Related papers: UniScene: Unified Occupancy-centric Driving Scene …

3D scene generation seeks to synthesize spatially structured, semantically meaningful, and photorealistic environments for applications such as immersive media, robotics, autonomous driving, and embodied AI. Early methods based on…

We introduce SceneTransporter, an end-to-end framework for structured 3D scene generation from a single image. While existing methods generate part-level 3D objects, they often fail to organize these parts into distinct instances in…

Scene generation has extensive industrial applications, demanding both high realism and precise control over geometry and appearance. Language-driven retrieval methods compose plausible scenes from a large object database, but overlook…

Occupancy prediction infers fine-grained 3D geometry and semantics from camera images of the surrounding environment, making it a critical perception task for autonomous driving. Existing methods either adopt dense grids as scene…

Large-scale diffusion generative models are greatly simplifying image, video and 3D asset creation from user-provided text prompts and images. However, the challenging problem of text-to-4D dynamic 3D scene generation with diffusion…

Motion planning is a crucial component in autonomous driving. State-of-the-art motion planners are trained on meticulously curated datasets, which are not only expensive to annotate but also insufficient in capturing rarely seen critical…

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,…

Generating 3D scenes from human motion sequences supports numerous applications, including virtual reality and architectural design. However, previous auto-regression-based human-aware 3D scene generation methods have struggled to…

In this paper, we draw inspiration from Alberto Elfes' pioneering work in 1989, where he introduced the concept of the occupancy grid as World Models for robots. We imbue the robot with a spatial-temporal world model, termed UniWorld, to…

Efficient data utilization is crucial for advancing 3D scene understanding in autonomous driving, where reliance on heavily human-annotated LiDAR point clouds challenges fully supervised methods. Addressing this, our study extends into…

In recent years, 3D generation has made great strides in both academia and industry. However, generating 3D scenes from a single RGB image remains a significant challenge, as current approaches often struggle to ensure both object…

Creating high-fidelity 3D models of indoor environments is essential for applications in design, virtual reality, and robotics. However, manual 3D modeling remains time-consuming and labor-intensive. While recent advances in generative AI…

Autonomous driving system development is critically dependent on the ability to replay complex and diverse traffic scenarios in simulation. In such scenarios, the ability to accurately simulate the vehicle sensors such as cameras, lidar or…

Recovering 3D scenes from sparse views is a challenging task due to its inherent ill-posed problem. Conventional methods have developed specialized solutions (e.g., geometry regularization or feed-forward deterministic model) to mitigate…

Semantic Scene Completion (SSC) from monocular RGB images is a fundamental yet challenging task due to the inherent ambiguity of inferring occluded 3D geometry from a single view. While feed-forward methods have made progress, they often…

Data-driven learning has advanced autonomous driving, yet task-specific models struggle with out-of-distribution scenarios due to their narrow optimization objectives and reliance on costly annotated data. We present DriveX, a…

Realistic and diverse multi-agent driving scenes are crucial for evaluating autonomous vehicles, but safety-critical events which are essential for this task are rare and underrepresented in driving datasets. Data-driven scene generation…

4D driving simulation is essential for developing realistic autonomous driving simulators. Despite advancements in existing methods for generating driving scenes, significant challenges remain in view transformation and spatial-temporal…

Self-driving vehicles (SDVs) require accurate calibration of LiDARs and cameras to fuse sensor data accurately for autonomy. Traditional calibration methods typically leverage fiducials captured in a controlled and structured scene and…

Generating controllable and physically plausible indoor scenes is a pivotal prerequisite for constructing high-fidelity simulation environments for embodied AI. However, existing deeplearning-based methods usually treat all objects as…