Related papers: Driv3R: Learning Dense 4D Reconstruction for Auton…

DUSt3R-based end-to-end scene reconstruction has recently shown promising results in dense visual SLAM. However, most existing methods only use image pairs to estimate pointmaps, overlooking spatial memory and global consistency.To this…

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…

With the popularity of monocular videos generated by video sharing and live broadcasting applications, reconstructing and editing dynamic scenes in stationary monocular cameras has become a special but anticipated technology. In contrast to…

Powerful 3D representations such as DUSt3R invariant point maps, which encode 3D shape and camera parameters, have significantly advanced feed forward 3D reconstruction. While point maps assume static scenes, Dynamic Point Maps (DPMs)…

Learning to understand dynamic 3D scenes from imagery is crucial for applications ranging from robotics to scene reconstruction. Yet, unlike other problems where large-scale supervised training has enabled rapid progress, directly…

In crowded urban environments where traffic is dense, current technologies struggle to oversee tight navigation, but surface-level understanding allows autonomous vehicles to safely assess proximity to surrounding obstacles. 3D or 2D scene…

Reconstructing and tracking dynamic 3D scenes remains a fundamental challenge in computer vision. Existing approaches often decouple geometry from motion: multi-view reconstruction methods assume static scenes, while dynamic tracking…

Dense 3D tracking from monocular video is fundamental to dynamic scene understanding. While recent 3D foundation models provide reliable per-frame geometry, recovering object motion in this geometry remains challenging and benefits from…

In this paper, we introduce SLAM3R, a novel and effective system for real-time, high-quality, dense 3D reconstruction using RGB videos. SLAM3R provides an end-to-end solution by seamlessly integrating local 3D reconstruction and global…

Large scale 3D scene reconstruction is important for applications such as virtual reality and simulation. Existing neural rendering approaches (e.g., NeRF, 3DGS) have achieved realistic reconstructions on large scenes, but optimize per…

Reconstructing large-scale dynamic scenes from visual observations is a fundamental challenge in computer vision, with critical implications for robotics and autonomous systems. While recent differentiable rendering methods such as Neural…

Photorealistic 4D reconstruction of street scenes is essential for developing real-world simulators in autonomous driving. However, most existing methods perform this task offline and rely on time-consuming iterative processes, limiting…

Learning-based 3D reconstruction has emerged as a transformative technique in autonomous driving, enabling precise modeling of environments through advanced neural representations. It has inspired pioneering solutions for vital tasks in…

Multi-view 3D reconstruction remains a core challenge in computer vision, particularly in applications requiring accurate and scalable representations across diverse perspectives. Current leading methods such as DUSt3R employ a…

While recent feed-forward 3D reconstruction models accelerate 3D reconstruction by jointly inferring dense geometry and camera poses in a single pass, their reliance on dense attention imposes a quadratic complexity, creating a prohibitive…

Recent advancements in 4D scene reconstruction, particularly those leveraging diffusion priors, have shown promise for novel view synthesis in autonomous driving. However, these methods often process frames independently or in a…

3D object detection and dense depth estimation are one of the most vital tasks in autonomous driving. Multiple sensor modalities can jointly attribute towards better robot perception, and to that end, we introduce a method for jointly…

Novel view synthesis from monocular videos of dynamic scenes with unknown camera poses remains a fundamental challenge in computer vision and graphics. While recent advances in 3D representations such as Neural Radiance Fields (NeRF) and 3D…

Neural reconstruction models for autonomous driving simulation have made significant strides in recent years, with dynamic models becoming increasingly prevalent. However, these models are typically limited to handling in-domain objects…

Synthesizing photo-realistic visual observations from an ego vehicle's driving trajectory is a critical step towards scalable training of self-driving models. Reconstruction-based methods create 3D scenes from driving logs and synthesize…