CVLGROAug 8, 2021

Joint Depth and Normal Estimation from Real-world Time-of-flight Raw Data

arXiv:2108.03649v16 citationsHas Code
Originality Incremental advance
AI Analysis

This work addresses the problem of improving depth and normal estimation for ToF sensors, which is incremental as it builds on existing methods with a new dataset and loss function.

The paper tackles joint depth and normal estimation from time-of-flight (ToF) raw sensor data by constructing the first large-scale dataset (ToF-100) and proposing a framework with a robust Chamfer loss, resulting in efficient reconstruction of high-resolution maps that significantly outperform state-of-the-art methods.

We present a novel approach to joint depth and normal estimation for time-of-flight (ToF) sensors. Our model learns to predict the high-quality depth and normal maps jointly from ToF raw sensor data. To achieve this, we meticulously constructed the first large-scale dataset (named ToF-100) with paired raw ToF data and ground-truth high-resolution depth maps provided by an industrial depth camera. In addition, we also design a simple but effective framework for joint depth and normal estimation, applying a robust Chamfer loss via jittering to improve the performance of our model. Our experiments demonstrate that our proposed method can efficiently reconstruct high-resolution depth and normal maps and significantly outperforms state-of-the-art approaches. Our code and data will be available at \url{https://github.com/hkustVisionRr/JointlyDepthNormalEstimation}

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes