An Adaptive Framework for Missing Depth Inference Using Joint Bilateral Filter

TL;DR

This paper introduces an adaptive framework utilizing joint bilateral filters for missing depth inference, improving depth map accuracy from various sensors by dynamically adjusting to complex geometries and identifying problematic areas.

Contribution

The paper presents a novel adaptive filtering approach that enhances depth estimation accuracy and robustness, incorporating a fast update algorithm for pixel fragility analysis using machine learning.

Findings

Outperforms existing methods in depth map accuracy

Effectively handles complex 3D geometries

Enables dynamic visualization of problematic depth areas

Abstract

Depth imaging has largely focused on sensor and intrinsics properties. However, the accuracy of acquire pixel is largely dependent on the capture. We propose a new depth estimation and approximation algorithm which takes an arbitrary 3D point cloud as input, with potentially complex geometric structures, and generates automatically a bounding box which is used to clamp the 3D distribution into a valid range. We then infer the desired compact geometric network from complex 3D geometries by using a series of adaptive joint bilateral filters. Our approach leverages these input depth in the construction of a compact descriptive adaptive filter framework. The built system that allows a user to control the result of capture depth map to fit the target geometry. In addition, it is desirable to visualize structurally problematic areas of the depth data in a dynamic environment. To provide this feature, we investigate a fast update algorithm for the fragility of each pixel's corresponding 3D point using machine learning. We present a new for of feature vector analysis and demonstrate the effectiveness in the dataset. In our experiment, we demonstrate the practicality and benefits of our proposed method by computing accurate solutions captured depth map from different types of sensors and shows better results than existing methods.