AI Paper Atlas

Research map / 3D vision / 3D generation

Doe-2: 3D Representation World Model for Unified Driving Scene Forecasting

Dong Zhuo, Wenzhao Zheng, Sicheng Zuo, Yuanhui Huang, Siming Yan, Lu Hou, Jie Zhou, Jiwen Lu

ECCV 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 0 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 3-layer DiT head to pure AR model (ablation)Doe-2 · nuScenes generationgFID: 29.93 -> 10.48Improved
replace pure DiT with AR+DiT head (ablation)Doe-2 · nuScenes generationFPS: ~1.9 -> ~4.0Improved
replace pure DiT with AR+DiT head (ablation)Doe-2 · nuScenes generationgFID: 16.25 -> 10.48Improved
compress latent dimension from 768 to 64 (ablation)Doe-2 · SurroundOcc generationmIoU: 8.24 -> 12.04Improved
compress latent dimension from 768 to 64 (ablation)Doe-2 · SurroundOccFPS: ~2.3 -> ~4.0Improved
compress latent dimension from 64 to 32 (ablation)Doe-2 · SurroundOcc generationmIoU: 12.04 -> 9.33Hurt
raise latent dimension from 64 to 768 (ablation)Doe-2 · SurroundOcc reconstructionmIoU: 19.65 -> 20.02Improved
lower KL weight from 0.01 to 0.00001 (ablation)Doe-2 · SurroundOcc generationmIoU: 8.92 -> 12.04Improved
lower KL weight from 0.00001 to 0.000001 (ablation)Doe-2 · SurroundOcc generationmIoU: 12.04 -> 11.45Hurt
lower KL weight from 0.00001 to 0.000001 (ablation)Doe-2 · SurroundOcc reconstructionmIoU: 19.65 -> 19.73No 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