The last 20 years have seen an increasing number of computer vision tasks being formulated as energy optimization problems. Such energy-based modeling can integrate multiple image cues and priors, thus making visual processing robust to noise and resilient to some degree of model misspecification. The scale of the resulting optimization problems however often posits them beyond the reach of generic optimization techniques and solvers. This motivates two active research directions, namely finding newmore tractable energy formulations for computer vision problems as well as developing new optimization methods that exploit the specific structure of computer vision energy functionals. This issue presents six papers along these two general lines of vision research. The paper “A Survey and Comparison of Discrete and ContinuousMultilabel SegmentationApproaches” considers perhaps the most popular class of low-level computer vision problems concernedwith image labeling (also known asmultilabel segmentation or image partitioning). Such problems are typically cast either as continuous (functional-driven) or as discrete (Markov Random Field-driven) energy optimiza-