Extending DeepSDF for automatic 3D shape retrieval and similarity transform estimation
This addresses a practical problem for 3D shape retrieval and compression in real-world scenes where objects vary in scale and orientation.
The paper tackles the limitation of DeepSDF requiring query shapes to be in the same canonical scale and pose as training data by jointly estimating shape and similarity transform parameters, reporting favorable comparisons to state-of-the-art methods on synthetic and real datasets.
Recent advances in computer graphics and computer vision have found successful application of deep neural network models for 3D shapes based on signed distance functions (SDFs) that are useful for shape representation, retrieval, and completion. However, this approach has been limited by the need to have query shapes in the same canonical scale and pose as those observed during training, restricting its effectiveness on real world scenes. We present a formulation to overcome this issue by jointly estimating shape and similarity transform parameters. We conduct experiments to demonstrate the effectiveness of this formulation on synthetic and real datasets and report favorable comparisons to the state of the art. Finally, we also emphasize the viability of this approach as a form of 3D model compression.