Related papers: StreetForward: Perceiving Dynamic Street with Feed…

High-fidelity reconstruction of driving scenes is crucial for autonomous driving. While recent feedforward 3D Gaussian Splatting (3DGS) methods enable fast reconstruction, their per-pixel Gaussian prediction paradigm often suffers from…

Autonomous driving needs fast, scalable 4D reconstruction and re-simulation for training and evaluation, yet most methods for dynamic driving scenes still rely on per-scene optimization, known camera calibration, or short frame windows,…

We propose DrivingForward, a feed-forward Gaussian Splatting model that reconstructs driving scenes from flexible surround-view input. Driving scene images from vehicle-mounted cameras are typically sparse, with limited overlap, and the…

Reconstructing dynamic 4D scenes remains challenging due to the presence of moving objects that corrupt camera pose estimation. Existing optimization methods alleviate this issue with additional supervision, but they are mostly…

Dynamic scene reconstruction in autonomous driving remains a fundamental challenge due to significant temporal variations, moving objects, and complex scene dynamics. Existing feed-forward 3D models have demonstrated strong performance in…

Dynamic driving scene reconstruction is critical for autonomous driving simulation and closed-loop learning. While recent feed-forward methods have shown promise for 3D reconstruction, they struggle with long-range driving sequences due to…

High-fidelity visual reconstruction and novel-view synthesis are essential for realistic closed-loop evaluation in autonomous driving. While 4D Gaussian Splatting (4DGS) offers a promising balance of accuracy and efficiency, existing…

We present a novel multi-view implicit surface reconstruction technique, termed StreetSurf, that is readily applicable to street view images in widely-used autonomous driving datasets, such as Waymo-perception sequences, without necessarily…

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…

We present FRUC, a feed-forward 3D Gaussian splatting framework for dynamic scene reconstruction from uncalibrated collaborative driving views. Existing multi-agent reconstruction frameworks are often hindered by rigid prerequisites,…

Visually localizing an image, i.e., estimating its camera pose, requires building a scene representation that serves as a visual map. The representation we choose has direct consequences towards the practicability of our system. Even when…

Reconstructing 3D representations from 2D inputs is a fundamental task in computer vision and graphics, serving as a cornerstone for understanding and interacting with the physical world. While traditional methods achieve high fidelity,…

Feed-forward 3D reconstruction for autonomous driving has advanced rapidly, yet existing methods struggle with the joint challenges of sparse, non-overlapping camera views and complex scene dynamics. We present UniSplat, a general…

Feedforward Gaussian Splatting has recently emerged as an efficient paradigm for 4D reconstruction in autonomous driving. However, in unstructured off-road scenes, its performance degrades due to high-frequency geometry, ego-motion jitter,…

Urban scene reconstruction is critical for autonomous driving, enabling structured 3D representations for data synthesis and closed-loop testing. Supervised approaches rely on costly human annotations and lack scalability, while current…

Estimating the 3D trajectory of every pixel from a monocular video is crucial and promising for a comprehensive understanding of the 3D dynamics of videos. Recent monocular 3D tracking works demonstrate impressive performance, but are…

The recent years have seen a surge of interest in methods for imaging beyond the direct line of sight. The most prominent techniques rely on time-resolved optical impulse responses, obtained by illuminating a diffuse wall with an ultrashort…

Reliable incremental estimation of camera poses and 3D reconstruction is key to enable various applications including robotics, interactive visualization, and augmented reality. However, this task is particularly challenging in dynamic…

The accurate reconstruction of dynamic street scenes is critical for applications in autonomous driving, augmented reality, and virtual reality. Traditional methods relying on dense point clouds and triangular meshes struggle with moving…

3D reconstruction and view synthesis are foundational problems in computer vision, graphics, and immersive technologies such as augmented reality (AR), virtual reality (VR), and digital twins. Traditional methods rely on computationally…