Micro-renewal of urban landscapes is a hot topic of research and has drawn increasing appreciation, as an effective means to enhance both the quality of urban environment and residents’ quality of life. Urban planning and landscape design now commonly adopt intelligent optimization algorithms as an important decision-making tool, to support more effective micro-renewal strategies. In this study, we have focused on the use of intelligent optimization algorithms—particle swarm optimization, genetic algorithm and ant colony algorithm—for urban landscape micro-renewal. By calculating and comparing the greening rates of different urban landscapes (ecosystems), we have analyzed the performance differences of different algorithms under different landscape conditions, to assess their appropriateness and effectiveness. It was found that the PSO algorithm, when compared with others, performed well in terms of greening rate under certain landscapes. The GA algorithm also performed well, in specific circumstances. However, the performance of the ACO algorithm was found to fluctuate greatly.