Related papers: SceneCrafter: Controllable Multi-View Driving Scen…

Novel view synthesis (NVS) boosts immersive experiences in computer vision and graphics. Existing techniques, though progressed, rely on dense multi-view observations, restricting their application. This work takes on the challenge of…

Synthesizing photo-realistic visual observations from an ego vehicle's driving trajectory is a critical step towards scalable training of self-driving models. Reconstruction-based methods create 3D scenes from driving logs and synthesize…

Vision-centric autonomous driving systems require diverse data for robust training and evaluation, which can be augmented by manipulating object positions and appearances within existing scene captures. While recent advancements in…

We present a method for text-driven perpetual view generation -- synthesizing long-term videos of various scenes solely, given an input text prompt describing the scene and camera poses. We introduce a novel framework that generates such…

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…

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.…

Creating CAD digital twins from the physical world is crucial for manufacturing, design, and simulation. However, current methods typically rely on costly 3D scanning with labor-intensive post-processing. To provide a user-friendly design…

Despite recent advances in text-conditioned 3D indoor scene generation, there remain gaps in the evaluation of these methods. Existing metrics often measure realism by comparing generated scenes to a set of ground-truth scenes, but they…

We present Edit3r, a feed-forward framework that reconstructs and edits 3D scenes in a single pass from unposed, view-inconsistent, instruction-edited images. Unlike prior methods requiring per-scene optimization, Edit3r directly predicts…

Using synthesized images to boost the performance of perception models is a long-standing research challenge in computer vision. It becomes more eminent in visual-centric autonomous driving systems with multi-view cameras as some long-tail…

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…

The creation of 3D scenes has traditionally been both labor-intensive and costly, requiring designers to meticulously configure 3D assets and environments. Recent advancements in generative AI, including text-to-3D and image-to-3D methods,…

We present SceneFactor, a diffusion-based approach for large-scale 3D scene generation that enables controllable generation and effortless editing. SceneFactor enables text-guided 3D scene synthesis through our factored diffusion…

We present BlenderFusion, a generative visual compositing framework that synthesizes new scenes by recomposing objects, camera, and background. It follows a layering-editing-compositing pipeline: (i) segmenting and converting visual inputs…

A powerful simulator highly decreases the need for real-world tests when training and evaluating autonomous vehicles. Data-driven simulators flourished with the recent advancement of conditional Generative Adversarial Networks (cGANs),…

Recent advances in text-to-3D scene generation have demonstrated significant potential to transform content creation across multiple industries. Although the research community has made impressive progress in addressing the challenges of…

Automatically generating a complete 3D scene from a text description, a reference image, or both has significant applications in fields like virtual reality and gaming. However, current methods often generate low-quality textures and…

Controllable driving scene generation is critical for realistic and scalable autonomous driving simulation, yet existing approaches struggle to jointly achieve photorealism and precise control. We introduce HorizonForge, a unified framework…

The essence of a video lies in its dynamic motions, including character actions, object movements, and camera movements. While text-to-video generative diffusion models have recently advanced in creating diverse contents, controlling…

Autonomous driving systems rely heavily on multimodal perception data to understand complex environments. However, the long-tailed distribution of real-world data hinders generalization, especially for rare but safety-critical vehicle…