AI Paper Atlas

Research map / Video / Video generation

RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space

Yichen Xie, Chensheng Peng, Mazen Abdelfattah, Yihan Hu, Jiezhi Yang, Eric Higgins, Ryan Brigden, Masayoshi Tomizuka, Wei Zhan

CVPR 2026 · Video › Video generation · approach: World-model video generation · 1 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 global spatio-temporal attention with relative ray embedding (ablation)RayNova (130M) · nuScenes val multi-view generationFVD: 214 -> 124Improved
use relative instead of absolute Plucker ray position embedding (ablation)RayNova (130M) · nuScenes val multi-view generationFVD: 138 -> 124Improved
use relative instead of absolute Plucker ray position embedding (ablation)RayNova (130M) · nuScenes val multi-view generationFID: 17.2 -> 17.2No clear effect
condition past frames on all scales instead of prefix scales (ablation)RayNova (130M) · nuScenes val multi-view generationFID: 17.2 -> 60.4Hurt
condition past frames on same scale only instead of prefix scales (ablation)RayNova (130M) · nuScenes val multi-view generationFVD: 124 -> 151Hurt
scale model from 130M to 2.8B parameters (ablation)RayNova · nuScenes val multi-view generationFID: 17.2 -> 10.5Improved
scale model from 130M to 2.8B parameters (ablation)RayNova · nuScenes val multi-view generationFVD: 124 -> 91Improved
add recurrent training stage (ablation)RayNova · nuScenes val multi-view generationFVD: 100 -> 91Improved
shift camera 4m (novel view) versus no shift, no 3D priorRayNova · nuScenes novel view synthesisFID: 14.11 -> 17.48 (1m vs 4m)No clear effect
geometry-free ray-space model instead of 3D-prior reconstruction (OmniRe)novel view synthesis · nuScenes novel view synthesis, shift 4mFVD: 428.20 -> 143.48Improved
autoregressive architecture instead of diffusion baselinesmulti-view world model · nuScenes val multi-view generationthroughput (images/s): 0.67 -> 1.96 (Panacea vs RayNova)Improved

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