VLMs reach only 0.66 accuracy on relative camera pose estimation while humans achieve 0.91 and specialized pipelines reach 0.99, exposing weaknesses in multi-view spatial reasoning.
The chessboard’s perspectiveshows depth receding toward the upper-right, meaning the camera is now pointed more to the right than before (yaw right)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Lost in Space? Vision-Language Models Struggle with Relative Camera Pose Estimation
VLMs reach only 0.66 accuracy on relative camera pose estimation while humans achieve 0.91 and specialized pipelines reach 0.99, exposing weaknesses in multi-view spatial reasoning.