Investigating Task-driven Latent Feasibility for Nonconvex Image Modeling
This work addresses image modeling problems for vision applications by offering a flexible framework that integrates task information, though it appears incremental as it builds on prior optimization and deep prior methods.
The paper tackles the challenge of modeling latent image distributions by introducing Task-driven Latent Feasibility (TLF), a framework that incorporates task-specific constraints to narrow solution spaces in optimization-based image modeling, and demonstrates its effectiveness in tasks like image deblurring and rain streak removal with advantages over state-of-the-art methods.
Properly modeling latent image distributions plays an important role in a variety of image-related vision problems. Most exiting approaches aim to formulate this problem as optimization models (e.g., Maximum A Posterior, MAP) with handcrafted priors. In recent years, different CNN modules are also considered as deep priors to regularize the image modeling process. However, these explicit regularization techniques require deep understandings on the problem and elaborately mathematical skills. In this work, we provide a new perspective, named Task-driven Latent Feasibility (TLF), to incorporate specific task information to narrow down the solution space for the optimization-based image modeling problem. Thanks to the flexibility of TLF, both designed and trained constraints can be embedded into the optimization process. By introducing control mechanisms based on the monotonicity and boundedness conditions, we can also strictly prove the convergence of our proposed inference process. We demonstrate that different types of image modeling problems, such as image deblurring and rain streaks removals, can all be appropriately addressed within our TLF framework. Extensive experiments also verify the theoretical results and show the advantages of our method against existing state-of-the-art approaches.