AI Paper Atlas

Research map / Video / Video segmentation and tracking

Stereo World Model: Camera-Guided Stereo Video Generation

Yang-Tian Sun, Zehuan Huang, Yifan Niu, Lin Ma, Yan-Pei Cao, Yuewen Ma, Xiaojuan Qi

CVPR 2026 · Video › Video segmentation and tracking · approach: Layered video decomposition and dynamics · 2 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
generate stereo views end-to-end instead of converting monocular outputsStereoWorld · Stereo video benchmark (435 stereo images)FVD: 96.87 -> 83.04Improved
use StereoWorld instead of monocular-then-convert baseline (Aether)Aether + StereoCrafter · Stereo video benchmark (435 stereo images)FPS: 0.11 -> 0.49Improved
use StereoWorld instead of SEVASEVA + StereoCrafter · Stereo video benchmark (435 stereo images)Matching pixels (K): 4.49 -> 4.56Improved
end-to-end stereo generation vs post-hoc conversionSEVA · Stereo video benchmark (435 stereo images)FVD-V: 31.10 -> 22.00Improved
use copy init instead of zero init for camera subspace (ablation)unified camera-frame RoPE · Camera injection ablation (TartanAir)RotErr: 1.81 -> 1.16Improved
use copy init instead of zero init for camera subspace (ablation)unified camera-frame RoPE · Camera injection ablation (TartanAir)FVD: 96.62 -> 93.17Improved
use unified camera-frame RoPE instead of Plucker ray concatenation (ablation)StereoWorld · Camera injection ablation (TartanAir)RotErr: 1.52 -> 1.16Improved
use unified camera-frame RoPE instead of PRoPE (ablation)StereoWorld · Camera injection ablation (TartanAir)FVD: 128.32 -> 93.17Improved
use stereo attention instead of full 4D attention (ablation)StereoWorld · Attention scheme ablationFLOPs (x10^10): 3.11 -> 1.56Improved
use stereo attention instead of full 4D attention (ablation)StereoWorld · Attention scheme ablationFPS: 0.34 -> 0.49Improved
use stereo attention instead of full 4D attention (ablation)StereoWorld · Attention scheme ablationCLIP-V: 97.55 -> 97.05Hurt
use stereo attention instead of full 4D attention (ablation)StereoWorld · Attention scheme ablationView synchronization (matching pixels): 4.51 -> 4.52No clear effect

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