MultiTest v.s. Drivence
We first compare Drivence with the baseline Multitest in terms of the full generation pipeline, which includes both trajectory generation and rendering. This end-to-end comparison reflects the overall quality of the synthesized driving sequences produced by each method.
MultiTest
Drivence
To further isolate the effect of the rendering component, we conduct an additional comparison using the same set of input trajectories for both methods. This setting allows us to directly assess the visual fidelity of the rendered outputs, independent of the differences in trajectory generation.
MultiTest
Drivence
Key frame
Frst, Multitest (right side) lacks lighting and shadow effects, resulting in flat and less realistic images. More critically, it fails to handle occlusions correctly: inserted NPCs remain fully visible even when they should be partially or fully occluded by original objects in the scene, both in the image and in the point cloud. This violates basic physical realism and may lead to perception errors that lack real-world relevance.