arXiv subjects

Yidan Zheng

Publications and source records attributed to Yidan Zheng.

3 recordsLinked to original sources

arXiv2026

Low Latency Gaze Tracking via Latent Optical Sensing

We present a real-time gaze tracking system that directly acquires task-relevant latent features using a fully passive optical encoder. Instead of forming and processing full-resolution images, our approach leverages a microlens array with a co-designed binary chromium mask to perform spatially multiplexed optical encoding, producing a compact set of measurements sufficient for gaze estimation. By integrating sensing and feature extraction in the optical domain, the proposed system eliminates the need for high-bandwidth image readout and substantially reduces computational overhead. The encoded measurements are captured by a 4 x 4 phototransistor array and mapped to gaze direction using a lightweight neural network. Our proof-of-concept prototype enables an end-to-end sensing-to-inference latency of 3.4 ms, outperforming published research systems. We demonstrate the effectiveness of our approach on both simulated and real-world data, achieving competitive gaze estimation accuracy while significantly improving latency and energy efficiency compared to conventional camera-based pipelines. This work highlights the potential of task-driven optical sensing for ultra-low-latency, computationally efficient human-computer interaction systems.

cs.CV↗

arXiv2025

Latent Space Imaging

Digital imaging systems have traditionally relied on brute-force measurement and processing of pixels arranged on regular grids. In contrast, the human visual system performs significant data reduction from the large number of photoreceptors to the optic nerve, effectively encoding visual information into a low-bandwidth latent space representation optimized for brain processing. Inspired by this, we propose a similar approach to advance artificial vision systems. Latent Space Imaging introduces a new paradigm that combines optics and software to encode image information directly into the semantically rich latent space of a generative model. This approach substantially reduces bandwidth and memory demands during image capture and enables a range of downstream tasks focused on the latent space. We validate this principle through an initial hardware prototype based on a single-pixel camera. By implementing an amplitude modulation scheme that encodes into the generative model's latent space, we achieve compression ratios ranging from 1:100 to 1:1000 during imaging, and up to 1:16384 for downstream applications. This approach leverages the model's intrinsic linear boundaries, demonstrating the potential of latent space imaging for highly efficient imaging hardware, adaptable future applications in high-speed imaging, and task-specific cameras with significantly reduced hardware complexity.

eess.IV↗

arXiv2011

On continuous expansions of configurations of points in Euclidean space

For any two configurations of ordered points $p=(p_{1},...,\p_{N})$ and $q=(q_{1},...,q_{N})$ in Euclidean space $E^d$ such that $q$ is an expansion of $p$, there exists a continuous expansion from $p$ to $q$ in dimension 2d; Bezdek and Connelly used this to prove the Kneser-Poulsen conjecture for the planar case. In this paper, we show that this construction is optimal in the sense that for any $d \ge 2$ there exists configurations of $(d+1)^2$ points $p$ and $q$ in $E^d$ such that $q$ is an expansion of $p$ but there is no continuous expansion from $p$ to $q$ in dimension less than 2d. The techniques used in our proof are completely elementary.

math.MG↗