PIE-Net: Photometric Invariant Edge Guided Network for Intrinsic Image Decomposition

by   Partha Das, et al.

Intrinsic image decomposition is the process of recovering the image formation components (reflectance and shading) from an image. Previous methods employ either explicit priors to constrain the problem or implicit constraints as formulated by their losses (deep learning). These methods can be negatively influenced by strong illumination conditions causing shading-reflectance leakages. Therefore, in this paper, an end-to-end edge-driven hybrid CNN approach is proposed for intrinsic image decomposition. Edges correspond to illumination invariant gradients. To handle hard negative illumination transitions, a hierarchical approach is taken including global and local refinement layers. We make use of attention layers to further strengthen the learning process. An extensive ablation study and large scale experiments are conducted showing that it is beneficial for edge-driven hybrid IID networks to make use of illumination invariant descriptors and that separating global and local cues helps in improving the performance of the network. Finally, it is shown that the proposed method obtains state of the art performance and is able to generalise well to real world images. The project page with pretrained models, finetuned models and network code can be found at https://ivi.fnwi.uva.nl/cv/pienet/.


page 15

page 16

page 17

page 18

page 19

page 20

page 23

page 24


SIGNet: Intrinsic Image Decomposition by a Semantic and Invariant Gradient Driven Network for Indoor Scenes

Intrinsic image decomposition (IID) is an under-constrained problem. The...

Intrinsic Image Transfer for Illumination Manipulation

This paper presents a novel intrinsic image transfer (IIT) algorithm for...

Self-Supervised Intrinsic Image Decomposition Network Considering Reflectance Consistency

We propose a novel intrinsic image decomposition network considering ref...

Physics-based Shading Reconstruction for Intrinsic Image Decomposition

We investigate the use of photometric invariance and deep learning to co...

Learning Data-driven Reflectance Priors for Intrinsic Image Decomposition

We propose a data-driven approach for intrinsic image decomposition, whi...

ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition

In general, intrinsic image decomposition algorithms interpret shading a...

CNN based Learning using Reflection and Retinex Models for Intrinsic Image Decomposition

Most of the traditional work on intrinsic image decomposition rely on de...

Please sign up or login with your details

Forgot password? Click here to reset