Related papers: Rethinking Driving World Model as Synthetic Data G…

Unlike humans, who can effortlessly estimate the entirety of objects even when partially occluded, modern computer vision algorithms still find this aspect extremely challenging. Leveraging this amodal perception for autonomous driving…

Training models to high-end performance requires availability of large labeled datasets, which are expensive to get. The goal of our work is to automatically synthesize labeled datasets that are relevant for a downstream task. We propose…

This paper presents DriVerse, a generative model for simulating navigation-driven driving scenes from a single image and a future trajectory. Previous autonomous driving world models either directly feed the trajectory or discrete control…

Using generative models to synthesize new data has become a de-facto standard in autonomous driving to address the data scarcity issue. Though existing approaches are able to boost perception models, we discover that these approaches fail…

Machine learning heavily relies on data, but real-world applications often encounter various data-related issues. These include data of poor quality, insufficient data points leading to under-fitting of machine learning models, and…

Generating multi-camera street-view videos is critical for augmenting autonomous driving datasets, addressing the urgent demand for extensive and varied data. Due to the limitations in diversity and challenges in handling lighting…

Accumulating substantial volumes of real-world driving data proves pivotal in the realm of trajectory forecasting for autonomous driving. Given the heavy reliance of current trajectory forecasting models on data-driven methodologies, we aim…

Controllable human video generation aims to produce realistic videos of humans with explicitly guided motions and appearances,serving as a foundation for digital humans, animation, and embodied AI.However, the scarcity of largescale,…

The synthesis of spatiotemporally coherent 4D content presents fundamental challenges in computer vision, requiring simultaneous modeling of high-fidelity spatial representations and physically plausible temporal dynamics. Current…

Datasets are essential for training and testing vehicle perception algorithms. However, the collection and annotation of real-world images is time-consuming and expensive. Driving simulators offer a solution by automatically generating…

While developing perception based deep learning models, the benefit of synthetic data is enormous. However, performance of networks trained with synthetic data for certain computer vision tasks degrade significantly when tested on real…

Recent progress in robot learning has been driven by large-scale datasets and powerful visuomotor policy architectures, yet policy robustness remains limited by the substantial cost of collecting diverse demonstrations, particularly for…

World models have demonstrated superiority in autonomous driving, particularly in the generation of multi-view driving videos. However, significant challenges still exist in generating customized driving videos. In this paper, we propose…

Rare and challenging driving scenarios are critical for autonomous vehicle development. Since they are difficult to encounter, simulating or generating them using generative models is a popular approach. Following previous efforts to…

The recent advent of large-scale 3D data, e.g. Objaverse, has led to impressive progress in training pose-conditioned diffusion models for novel view synthesis. However, due to the synthetic nature of such 3D data, their performance drops…

We present ReinDriveGen, a framework that enables full controllability over dynamic driving scenes, allowing users to freely edit actor trajectories to simulate safety-critical corner cases such as front-vehicle collisions, drifting cars,…

Autonomous driving relies on a huge volume of real-world data to be labeled to high precision. Alternative solutions seek to exploit driving simulators that can generate large amounts of labeled data with a plethora of content variations.…

Understanding the world in first-person view is fundamental in Augmented Reality (AR). This immersive perspective brings dramatic visual changes and unique challenges compared to third-person views. Synthetic data has empowered…

Current end-to-end deep learning driving models have two problems: (1) Poor generalization ability of unobserved driving environment when diversity of training driving dataset is limited (2) Lack of accident explanation ability when driving…

Collecting multi-view driving scenario videos to enhance the performance of 3D visual perception tasks presents significant challenges and incurs substantial costs, making generative models for realistic data an appealing alternative. Yet,…