Blocks2World: Controlling Realistic Scenes with Editable Primitives
We present Blocks2World, a novel method for 3D scene rendering and editing that leverages a two-step process: convex decomposition of images and conditioned synthesis. Our technique begins by extracting 3D parallelepipeds from various objects in a given scene using convex decomposition, thus obtaining a primitive representation of the scene. These primitives are then utilized to generate paired data through simple ray-traced depth maps. The next stage involves training a conditioned model that learns to generate images from the 2D-rendered convex primitives. This step establishes a direct mapping between the 3D model and its 2D representation, effectively learning the transition from a 3D model to an image. Once the model is fully trained, it offers remarkable control over the synthesis of novel and edited scenes. This is achieved by manipulating the primitives at test time, including translating or adding them, thereby enabling a highly customizable scene rendering process. Our method provides a fresh perspective on 3D scene rendering and editing, offering control and flexibility. It opens up new avenues for research and applications in the field, including authoring and data augmentation.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationSimilar Papers 제목 키워드 기반
RealityBridge: Bridging Editable 3D Gaussian Splatting Driving Simulations and Real-World Videos
Long-tail hazardous scenarios are essential for safety-oriented autonomous driving, yet they are difficult to collect at scale. Editable 3D Gaussian Splatting (3DGS) simulation offers a scalable alternative through real-…
Autonomous DrivingVideo GenerationMorphoSim: An Interactive, Controllable, and Editable Language-guided 4D World Simulator
World models that support controllable and editable spatiotemporal environments are valuable for robotics, enabling scalable training data, repro ducible evaluation, and flexible task design. While recent text-to-video m…
EditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Points
Neural radiance fields (NeRF) achieve highly photo-realistic novel-view synthesis, but it's a challenging problem to edit the scenes modeled by NeRF-based methods, especially for dynamic scenes. We propose editable neura…
NeRFNovel View SynthesisEditable Free-viewpoint Video Using a Layered Neural Representation
Generating free-viewpoint videos is critical for immersive VR/AR experience but recent neural advances still lack the editing ability to manipulate the visual perception for large dynamic scenes. To fill this gap, in thi…
DisentanglementNeRFScene ParsingVideo GenerationWorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes
Recent 3D world modeling systems based on generative scene synthesis, such as Marble, can create coherent and explorable 3D environments, yet their outputs are typically static monolithic assets with limited editability …