MRD finds physically different 3D scenes that reproduce a target model activation, revealing which shape and material properties vision models are sensitive to.
Many-Worlds Inverse Rendering
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Discontinuous visibility changes remain a major bottleneck when optimizing surfaces within a physically-based inverse renderer. Many previous works have proposed sophisticated algorithms and data structures to sample visibility silhouettes more efficiently. Our work presents another solution: instead of differentiating a tentative surface locally, we differentiate a volumetric perturbation of a surface. We refer this as a many-worlds representation because it models a non-interacting superposition of conflicting explanations (worlds) of the input dataset. Each world is optically isolated from others, leading to a new transport law that distinguishes our method from prior work based on exponential random media. The resulting Monte Carlo algorithm is simpler and more efficient than prior methods. We demonstrate that our method promotes rapid convergence, both in terms of the total iteration count and the cost per iteration.
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.