Related papers: FAR-Drive: Frame-AutoRegressive Video Generation i…
Diffusion models are advancing autonomous driving by enabling realistic data synthesis, predictive end-to-end planning, and closed-loop simulation, with a primary focus on temporally consistent generation. However, large-scale 3D scene…
Visual autoregressive models achieve remarkable generation quality through next-scale predictions across multi-scale token pyramids. However, the conventional method uses uniform scale downsampling to build these pyramids, leading to…
Arbitrary viewpoint image generation holds significant potential for autonomous driving, yet remains a challenging task due to the lack of ground-truth data for extrapolated views, which hampers the training of high-fidelity generative…
The long-tail distribution of real driving data poses challenges for training and testing autonomous vehicles (AV), where rare yet crucial safety-critical scenarios are infrequent. And virtual simulation offers a low-cost and efficient…
Generative models offer a scalable and flexible paradigm for simulating complex environments, yet current approaches fall short in addressing the domain-specific requirements of autonomous driving - such as multi-agent interactions,…
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,…
The field of autonomous driving increasingly demands high-quality annotated video training data. In this paper, we propose Panacea+, a powerful and universally applicable framework for generating video data in driving scenes. Built upon the…
Urban scene synthesis with video generation models has recently shown great potential for autonomous driving. Existing video generation approaches to autonomous driving primarily focus on RGB video generation and lack the ability to support…
High-fidelity visual reconstruction and novel-view synthesis are essential for realistic closed-loop evaluation in autonomous driving. While 4D Gaussian Splatting (4DGS) offers a promising balance of accuracy and efficiency, existing…
Realistic and controllable simulation is critical for advancing end-to-end autonomous driving, yet existing approaches often struggle to support novel view synthesis under large viewpoint changes or to ensure geometric consistency. We…
The delivery of high-quality, low-latency video streams is critical for remote autonomous vehicle control, where operators must intervene in real time. However, reliable video delivery over Fourth/Fifth-Generation (4G/5G) mobile networks is…
Autonomous driving involves complex decision-making in highly interactive environments, requiring thoughtful negotiation with other traffic participants. While reinforcement learning provides a way to learn such interaction behavior,…
Inference speed and tracking performance are two critical evaluation metrics in the field of visual tracking. However, high-performance trackers often suffer from slow processing speeds, making them impractical for deployment on…
We present ART$\boldsymbol{\cdot}$V, an efficient framework for auto-regressive video generation with diffusion models. Unlike existing methods that generate entire videos in one-shot, ART$\boldsymbol{\cdot}$V generates a single frame at a…
Generating long videos that can show complex stories, like movie scenes from scripts, has great promise and offers much more than short clips. However, current methods that use autoregression with diffusion models often struggle because…
Monocular depth estimation can benefit from autoregressive (AR) generation, but direct AR modeling is hindered by the modality gap between RGB and depth, inefficient pixel-wise generation, and instability in continuous depth prediction. We…
Frame-level autoregressive (frame-AR) models have achieved significant progress, enabling real-time video generation comparable to bidirectional diffusion models and serving as a foundation for interactive world models and game engines.…
Conventional wisdom suggests that autoregressive models are used to process discrete data. When applied to continuous modalities such as visual data, Visual AutoRegressive modeling (VAR) typically resorts to quantization-based approaches to…
Recent advances in video super-resolution have shown that convolutional neural networks combined with motion compensation are able to merge information from multiple low-resolution (LR) frames to generate high-quality images. Current…
We present FRUC, a feed-forward 3D Gaussian splatting framework for dynamic scene reconstruction from uncalibrated collaborative driving views. Existing multi-agent reconstruction frameworks are often hindered by rigid prerequisites,…