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