相关论文: LaGen: Towards Autoregressive LiDAR Scene Generati…

Semantic grids are a useful representation of the environment around a robot. They can be used in autonomous vehicles to concisely represent the scene around the car, capturing vital information for downstream tasks like navigation or…

Synthesizing high-fidelity and controllable 4D LiDAR data is crucial for creating scalable simulation environments for autonomous driving. This task is inherently challenging due to the sensor's unique spherical geometry, the temporal…

In this paper, we propose an automatic labeled sequential data generation pipeline for human segmentation and velocity estimation with point clouds. Considering the impact of deep neural networks, state-of-the-art network architectures have…

To achieve autonomous driving without high-definition maps, we present a model capable of generating multiple plausible paths from egocentric images for autonomous vehicles. Our generative model comprises two neural networks: the feature…

Simulation-based testing has emerged as an essential tool for verifying and validating autonomous vehicles (AVs). However, contemporary methodologies, such as deterministic and imitation learning-based driver models, struggle to capture the…

Controllable synthetic data generation can substantially lower the annotation cost of training data. Prior works use diffusion models to generate driving images conditioned on the 3D object layout. However, those models are trained on…

Understanding and replicating the real world is a critical challenge in Artificial General Intelligence (AGI) research. To achieve this, many existing approaches, such as world models, aim to capture the fundamental principles governing the…

We present a latent diffusion model over 3D scenes, that can be trained using only 2D image data. To achieve this, we first design an autoencoder that maps multi-view images to 3D Gaussian splats, and simultaneously builds a compressed…

In the autonomous driving domain, data collection and annotation from real vehicles are expensive and sometimes unsafe. Simulators are often used for data augmentation, which requires realistic sensor models that are hard to formulate and…

Automotive radar has shown promising developments in environment perception due to its cost-effectiveness and robustness in adverse weather conditions. However, the limited availability of annotated radar data poses a significant challenge…

Diverse and realistic traffic scenarios are crucial for evaluating the AI safety of autonomous driving systems in simulation. This work introduces a data-driven method called TrafficGen for traffic scenario generation. It learns from the…

Utilization of classification latent space information for downstream reconstruction and generation is an intriguing and a relatively unexplored area. In general, discriminative representations are rich in class-specific features but are…

Recent advances in 3D scene generation produce visually appealing output, but current representations hinder artists' workflows that require modifiable 3D textured mesh scenes for visual effects and game development. Despite significant…

We present GuidedSceneGen, a text-to-3D generation framework that produces metrically accurate, globally consistent, and semantically interpretable indoor scenes. Unlike prior text-driven methods that often suffer from geometric drift or…

LiDAR-based 3D object detectors typically rely on proposal heads with hand-crafted components like anchor assignment and non-maximum suppression (NMS), complicating training and limiting extensibility. We present AutoReg3D, an…

Generative modeling frameworks have emerged as an effective approach to capture high-dimensional image distributions from large datasets without requiring domain-specific knowledge, a capability essential for longitudinal disease…

Autoregressive (AR) visual generation has emerged as a powerful paradigm for image and multimodal synthesis, owing to its scalability and generality. However, existing AR image generation suffers from severe memory bottlenecks due to the…

Controllable generation, which enables fine-grained control over generated outputs, has emerged as a critical focus in visual generative models. Currently, there are two primary technical approaches in visual generation: diffusion models…

In this paper, we focus on latent modification and generation of 3D point cloud object models with respect to their semantic parts. Different to the existing methods which use separate networks for part generation and assembly, we propose a…

Unsupervised generation of clothed virtual humans with various appearance and animatable poses is important for creating 3D human avatars and other AR/VR applications. Existing methods are either limited to rigid object modeling, or not…