3d gaussian splatting: Survey, technologies, challenges, and opportunities

Y Bao, T Ding, J Huo, Y Liu, Y Li, W Li… - IEEE Transactions on …, 2025‏ - ieeexplore.ieee.org
3D Gaussian Splatting (3DGS) has emerged as a prominent technique with the potential to
become a mainstream method for 3D representations. It can effectively transform multi-view …

[PDF][PDF] Scube: Instant large-scale scene reconstruction using voxsplats

X Ren, Y Lu, JZ Wu, H Ling, M Chen… - The Thirty-eighth …, 2024‏ - proceedings.neurips.cc
We present SCube, a novel method for reconstructing large-scale 3D scenes (geometry,
appearance, and semantics) from a sparse set of posed images. Our method encodes …

Distractor-free Generalizable 3D Gaussian Splatting

Y Bao, J Liao, J Huo, Y Gao - arxiv preprint arxiv:2411.17605, 2024‏ - arxiv.org
We present DGGS, a novel framework addressing the previously unexplored challenge of
Distractor-free Generalizable 3D Gaussian Splatting (3DGS). It accomplishes two key …

PINGS: Gaussian Splatting Meets Distance Fields within a Point-Based Implicit Neural Map

Y Pan, X Zhong, L **, L Wiesmann, M Popović… - arxiv preprint arxiv …, 2025‏ - arxiv.org
Robots require high-fidelity reconstructions of their environment for effective operation. Such
scene representations should be both, geometrically accurate and photorealistic to support …

Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos

H Liang, J Ren, A Mirzaei, A Torralba, Z Liu… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Recent advancements in static feed-forward scene reconstruction have demonstrated
significant progress in high-quality novel view synthesis. However, these models often …

[PDF][PDF] Towards Zero Bottlenecks for Scaling Autonomous Driving

A Tonderski - 2025‏ - lup.lub.lu.se
In this dissertation I examine the main scaling challenges in autonomous driving
development, discussing recent advances in the field while contributing specific solutions to …

Multimodální strojové učení pro automatické porozumění městským prostředím

V Antonín - 2024‏ - dspace.cvut.cz
Tato práce se zabývá multimodálním stojovým učením s cílem řešit problémy při vývoji
modelů strojového učení s omezeným množstvím anotovaných trénovacích dat, což je …