MRD finds physically different 3D scenes that reproduce a target model activation, revealing which shape and material properties vision models are sensitive to.
Title resolution pending
1 Pith paper cite this work, alongside 214 external citations. Polarity classification is still indexing.
1
Pith paper citing it
214
external citations · OpenAlex
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MRD: Using Physically Based Differentiable Rendering to Probe Vision Models for 3D Scene Understanding
MRD finds physically different 3D scenes that reproduce a target model activation, revealing which shape and material properties vision models are sensitive to.