Over the past two decades, research in the field of Simultaneous Localization and Mapping (SLAM) has undergone a significant evolution, highlighting its critical role in enabling autonomous exploration of unseen environments. This evolution ranges from hand-crafted methods, through the era of deep learning, to more recent developments in the wake of Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS) representations.Â
These latter advancements, in particular, are happening right now at unprecedented speed: indeed, since the first NeRF-inspired SLAM system came out in 2021 -- iMAP: Implicit Mapping and Positioning in Real-Time, ICCV 2021 -- more than 200 papers have been posted on arXiv or published at top-tier conferences in Computer Vision and Machine Learning. For a recent overview, see Tosi et al. "How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Survey".
This sudden revolution brought excitement to the research community paving the way, on the one hand, for new applications beyond the original purpose of SLAM systems. Among these is the possibility of rendering realistic novel views from unobserved viewpoints, something made possible by the recent advances in novel view synthesis, which further extends the overall SLAM purpose.
On the other hand, new challenges emerged caused by the speed at which newer and newer SLAM systems are being proposed.
For example, as many papers came out in a very short amount of time, most of them are concurrent and did not have the chance to compare to each other, leaving several open questions -- e.g., which are the real key factors in many of these SLAM systems? Which scene representation is the best suited?
The workshop aims to bring researchers together being interested in dense neural SLAM methods and provide a forum for the mutual exchange of experiences, beliefs, intuitions, ideas and future research directions.
With a mix of invited keynote talks of renown experts, a poster session and a panel discussion, we invite people both from academia and industry across all seniority levels to learn from each other and engage in discussions.