Causal-Entity Reflected Egocentric Traffic Accident Video Synthesis
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913917521887232 |
|---|---|
| author | Li, Lei-lei Fang, Jianwu Xiao, Junbin Pang, Shanmin Yu, Hongkai Lv, Chen Xue, Jianru Chua, Tat-Seng |
| author_facet | Li, Lei-lei Fang, Jianwu Xiao, Junbin Pang, Shanmin Yu, Hongkai Lv, Chen Xue, Jianru Chua, Tat-Seng |
| contents | Egocentricly comprehending the causes and effects of car accidents is crucial for the safety of self-driving cars, and synthesizing causal-entity reflected accident videos can facilitate the capability test to respond to unaffordable accidents in reality. However, incorporating causal relations as seen in real-world videos into synthetic videos remains challenging. This work argues that precisely identifying the accident participants and capturing their related behaviors are of critical importance. In this regard, we propose a novel diffusion model, Causal-VidSyn, for synthesizing egocentric traffic accident videos. To enable causal entity grounding in video diffusion, Causal-VidSyn leverages the cause descriptions and driver fixations to identify the accident participants and behaviors, facilitated by accident reason answering and gaze-conditioned selection modules. To support Causal-VidSyn, we further construct Drive-Gaze, the largest driver gaze dataset (with 1.54M frames of fixations) in driving accident scenarios. Extensive experiments show that Causal-VidSyn surpasses state-of-the-art video diffusion models in terms of frame quality and causal sensitivity in various tasks, including accident video editing, normal-to-accident video diffusion, and text-to-video generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_23263 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Causal-Entity Reflected Egocentric Traffic Accident Video Synthesis Li, Lei-lei Fang, Jianwu Xiao, Junbin Pang, Shanmin Yu, Hongkai Lv, Chen Xue, Jianru Chua, Tat-Seng Computer Vision and Pattern Recognition Egocentricly comprehending the causes and effects of car accidents is crucial for the safety of self-driving cars, and synthesizing causal-entity reflected accident videos can facilitate the capability test to respond to unaffordable accidents in reality. However, incorporating causal relations as seen in real-world videos into synthetic videos remains challenging. This work argues that precisely identifying the accident participants and capturing their related behaviors are of critical importance. In this regard, we propose a novel diffusion model, Causal-VidSyn, for synthesizing egocentric traffic accident videos. To enable causal entity grounding in video diffusion, Causal-VidSyn leverages the cause descriptions and driver fixations to identify the accident participants and behaviors, facilitated by accident reason answering and gaze-conditioned selection modules. To support Causal-VidSyn, we further construct Drive-Gaze, the largest driver gaze dataset (with 1.54M frames of fixations) in driving accident scenarios. Extensive experiments show that Causal-VidSyn surpasses state-of-the-art video diffusion models in terms of frame quality and causal sensitivity in various tasks, including accident video editing, normal-to-accident video diffusion, and text-to-video generation. |
| title | Causal-Entity Reflected Egocentric Traffic Accident Video Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.23263 |