First-person egocentric view in a narrow indoor hallway. The listener walks toward a visible loudspeaker mounted on the right wall while continuous music plays; as the listener approaches and passes it, the sound is perceived from behind first and only shifts to the front after the speaker has already been passed.
Seedance 2.0ByteDance · proprietary
Kling 3.0 OmniKuaishou · proprietary
Veo 3.1Google · proprietary
LTX-2.3Lightricks · open
Ovi 1.1character.ai · open
JavisDiT++JavisDiT · open
MagiHumanGAIR-NLP · open
Per-prompt rubric
Basic standards
Visual presence
- a loudspeaker
- an indoor hallway
Event: a person walks past a wall-mounted loudspeaker in a hallway
Audio presence
- a loudspeaker
Sound: music from a loudspeaker
Key standards
Visual physical commonsense (V-PC)
- A first-person camera walks continuously down a narrow indoor hallway toward a visible loudspeaker mounted on the right wall, then continues past it.
Audio physical commonsense (A-PC)
- Continuous music plays uninterrupted throughout the clip with consistent musical content.
Cross-modal physical commonsense (AV-PC)
- While the loudspeaker is still visibly ahead of the camera, the music is localized behind the listener in the audio field.
- After the camera has visibly passed the loudspeaker, the music shifts to be localized in front of the listener.