3D Representations are computational models that encode the geometry, structure, and appearance of objects or scenes in three-dimensional space. They include formats such as point clouds, meshes, voxel grids, and implicit neural representations that capture spatial relationships and surface properties. These representations are used in computer vision, graphics, and robotics for tasks such as reconstruction, rendering, simulation, and spatial reasoning from multi-view or sensor data.

Posts

HorizonForge: Driving Scene Editing with Any Trajectories and Any Vehicles

/in /by

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 that reconstructs scenes as editable Gaussian Splats and Meshes, enabling fine-grained 3D manipulation and language-driven vehicle insertion. Edits are rendered through a noise-aware video diffusion process that enforces spatial and temporal consistency, producing diverse scene variations in a single feed-forward pass without per-trajectory optimization. To standardize evaluation, we further propose HorizonSuite, a comprehensive benchmark spanning ego- and agent-level editing tasks such as trajectory modifications and object manipulation. Extensive experiments show that Gaussian-Mesh representation delivers substantially higher fidelity than alternative 3D representations, and that temporal priors from video diffusion are essential for coherent synthesis. Combining these findings, HorizonForge establishes a simple yet powerful paradigm for photorealistic, controllable driving simulation, achieving an 83.4% user-preference gain and a 25.19% FID improvement over the second-best state-of-the-art method. Project page: https://horizonforge.github.io/.

Read more