NeuralBlox: Real-Time Neural Representation Fusion for Robust Volumetric Mapping
This work addresses the challenge of robust volumetric mapping for robotics or AR/VR applications, though it is incremental as it builds on existing neural implicit representation methods.
The paper tackles the problem of incrementally building and updating neural implicit representations for large-scale 3D mapping from sequential partial observations, achieving real-time performance on a CPU and demonstrating improved scene completeness compared to traditional methods like TSDFs under noisy inputs.
We present a novel 3D mapping method leveraging the recent progress in neural implicit representation for 3D reconstruction. Most existing state-of-the-art neural implicit representation methods are limited to object-level reconstructions and can not incrementally perform updates given new data. In this work, we propose a fusion strategy and training pipeline to incrementally build and update neural implicit representations that enable the reconstruction of large scenes from sequential partial observations. By representing an arbitrarily sized scene as a grid of latent codes and performing updates directly in latent space, we show that incrementally built occupancy maps can be obtained in real-time even on a CPU. Compared to traditional approaches such as Truncated Signed Distance Fields (TSDFs), our map representation is significantly more robust in yielding a better scene completeness given noisy inputs. We demonstrate the performance of our approach in thorough experimental validation on real-world datasets with varying degrees of added pose noise.