Sida Peng

Papers

Total Citations

H-Index

About

Sida Peng is a leading researcher in computer vision, with a focus on 3D scene understanding, neural rendering, and depth estimation. His most significant contributions lie in advancing metric depth estimation from monocular images, where he pioneered the concept of prompting for depth foundation models. In his highly influential work, "Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation" (2025), Peng introduced a novel paradigm that leverages low-cost prompts to unlock the full potential of vision foundation models, achieving unprecedented 4K resolution accuracy. This breakthrough has already garnered 15 citations in its first year, demonstrating its immediate impact on the field. Peng’s research bridges the gap between foundation model capabilities and practical, high-fidelity 3D reconstruction, enabling applications in autonomous driving, augmented reality, and robotics. His work is celebrated for its elegance and efficiency, offering a scalable solution to one of computer vision’s most persistent challenges: obtaining precise depth from a single image. Peng continues to push boundaries at the intersection of generative AI and geometric vision, making him a rising star to watch in the coming years.