Paper
Composing Driving Worlds through Disentangled Control for Adversarial Scenario Generation
Authors
Yifan Zhan, Zhengqing Chen, Qingjie Wang, Zhuo He, Muyao Niu, Xiaoyang Guo, Wei Yin, Weiqiang Ren, Qian Zhang, Yinqiang Zheng
Abstract
A major challenge in autonomous driving is the "long tail" of safety-critical edge cases, which often emerge from unusual combinations of common traffic elements. Synthesizing these scenarios is crucial, yet current controllable generative models provide incomplete or entangled guidance, preventing the independent manipulation of scene structure, object identity, and ego actions. We introduce CompoSIA, a compositional driving video simulator that disentangles these traffic factors, enabling fine-grained control over diverse adversarial driving scenarios. To support controllable identity replacement of scene elements, we propose a noise-level identity injection, allowing pose-agnostic identity generation across diverse element poses, all from a single reference image. Furthermore, a hierarchical dual-branch action control mechanism is introduced to improve action controllability. Such disentangled control enables adversarial scenario synthesis-systematically combining safe elements into dangerous configurations that entangled generators cannot produce. Extensive comparisons demonstrate superior controllable generation quality over state-of-the-art baselines, with a 17% improvement in FVD for identity editing and reductions of 30% and 47% in rotation and translation errors for action control. Furthermore, downstream stress-testing reveals substantial planner failures: across editing modalities, the average collision rate of 3s increases by 173%.
Metadata
Related papers
Fractal universe and quantum gravity made simple
Fabio Briscese, Gianluca Calcagni • 2026-03-25
POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan
Marta Moscati, Muhammad Saad Saeed, Marina Zanoni, Mubashir Noman, Rohan Kuma... • 2026-03-25
LensWalk: Agentic Video Understanding by Planning How You See in Videos
Keliang Li, Yansong Li, Hongze Shen, Mengdi Liu, Hong Chang, Shiguang Shan • 2026-03-25
Orientation Reconstruction of Proteins using Coulomb Explosions
Tomas André, Alfredo Bellisario, Nicusor Timneanu, Carl Caleman • 2026-03-25
The role of spatial context and multitask learning in the detection of organic and conventional farming systems based on Sentinel-2 time series
Jan Hemmerling, Marcel Schwieder, Philippe Rufin, Leon-Friedrich Thomas, Mire... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.12864v1</id>\n <title>Composing Driving Worlds through Disentangled Control for Adversarial Scenario Generation</title>\n <updated>2026-03-13T10:10:21Z</updated>\n <link href='https://arxiv.org/abs/2603.12864v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.12864v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>A major challenge in autonomous driving is the \"long tail\" of safety-critical edge cases, which often emerge from unusual combinations of common traffic elements. Synthesizing these scenarios is crucial, yet current controllable generative models provide incomplete or entangled guidance, preventing the independent manipulation of scene structure, object identity, and ego actions. We introduce CompoSIA, a compositional driving video simulator that disentangles these traffic factors, enabling fine-grained control over diverse adversarial driving scenarios. To support controllable identity replacement of scene elements, we propose a noise-level identity injection, allowing pose-agnostic identity generation across diverse element poses, all from a single reference image. Furthermore, a hierarchical dual-branch action control mechanism is introduced to improve action controllability. Such disentangled control enables adversarial scenario synthesis-systematically combining safe elements into dangerous configurations that entangled generators cannot produce. Extensive comparisons demonstrate superior controllable generation quality over state-of-the-art baselines, with a 17% improvement in FVD for identity editing and reductions of 30% and 47% in rotation and translation errors for action control. Furthermore, downstream stress-testing reveals substantial planner failures: across editing modalities, the average collision rate of 3s increases by 173%.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n <published>2026-03-13T10:10:21Z</published>\n <arxiv:primary_category term='cs.CV'/>\n <author>\n <name>Yifan Zhan</name>\n </author>\n <author>\n <name>Zhengqing Chen</name>\n </author>\n <author>\n <name>Qingjie Wang</name>\n </author>\n <author>\n <name>Zhuo He</name>\n </author>\n <author>\n <name>Muyao Niu</name>\n </author>\n <author>\n <name>Xiaoyang Guo</name>\n </author>\n <author>\n <name>Wei Yin</name>\n </author>\n <author>\n <name>Weiqiang Ren</name>\n </author>\n <author>\n <name>Qian Zhang</name>\n </author>\n <author>\n <name>Yinqiang Zheng</name>\n </author>\n </entry>"
}