Unsigned Distance Field as an Accurate 3D Scene Representation for Neural Scene Completion
This addresses scene completion accuracy for 3D reconstruction applications, representing an incremental improvement over existing SDF-based methods.
The paper tackles the problem of scene completion from partial scans by proposing an Unsigned Distance Function (UDF) as an alternative to Signed Distance Functions (SDFs), showing improved completion results on indoor and outdoor point clouds from RGB-D and LiDAR sensors.
Scene Completion is the task of completing missing geometry from a partial scan of a scene. Most previous methods compute an implicit representation from range data using a Truncated Signed Distance Function (T-SDF) computed on a 3D grid as input to neural networks. The truncation decreases but does not remove the border errors introduced by the sign of SDF for open surfaces. As an alternative, we present an Unsigned Distance Function (UDF) as an input representation to scene completion neural networks. The proposed UDF is simple, and efficient as a geometry representation, and can be computed on any point cloud. In contrast to usual Signed Distance Functions, our UDF does not require normal computation. To obtain the explicit geometry, we present a method for extracting a point cloud from discretized UDF values on a sparse grid. We compare different SDFs and UDFs for the scene completion task on indoor and outdoor point clouds collected using RGB-D and LiDAR sensors and show improved completion using the proposed UDF function.