SMORE: Simultaneous Map and Object REconstruction

TL;DR

SMORE introduces a holistic neural surface reconstruction method for large-scale dynamic urban scenes from LiDAR, enabling accurate modeling of moving objects and backgrounds through global optimization and coordinate descent.

Contribution

The paper presents a novel global optimization framework for dynamic scene reconstruction from LiDAR that decomposes scenes into moving objects and background without retraining.

Findings

Significantly improves dynamic surface reconstruction accuracy.

Enables auto-labeling and ground truth generation for complex scenes.

Outperforms prior methods by an order of magnitude in dynamic reconstruction.

Abstract

We present a method for dynamic surface reconstruction of large-scale urban scenes from LiDAR. Depth-based reconstructions tend to focus on small-scale objects or large-scale SLAM reconstructions that treat moving objects as outliers. We take a holistic perspective and optimize a compositional model of a dynamic scene that decomposes the world into rigidly-moving objects and the background. To achieve this, we take inspiration from recent novel view synthesis methods and frame the reconstruction problem as a global optimization over neural surfaces, ego poses, and object poses, which minimizes the error between composed spacetime surfaces and input LiDAR scans. In contrast to view synthesis methods, which typically minimize 2D errors with gradient descent, we minimize a 3D point-to-surface error by coordinate descent, which we decompose into registration and surface reconstruction steps. Each step can be handled well by off-the-shelf methods without any re-training. We analyze the surface reconstruction step for rolling-shutter LiDARs, and show that deskewing operations common in continuous time SLAM can be applied to dynamic objects as well, improving results over prior art by an order of magnitude. Beyond pursuing dynamic reconstruction as a goal in and of itself, we propose that such a system can be used to auto-label partially annotated sequences and produce ground truth annotation for hard-to-label problems such as depth completion and scene flow. Please see https://anishmadan23.github.io/smore/ for more visual results.