High-performance adaptive texture streaming and rendering of large 3D cities

Abstract We propose a high-performance texture streaming system for real-time rendering of large 3D cities with millions textures. Our main contribution is that automatically adjusts the workload at runtime based on measured frame latencies, specifically addressing high memory binding costs hardware virtual texturing which causes rate stuttering. streams textures in parallel prioritization GPU computed mesh perceptibility, and these are cached sparse partially resident image without need preprocessing step. In addition, we improve quality by minimizing pop-in artifacts using color blending scheme mipmap levels. evaluate our three structurally distinct datasets many compared it to baseline, game engine, prior method. Results show an 8X improvement performance 7X baseline.