paper-with-me

홈 › Papers

DrivingScene: A Multi-Task Online Feed-Forward 3D Gaussian Splatting Method for Dynamic Driving Scenes

2025-10-14 · Qirui Hou, Wenzhang Sun, Chang Zeng, Chunfeng Wang, Hao Li, Jianxun Cui arxiv

Real-time, high-fidelity reconstruction of dynamic driving scenes is challenged by complex dynamics and sparse views, with prior methods struggling to balance quality and efficiency. We propose DrivingScene, an online, feed-forward framework that reconstructs 4D dynamic scenes from only two consecutive surround-view images. Our key innovation is a lightweight residual flow network that predicts the non-rigid motion of dynamic objects per camera on top of a learned static scene prior, explicitly modeling dynamics via scene flow. We also introduce a coarse-to-fine training paradigm that circumvents the instabilities common to end-to-end approaches. Experiments on nuScenes dataset show our image-only method simultaneously generates high-quality depth, scene flow, and 3D Gaussian point clouds online, significantly outperforming state-of-the-art methods in both dynamic reconstruction and novel view synthesis.

📄 PDF Abstract BibTeX arXiv:2510.24734

Code (0)

등록된 구현이 없습니다.

Tasks

Dynamic ReconstructionNovel View SynthesisPoint Clouds

Similar Papers 제목 키워드 기반

Feedforward Control in the Presence of Input Nonlinearities: A Learning-based Approach

2022-09-23 · Jilles van Hulst, Maurice Poot, Dragan Kostić, Kai Wa Yan 외

Advanced feedforward control methods enable mechatronic systems to perform varying motion tasks with extreme accuracy and throughput. The aim of this paper is to develop a data-driven feedforward controller that addresse…

Learning nonlinear feedforward: a Gaussian Process Approach Applied to a Printer with Friction

2021-12-07 · Max van Meer, Maurice Poot, Jim Portegies, Tom Oomen

Feedforward control is essential to achieving good tracking performance in positioning systems. The aim of this paper is to develop an identification strategy for inverse models of systems with nonlinear dynamics of unkn…

Friction

On the Role of Transformer Feed-Forward Layers in Nonlinear In-Context Learning

2025-01-30 · Haoyuan Sun, Ali Jadbabaie, Navid Azizan

Transformer-based models demonstrate a remarkable ability for in-context learning (ICL), where they can adapt to unseen tasks from a few prompt examples without parameter updates. Notably, recent research has provided in…

In-Context Learning

Physics-Guided Neural Networks for Feedforward Control: An Orthogonal Projection-Based Approach

2022-01-10 · Johan Kon, Dennis Bruijnen, Jeroen van de Wijdeven, Marcel Heertjes 외

Unknown nonlinear dynamics can limit the performance of model-based feedforward control. The aim of this paper is to develop a feedforward control framework for systems with unknown, typically nonlinear, dynamics. To add…

Friction

FreeStreamGS: Online Feed-forward 3D Gaussian Splatting from Unposed Streaming Inputs

2026-06-02 · Ruiyang Chen, Feiran Li, Chu Zhou, Zonglin Li 외 arxiv

Feed-forward 3D Gaussian Splatting (3DGS) allows efficient and high-fidelity novel view synthesis (NVS) from an offline recorded image sequence. However, achieving online NVS from streaming and unposed image inputs remai…

Novel View Synthesis