相关论文: HorizonForge: Driving Scene Editing with Any Traje…
This paper aims to tackle the problem of modeling dynamic urban streets for autonomous driving scenes. Recent methods extend NeRF by incorporating tracked vehicle poses to animate vehicles, enabling photo-realistic view synthesis of dynamic…
Recent advances in text-to-image (T2I) diffusion models have significantly improved semantic image editing, yet most methods fall short in performing 3D-aware object manipulation. In this work, we present FFSE, a 3D-aware autoregressive…
Synthesizing consistent and photorealistic 3D scenes is an open problem in computer vision. Video diffusion models generate impressive videos but cannot directly synthesize 3D representations, i.e., lack 3D consistency in the generated…
This paper proposes ProEdit - a simple yet effective framework for high-quality 3D scene editing guided by diffusion distillation in a novel progressive manner. Inspired by the crucial observation that multi-view inconsistency in scene…
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…
High-fidelity reconstruction of driving scenes is crucial for autonomous driving. While recent feedforward 3D Gaussian Splatting (3DGS) methods enable fast reconstruction, their per-pixel Gaussian prediction paradigm often suffers from…
Generating 3D scenes from natural language holds great promise for applications in gaming, film, and design. However, existing methods struggle with automation, 3D consistency, and fine-grained control. We present DreamScene, an end-to-end…
Video diffusion models have rich world priors, but their use in spatial tasks is limited by poor control, spatial-temporal inconsistent results, and entangled scene-camera dynamics. Current approaches, such as per-task fine-tuning or…
Scene view synthesis, which generates novel views from limited perspectives, is increasingly vital for applications like virtual reality, augmented reality, and robotics. Unlike object-based tasks, such as generating 360{\deg} views of a…
Editable high-fidelity 4D scenes are crucial for autonomous driving, as they can be applied to end-to-end training and closed-loop simulation. However, existing reconstruction methods are primarily limited to replicating observed scenes and…
Controllable scene synthesis aims to create interactive environments for various industrial use cases. Scene graphs provide a highly suitable interface to facilitate these applications by abstracting the scene context in a compact manner.…
Vision Language Models (VLMs) are increasingly deployed in autonomous vehicles and mobile systems, making it crucial to evaluate their ability to support safer decision-making in complex environments. However, existing benchmarks…
Text-conditioned image editing has greatly benefitted from the advancements in Image Diffusion Models. However, extending these techniques to facial video editing introduces challenges in preserving facial identity throughout the source…
We introduce PortraitGen, a powerful portrait video editing method that achieves consistent and expressive stylization with multimodal prompts. Traditional portrait video editing methods often struggle with 3D and temporal consistency, and…
Driving simulation plays a crucial role in developing reliable driving agents by providing controlled, evaluative environments. To enable meaningful assessments, a high-quality driving simulator must satisfy several key requirements:…
Recent advancements in 4D scene reconstruction, particularly those leveraging diffusion priors, have shown promise for novel view synthesis in autonomous driving. However, these methods often process frames independently or in a…
Self-supervised learning has made substantial strides in image processing, while visual pre-training for autonomous driving is still in its infancy. Existing methods often focus on learning geometric scene information while neglecting…
With the increasing popularity of autonomous driving based on the powerful and unified bird's-eye-view (BEV) representation, a demand for high-quality and large-scale multi-view video data with accurate annotation is urgently required.…
We introduce Drag4D, an interactive framework that integrates object motion control within text-driven 3D scene generation. This framework enables users to define 3D trajectories for the 3D objects generated from a single image, seamlessly…
Urban scene reconstruction from real-world observations has emerged as a powerful tool for self-driving development and testing. While current neural rendering approaches achieve high-fidelity rendering along the recorded trajectories,…