MRD: Using Physically Based Differentiable Rendering to Probe Vision Models for 3D Scene Understanding
By: Benjamin Beilharz, Thomas S. A. Wallis
Potential Business Impact:
Shows how computers "see" 3D objects.
While deep learning methods have achieved impressive success in many vision benchmarks, it remains difficult to understand and explain the representations and decisions of these models. Though vision models are typically trained on 2D inputs, they are often assumed to develop an implicit representation of the underlying 3D scene (for example, showing tolerance to partial occlusion, or the ability to reason about relative depth). Here, we introduce MRD (metamers rendered differentiably), an approach that uses physically based differentiable rendering to probe vision models' implicit understanding of generative 3D scene properties, by finding 3D scene parameters that are physically different but produce the same model activation (i.e. are model metamers). Unlike previous pixel-based methods for evaluating model representations, these reconstruction results are always grounded in physical scene descriptions. This means we can, for example, probe a model's sensitivity to object shape while holding material and lighting constant. As a proof-of-principle, we assess multiple models in their ability to recover scene parameters of geometry (shape) and bidirectional reflectance distribution function (material). The results show high similarity in model activation between target and optimized scenes, with varying visual results. Qualitatively, these reconstructions help investigate the physical scene attributes to which models are sensitive or invariant. MRD holds promise for advancing our understanding of both computer and human vision by enabling analysis of how physical scene parameters drive changes in model responses.
Similar Papers
MRD: Multi-resolution Retrieval-Detection Fusion for High-Resolution Image Understanding
CV and Pattern Recognition
Helps computers see and understand big pictures better.
MRD: Multi-resolution Retrieval-Detection Fusion for High-Resolution Image Understanding
CV and Pattern Recognition
Helps computers see tiny details in big pictures.
PhysHDR: When Lighting Meets Materials and Scene Geometry in HDR Reconstruction
Graphics
Makes dark photos look bright and clear.