Related papers: Driving with DINO: Vision Foundation Features as a…

We often aim to generate images that are both photorealistic and 3D-consistent, adhering to precise geometry, material, and viewpoint controls. Typically, this is achieved by fine-tuning an image generator, pre-trained on billions of real…

Diffusion models have fundamentally transformed the field of generative models, making the assessment of similarity between customized model outputs and reference inputs critically important. However, traditional perceptual similarity…

Simulation frameworks have been key enablers for the development and validation of autonomous driving systems. However, existing methods struggle to comprehensively address the autonomy-oriented requirements of balancing: (i) dynamical…

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…

A fundamental bottleneck in Novel View Synthesis (NVS) for autonomous driving is the inherent supervision gap on novel trajectories: models are tasked with synthesizing unseen views during inference, yet lack ground truth images for these…

Generative diffusion models for end-to-end autonomous driving often suffer from mode collapse, tending to generate conservative and homogeneous behaviors. While DiffusionDrive employs predefined anchors representing different driving…

Velocity-model building is a fundamental component of seismic imaging, yet it remains a challenging inverse problem due to limited data coverage, nonlinearity, and the need to integrate heterogeneous information such as well logs. We…

LiDAR-based semantic segmentation is a key component for autonomous mobile robots, yet large-scale annotation of LiDAR point clouds is prohibitively expensive and time-consuming. Although simulators can provide labeled synthetic data,…

We present FlightDiffusion, a diffusion-model-based framework for training autonomous drones from first-person view (FPV) video. Our model generates realistic video sequences from a single frame, enriched with corresponding action spaces to…

The Vision-Language Foundation Model has recently shown outstanding performance in various perception learning tasks. The outstanding performance of the vision-language model mainly relies on large-scale pre-training datasets and different…

Accurate and high-fidelity driving scene reconstruction demands the effective utilization of comprehensive scene information as conditional inputs. Existing methods predominantly rely on 3D bounding boxes and BEV road maps for foreground…

Rapid autonomous traversal of unstructured terrain is essential for scenarios such as disaster response, search and rescue, or planetary exploration. As a vehicle navigates at the limit of its capabilities over extreme terrain, its dynamics…

Detectors often suffer from degraded performance, primarily due to the distributional gap between the source and target domains. This issue is especially evident in single-source domains with limited data, as models tend to rely on…

Collaborative perception plays a crucial role in enhancing environmental understanding by expanding the perceptual range and improving robustness against sensor failures, which primarily involves collaborative 3D detection and tracking…

End-to-End (E2E) solutions have emerged as a mainstream approach for autonomous driving systems, with Vision-Language-Action (VLA) models representing a new paradigm that leverages pre-trained multimodal knowledge from Vision-Language…

Autonomous driving systems rely heavily on robust sensor fusion to perceive complex envi- ronments. Traditional setups using RGB cameras and LiDAR often struggle in high-dynamic- range scenes or high-speed scenarios due to motion blur and…

Generating realistic and diverse road scenarios is essential for autonomous vehicle testing and validation. Nevertheless, owing to the complexity and variability of real-world road environments, creating authentic and varied scenarios for…

Open-vocabulary object detectors such as Grounding DINO are trained on vast and diverse data, achieving remarkable performance on challenging datasets. Due to that, it is unclear where to find their limitations, which is of major concern…

Open-Vocabulary Segmentation (OVS) aims to segment image regions beyond predefined category sets by leveraging semantic descriptions. While CLIP based approaches excel in semantic generalization, they frequently lack the fine-grained…

Recently, the diffusion model has emerged as a powerful generative technique for robotic policy learning, capable of modeling multi-mode action distributions. Leveraging its capability for end-to-end autonomous driving is a promising…