- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper studies whether driving VLMs can distinguish moving from stationary vehicles when the camera is also moving. It finds little benefit from additional frames in the tested settings, then uses target positions and ego poses to compensate for camera motion. Experiments on DriveLM-nuScenes show that providing this information improves motion-state question answering.
Critical strengths
- The paper takes an interesting angle on how driving VLMs judge object motion when the camera itself is moving. It highlights a failure case and shows that providing explicit geometric information can improve motion-state judgments.
Critical weaknesses
- The explanation for the failure is not established. In the theoretical analysis, the observation is limited to a single object’s relative position track. In the experiments, however, the models receive full images with background cues that can help estimate ego-motion. Poor performance and limited gains from extra frames may therefore reflect weak temporal learning or insufficient training, rather than missing information. The experiments do not separate these explanations.
- The improvement depends on additional inputs whose practical cost and reliability are not evaluated. The method uses annotated target positions, cross-frame matches, and ego poses. Obtaining comparable inputs in practice requires detection, position estimation, tracking, and synchronization, which add cost and introduce errors. The paper neither measures this cost nor evaluates actual detection and tracking outputs. Testing ego-pose noise alone does not establish whether the gains would remain in practice.
- Most importantly, it is unclear whether this weakness actually limits driving. Poor moving/stationary question answering does not by itself show that a model makes worse driving decisions. Relative-motion cues may already support the required driving decisions, but the paper does not test this possibility or show that adding motion relative to the ground improves planning or driving. The claimed practical importance of the diagnosed weakness therefore remains insufficiently supported.
Questions for authors
- What evidence separates missing information from insufficient temporal learning? How would a stronger temporal model, or a pipeline that estimates ego-motion from the same images, perform without annotated side inputs?
- With estimated target positions, tracks, and ego poses, how much improvement remains, at what additional cost, and does it lead to better planning or driving performance?