
scale backbone from WAN 2.1 1.3B to 14B (1 dataset) (ablation)GenCeption · Depth averageaverage AbsRel: 0.122 -> 0.093Improved
scale backbone from WAN 2.1 1.3B to 14B (4 datasets) (ablation)GenCeption · Depth averageaverage AbsRel: 0.094 -> 0.071Improved
increase training datasets from 1 to 4 (14B) (ablation)GenCeption · Depth averageaverage AbsRel: 0.093 -> 0.071Improved
joint multi-task training instead of specialist (ablation)GenCeption-L · Sintel depthAbsRel: 0.130 -> 0.156Hurt
joint multi-task training instead of specialist (ablation)GenCeption-L · Hi4D normalsmAE: 10.99 -> 11.47Hurt
joint multi-task training instead of specialist (ablation)GenCeption-L · Sintel normalsmAE: 29.7 -> 29.3Improved
joint multi-task training instead of specialist (ablation)GenCeption-L · Video mattingMSE: 0.0027 -> 0.0010Improved
joint multi-task training instead of specialist (ablation)GenCeption-L · Ref-DAVISJ&F: 76.4 -> 75.8No clear effect
joint multi-task training with learnable tokens (ablation)GenCeption · 3D human keypointsperformanceHurt

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