REVIEW 3 cited by
Seeing Through Their Eyes: Evaluating Visual Perspective Taking in Vision Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Visual perspective-taking (VPT), the ability to understand the viewpoint of another person, enables individuals to anticipate the actions of other people. For instance, a driver can avoid accidents by assessing what pedestrians see. Humans typically develop this skill in early childhood, but it remains unclear whether the recently emerging Vision Language Models (VLMs) possess such capability. Furthermore, as these models are increasingly deployed in the real world, understanding how they perform nuanced tasks like VPT becomes essential. In this paper, we introduce two manually curated datasets, Isle-Bricks and Isle-Dots for testing VPT skills, and we use it to evaluate 12 commonly used VLMs. Across all models, we observe a significant performance drop when perspective-taking is required. Additionally, we find performance in object detection tasks is poorly correlated with performance on VPT tasks, suggesting that the existing benchmarks might not be sufficient to understand this problem. The code and the dataset will be available at https://sites.google.com/view/perspective-taking
Forward citations
Cited by 3 Pith papers
-
SpatialQuery: Benchmarking Geometry-Grounded Multi-Instance Spatial Reasoning in Vision-Language Models
SPATIALQUERY-1M adds a 1.06M-pair closest-instance metric spatial reasoning benchmark, and SPATIALQUERY answers it by grounding geometry and prompting a VLM with a bird's-eye-view abstraction.
-
OrientSAM: Mitigating Camera-Centric Shortcut in Multimodal Spatial Reasoning via Orientation-Aware Spatial Alignment
OrientSAM injects Fourier-encoded object orientation into a vision-language model and uses curriculum training, improving reference-centric spatial reasoning and reducing camera-centric shortcut behavior.
-
Mind Meets Space: Rethinking Agentic Spatial Intelligence from a Neuroscience-inspired Perspective
Agent spatial intelligence is organized into six neuroscience-inspired modules, and the field is reviewed through that lens without any experimental validation.
Discussion (0). Sign in to comment.