Related papers: SceneForge: Structured World Supervision from 3D I…

Scene understanding is a prerequisite to many high level tasks for any automated intelligent machine operating in real world environments. Recent attempts with supervised learning have shown promise in this direction but also highlighted…

We present a physics-based character control framework for synthesizing human-scene interactions. Recent advances adopt physics simulation to mitigate artifacts produced by data-driven kinematic approaches. However, existing physics-based…

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…

Despite encouraging progress in 3D scene understanding, it remains challenging to develop an effective Large Multi-modal Model (LMM) that is capable of understanding and reasoning in complex 3D environments. Most previous methods typically…

With the fast pace of 3D capture technology and resulting abundance of 3D data, effective 3D scene editing becomes essential for a variety of graphics applications. In this work we present ScanEdit, an instruction-driven method for…

Interactive image editing allows users to modify images through visual interaction operations such as drawing, clicking, and dragging. Existing methods construct such supervision signals from videos, as they capture how objects change with…

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…

Scenes in the real world are often composed of several static and dynamic objects. Capturing their 4-dimensional structures, composition and spatio-temporal configuration in-the-wild, though extremely interesting, is equally hard.…

We propose UniSeg3D, a unified 3D scene understanding framework that achieves panoptic, semantic, instance, interactive, referring, and open-vocabulary segmentation tasks within a single model. Most previous 3D segmentation approaches are…

We present a novel method for populating 3D indoor scenes with virtual humans that can navigate in the environment and interact with objects in a realistic manner. Existing approaches rely on training sequences that contain captured human…

Story Visualization aims to generate images aligned with story prompts, reflecting the coherence of storybooks through visual consistency among characters and scenes.Whereas current approaches exclusively concentrate on characters and…

Building an efficient and physically consistent world model from limited observations is a long standing challenge in vision and robotics. Many existing world modeling pipelines are based on implicit generative models, which are hard to…

We present Stable View Synthesis (SVS). Given a set of source images depicting a scene from freely distributed viewpoints, SVS synthesizes new views of the scene. The method operates on a geometric scaffold computed via…

Urban scene reconstruction requires modeling both static infrastructure and dynamic elements while supporting diverse environmental conditions. We present \textbf{StyledStreets}, a multi-style street simulator that achieves…

Semantic occupancy has emerged as a powerful representation in world models for its ability to capture rich spatial semantics. However, most existing occupancy world models rely on static and fixed embeddings or grids, which inherently…

We introduce SceneScript, a method that directly produces full scene models as a sequence of structured language commands using an autoregressive, token-based approach. Our proposed scene representation is inspired by recent successes in…

3D scene stylization aims at generating stylized images of the scene from arbitrary novel views following a given set of style examples, while ensuring consistency when rendered from different views. Directly applying methods for image or…

Reconstructing large-scale dynamic scenes from visual observations is a fundamental challenge in computer vision, with critical implications for robotics and autonomous systems. While recent differentiable rendering methods such as Neural…

Reconstructing models of the real world, including 3D geometry, appearance, and motion of real scenes, is essential for computer graphics and computer vision. It enables the synthesizing of photorealistic novel views, useful for the movie…

We present 3DScenePrompt, a framework that generates the next video chunk from arbitrary-length input while enabling precise camera control and preserving scene consistency. Unlike methods conditioned on a single image or a short clip, we…