Related papers: Driving View Synthesis on Free-form Trajectories w…
Driving video generation has achieved much progress in controllability, video resolution, and length, but fails to support fine-grained object-level controllability for diverse driving videos, while preserving the spatiotemporal…
Generating 4D scenes from a single-view video is inherently ill-posed: a single viewpoint lacks the information needed to recover a complete, dynamic scene with full coverage. Existing methods are typically limited to monocular videos,…
The ability to generate virtual environments is crucial for applications ranging from gaming to physical AI domains such as robotics, autonomous driving, and industrial AI. Current learning-based 3D reconstruction methods rely on the…
Controllable generation is considered a potentially vital approach to address the challenge of annotating 3D data, and the precision of such controllable generation becomes particularly imperative in the context of data production for…
Reconstructing 3D scenes and synthesizing novel views from sparse input views is a highly challenging task. Recent advances in video diffusion models have demonstrated strong temporal reasoning capabilities, making them a promising tool for…
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…
Despite recent successes in novel view synthesis using 3D Gaussian Splatting (3DGS), modeling scenes with sparse inputs remains a challenge. In this work, we address two critical yet overlooked issues in real-world sparse-input modeling:…
3D Gaussian Splatting (3DGS) is a leading 3D scene reconstruction method, obtaining high-quality reconstruction with real-time rendering runtime performance. The main idea behind 3DGS is to represent the scene as a collection of 3D…
Novel view synthesis of urban scenes is essential for autonomous driving-related applications.Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization. We…
The advancement of autonomous driving technologies necessitates increasingly sophisticated methods for understanding and predicting real-world scenarios. Vision language models (VLMs) are emerging as revolutionary tools with significant…
We tackle the challenge of generating dynamic 4D scenes from monocular, multi-object videos with heavy occlusions, and introduce GenMOJO, a novel approach that integrates rendering-based deformable 3D Gaussian optimization with generative…
Current methods for 3D scene reconstruction from sparse posed images employ intermediate 3D representations such as neural fields, voxel grids, or 3D Gaussians, to achieve multi-view consistent scene appearance and geometry. In this paper…
Safety-critical scenarios are rare yet pivotal for evaluating and enhancing the robustness of autonomous driving systems. While existing methods generate safety-critical driving trajectories, simulations, or single-view videos, they fall…
Generating high-quality novel views of a scene from a single image requires maintaining structural coherence across different views, referred to as view consistency. While diffusion models have driven advancements in novel view synthesis,…
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…
Synthesizing extrapolated views from recorded driving logs is critical for simulating driving scenes for autonomous driving vehicles, yet it remains a challenging task. Recent methods leverage generative priors as pseudo ground truth, but…
Driving simulators play a large role in developing and testing new intelligent vehicle systems. The visual fidelity of the simulation is critical for building vision-based algorithms and conducting human driver experiments. Low visual…
We introduce Diff4Splat, a feed-forward method that synthesizes controllable and explicit 4D scenes from a single image. Our approach unifies the generative priors of video diffusion models with geometry and motion constraints learned from…
Dynamic 3D scene representation and novel view synthesis are crucial for enabling immersive experiences required by AR/VR and metaverse applications. It is a challenging task due to the complexity of unconstrained real-world scenes and…
We aim to address sparse-view reconstruction of a 3D scene by leveraging priors from large-scale vision models. While recent advancements such as 3D Gaussian Splatting (3DGS) have demonstrated remarkable successes in 3D reconstruction,…