AI Paper Atlas

Research map / 3D vision / 3D generation

HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation

Xin Zhou, Dingkang Liang, Sifan Tu, Xiwu Chen, Yikang Ding, Dingyuan Zhang, Feiyang Tan, Hengshuang Zhao, Xiang Bai

ICCV 2025 · 3D vision › 3D generation · approach: 3D perception for autonomous driving · 45 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
unify understanding and generation in one model instead of separated models sharing BEV (ablation)HERMES · nuScenes (quarter of training scenes, ablation)Chamfer distance 3s: 1.875 -> 1.718Improved
unify understanding and generation instead of separated models (ablation)HERMES · OmniDrive-nuScenes captioning (quarter data, ablation)CIDEr: 0.722 -> 0.720No clear effect
train generation jointly with understanding instead of generation only (ablation)HERMES · nuScenes (quarter of training scenes, ablation)Chamfer distance 3s: 1.687 -> 1.718Hurt
train understanding jointly with generation instead of understanding only (ablation)HERMES · OmniDrive-nuScenes captioning (quarter data, ablation)CIDEr: 0.728 -> 0.720Hurt
add world queries (vs integrating ego motion directly into BEV) (ablation)HERMES · nuScenes val (full training data)Chamfer distance 3s: 10% reductionImproved
add world queries (vs none) (ablation)HERMES · OmniDrive-nuScenes captioning (full data)CIDEr: 1% decreaseHurt
add current point cloud prediction as auxiliary task (ablation)HERMES · nuScenes (quarter of training scenes, ablation)Chamfer distance 3s: 1.779 -> 1.718Improved
use max pooling instead of attention pooling for world queries (ablation)HERMES · nuScenes (quarter of training scenes, ablation)Chamfer distance 3s: 1.748 -> 1.718Improved
use max pooling instead of average pooling for world queries (ablation)HERMES · nuScenes (quarter of training scenes, ablation)Chamfer distance 3s: 1.741 -> 1.718Improved
increase flattened BEV size from 25x25 to 50x50 (ablation)HERMES · OmniDrive-nuScenes captioning (quarter data, ablation)CIDEr: 0.671 -> 0.720Improved
increase flattened BEV size from 25x25 to 50x50 (ablation)HERMES · nuScenes (quarter of training scenes, ablation)Chamfer distance 3s: 1.698 -> 1.718Hurt
scale LLM from 1.8B to 3.8B (ablation)HERMES · nuScenes (quarter of training scenes, ablation)Chamfer distance 3s: 1.718 -> 1.701Improved

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