Related papers: HiScene: Creating Hierarchical 3D Scenes with Isom…
3D scanning is a complex multistage process that generates a point cloud of an object typically containing damaged parts due to occlusions, reflections, shadows, scanner motion, specific properties of the object surface, imperfect…
Holistic 3D scene understanding entails estimation of both layout configuration and object geometry in a 3D environment. Recent works have shown advances in 3D scene estimation from various input modalities (e.g., images, 3D scans), by…
Controllable 3D indoor scene synthesis stands at the forefront of technological progress, offering various applications like gaming, film, and augmented/virtual reality. The capability to stylize and de-couple objects within these scenarios…
Open-vocabulary image segmentation aims to partition an image into semantic regions according to arbitrary text descriptions. However, complex visual scenes can be naturally decomposed into simpler parts and abstracted at multiple levels of…
Careful robot manipulation in every-day cluttered environments requires an accurate understanding of the 3D scene, in order to grasp and place objects stably and reliably and to avoid colliding with other objects. In general, we must…
We introduce ReStyle3D, a novel framework for scene-level appearance transfer from a single style image to a real-world scene represented by multiple views. The method combines explicit semantic correspondences with multi-view consistency…
We identify occlusion reasoning as a fundamental yet overlooked aspect for 3D layout-conditioned generation. It is essential for synthesizing partially occluded objects with depth-consistent geometry and scale. While existing methods can…
We present an open-source, real-time implementation of SemanticPaint, a system for geometric reconstruction, object-class segmentation and learning of 3D scenes. Using our system, a user can walk into a room wearing a depth camera and a…
We tackle the problem of text-driven 3D generation from a geometry alignment perspective. Given a set of text prompts, we aim to generate a collection of objects with semantically corresponding parts aligned across them. Recent methods…
Panoramic image enables deeper understanding and more holistic perception of $360^\circ$ surrounding environment, which can naturally encode enriched scene context information compared to standard perspective image. Previous work has made…
We present BetterScene, an approach to enhance novel view synthesis (NVS) quality for diverse real-world scenes using extremely sparse, unconstrained photos. BetterScene leverages the production-ready Stable Video Diffusion (SVD) model…
Generating coherent and useful image/video scenes from a free-form textual description is technically a very difficult problem to handle. Textual description of the same scene can vary greatly from person to person, or sometimes even for…
The completion, extension, and generation of 3D semantic scenes are an interrelated set of capabilities that are useful for robotic navigation and exploration. Existing approaches seek to decouple these problems and solve them one-off.…
Learning object-centric representations from unsupervised videos is challenging. Unlike most previous approaches that focus on decomposing 2D images, we present a 3D generative model named DynaVol-S for dynamic scenes that enables…
Recent advancements in video generation have primarily leveraged diffusion models for short-duration content. However, these approaches often fall short in modeling complex narratives and maintaining character consistency over extended…
World building with 3D scene representations is increasingly important for content creation, simulation, and interactive experiences, yet real workflows are inherently iterative: creators must repeatedly extend an existing scene under user…
We introduce Text2Immersion, an elegant method for producing high-quality 3D immersive scenes from text prompts. Our proposed pipeline initiates by progressively generating a Gaussian cloud using pre-trained 2D diffusion and depth…
Recent advances in diffusion-based video generation have opened new possibilities for controllable video editing, yet realistic video object insertion (VOI) remains challenging due to limited 4D scene understanding and inadequate handling…
Existing scene understanding systems mainly focus on recognizing the visible parts of a scene, ignoring the intact appearance of physical objects in the real-world. Concurrently, image completion has aimed to create plausible appearance for…
A natural approach to generative modeling of videos is to represent them as a composition of moving objects. Recent works model a set of 2D sprites over a slowly-varying background, but without considering the underlying 3D scene that gives…