Learnable Burst-Encodable Time-of-Flight Imaging for High-Fidelity Long-Distance Depth Sensing

2025-05-28

AI Summary

Long-range depth imaging faces dual challenges: high hardware cost in direct time-of-flight (dToF) systems and phase ambiguity coupled with low signal-to-noise ratio (SNR) in indirect time-of-flight (iToF) systems. To address these, this work proposes a burst-encoded ToF imaging paradigm: it employs burst-mode pulse emission and full-cycle phase delay estimation to eliminate phase wrapping; introduces an end-to-end learnable framework jointly optimizing hardware-feasible encoding functions and depth reconstruction networks; and enforces physical realizability of optical encoding via dual-well constraints and first-order difference regularization. This is the first work to realize a unified burst-encodable dToF/iToF architecture with co-optimized encoding and reconstruction. Experimental validation—spanning simulation and real-world measurements up to 100 meters—demonstrates a 42% reduction in depth error, significant SNR improvement, and stable ranging beyond 150 meters.

Technology Category

• Search and Optimization: Distributed Search
• Computer Vision: Learning & Optimization for CV
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Long-distance depth imaging holds great promise for applications such as autonomous driving and robotics. Direct time-of-flight (dToF) imaging offers high-precision, long-distance depth sensing, yet demands ultra-short pulse light sources and high-resolution time-to-digital converters. In contrast, indirect time-of-flight (iToF) imaging often suffers from phase wrapping and low signal-to-noise ratio (SNR) as the sensing distance increases. In this paper, we introduce a novel ToF imaging paradigm, termed Burst-Encodable Time-of-Flight (BE-ToF), which facilitates high-fidelity, long-distance depth imaging. Specifically, the BE-ToF system emits light pulses in burst mode and estimates the phase delay of the reflected signal over the entire burst period, thereby effectively avoiding the phase wrapping inherent to conventional iToF systems. Moreover, to address the low SNR caused by light attenuation over increasing distances, we propose an end-to-end learnable framework that jointly optimizes the coding functions and the depth reconstruction network. A specialized double well function and first-order difference term are incorporated into the framework to ensure the hardware implementability of the coding functions. The proposed approach is rigorously validated through comprehensive simulations and real-world prototype experiments, demonstrating its effectiveness and practical applicability.

Problem

• Enables high-fidelity long-distance depth sensing
• Overcomes phase wrapping and low SNR in iToF
• Jointly optimizes coding and reconstruction via learnable framework

Innovation

• Burst-Encodable ToF for long-distance depth imaging
• Learnable framework optimizes coding and reconstruction
• Double well function ensures hardware implementability