Semantic Photometric Bundle Adjustment on Natural Sequences
This work provides a significant improvement for dense 3D object reconstruction from natural image sequences, particularly benefiting applications where objects are often occluded or poorly textured.
This paper addresses the challenge of dense object reconstruction from natural image sequences, particularly when objects are partially observed or lack texture. The authors propose semantic Photometric Bundle Adjustment (PBA), which integrates a 3D object prior derived from deep learning into the photometric bundle adjustment framework, achieving state-of-the-art performance on various natural sequences.
The problem of obtaining dense reconstruction of an object in a natural sequence of images has been long studied in computer vision. Classically this problem has been solved through the application of bundle adjustment (BA). More recently, excellent results have been attained through the application of photometric bundle adjustment (PBA) methods -- which directly minimize the photometric error across frames. A fundamental drawback to BA & PBA, however, is: (i) their reliance on having to view all points on the object, and (ii) for the object surface to be well textured. To circumvent these limitations we propose semantic PBA which incorporates a 3D object prior, obtained through deep learning, within the photometric bundle adjustment problem. We demonstrate state of the art performance in comparison to leading methods for object reconstruction across numerous natural sequences.