相关论文: DreamCar: Leveraging Car-specific Prior for in-the…

3D cars are commonly used in self-driving systems, virtual/augmented reality, and games. However, existing 3D car datasets are either synthetic or low-quality, limiting their applications in practical scenarios and presenting a significant…

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…

3D car modeling is crucial for applications in autonomous driving systems, virtual and augmented reality, and gaming. However, due to the distinctive properties of cars, such as highly reflective and transparent surface materials, existing…

Realistic simulation is key to enabling safe and scalable development of % self-driving vehicles. A core component is simulating the sensors so that the entire autonomy system can be tested in simulation. Sensor simulation involves modeling…

Creating realistic and simulation-ready 3D assets is crucial for autonomous driving research and virtual environment construction. However, existing 3D vehicle generation methods are often trained on synthetic data with significant domain…

Volumetric scene reconstruction from a single image is crucial for a broad range of applications like autonomous driving and robotics. Recent volumetric reconstruction methods achieve impressive results, but generally require expensive 3D…

The 3D reconstruction of objects is a prerequisite for many highly relevant applications of computer vision such as mobile robotics or autonomous driving. To deal with the inverse problem of reconstructing 3D objects from their 2D…

Diffusion models have emerged as the new state-of-the-art generative model with high quality samples, with intriguing properties such as mode coverage and high flexibility. They have also been shown to be effective inverse problem solvers,…

Autonomous driving has attracted remarkable attention from both industry and academia. An important task is to estimate 3D properties(e.g.translation, rotation and shape) of a moving or parked vehicle on the road. This task, while critical,…

Large-scale scene data is essential for training and testing in robot learning. Neural reconstruction methods have promised the capability of reconstructing large physically-grounded outdoor scenes from captured sensor data. However, these…

This paper presents an effective solution for view extrapolation in autonomous driving scenarios. Recent approaches focus on generating shifted novel view images from given viewpoints using diffusion models. However, these methods heavily…

Decompositional reconstruction of 3D scenes, with complete shapes and detailed texture of all objects within, is intriguing for downstream applications but remains challenging, particularly with sparse views as input. Recent approaches…

Drag-based editing has become popular in 2D content creation, driven by the capabilities of image generative models. However, extending this technique to 3D remains a challenge. Existing 3D drag-based editing methods, whether employing…

We present a novel approach to detect, segment, and reconstruct complete textured 3D models of vehicles from a single image for autonomous driving. Our approach combines the strengths of deep learning and the elegance of traditional…

Text-to-3D is an emerging task that allows users to create 3D content with infinite possibilities. Existing works tackle the problem by optimizing a 3D representation with guidance from pre-trained diffusion models. An apparent drawback is…

Current 3D reconstruction techniques struggle to infer unbounded scenes from a few images faithfully. Specifically, existing methods have high computational demands, require detailed pose information, and cannot reconstruct occluded regions…

Modeling the 3D world from sensor data for simulation is a scalable way of developing testing and validation environments for robotic learning problems such as autonomous driving. However, manually creating or re-creating real-world-like…

High-fidelity and controllable 3D simulation is essential for addressing the long-tail data scarcity in Autonomous Driving (AD), yet existing methods struggle to simultaneously achieve photorealistic rendering and interactive traffic…

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…

We present an approach for reconstructing vehicles from a single (RGB) image, in the context of autonomous driving. Though the problem appears to be ill-posed, we demonstrate that prior knowledge about how 3D shapes of vehicles project to…