Related papers: HoloScene: Simulation-Ready Interactive 3D Worlds …
Humans can naturally identify and mentally complete occluded objects in cluttered environments. However, imparting similar cognitive ability to robotics remains challenging even with advanced reconstruction techniques, which models scenes…
Most indoor 3D scene reconstruction methods focus on recovering 3D geometry and scene layout. In this work, we go beyond this to propose PhotoScene, a framework that takes input image(s) of a scene along with approximately aligned CAD…
Scene-level 3D generation represents a critical frontier in multimedia and computer graphics, yet existing approaches either suffer from limited object categories or lack editing flexibility for interactive applications. In this paper, we…
In the field of 3D content generation, single image scene reconstruction methods still struggle to simultaneously ensure the quality of individual assets and the coherence of the overall scene in complex environments, while texture editing…
We propose a new 3D holistic++ scene understanding problem, which jointly tackles two tasks from a single-view image: (i) holistic scene parsing and reconstruction---3D estimations of object bounding boxes, camera pose, and room layout, and…
Recent advances in 3D scene reconstruction and 4D human animation have broadened adoption, but integrating the two remains difficult. Key challenges include placing humans at plausible locations and scales without interpenetration, aligning…
3D scene reconstruction from 2D images is one of the most important tasks in computer graphics. Unfortunately, existing datasets and benchmarks concentrate on idealized synthetic or meticulously captured realistic data. Such benchmarks fail…
MonoScene proposes a 3D Semantic Scene Completion (SSC) framework, where the dense geometry and semantics of a scene are inferred from a single monocular RGB image. Different from the SSC literature, relying on 2.5 or 3D input, we solve the…
This paper scales object-level reconstruction to complex scenes, advancing interactive scene reconstruction. We introduce two datasets, OmniSim and InterReal, featuring 28 scenes with multiple interactive objects. To tackle the challenge of…
Generating high-quality, textured 3D scenes from a single image remains a fundamental challenge in vision and graphics. Recent image-to-3D generators recover reasonable geometry from single views, but their object-centric training limits…
Reconstructing complete and interactive 3D scenes remains a fundamental challenge in computer vision and robotics, particularly due to persistent object occlusions and limited sensor coverage. Multiview observations from a single scene scan…
Generating 3D scenes from natural language holds great promise for applications in gaming, film, and design. However, existing methods struggle with automation, 3D consistency, and fine-grained control. We present DreamScene, an end-to-end…
This work addresses the problem of recovering complete, simulatable object geometry from reconstructed real-world scenes, enabling physics-based interaction with objects embedded in the scene. While modern multi-view reconstruction methods…
State-of-the-art text-to-video models excel at generating isolated clips but fall short of creating the coherent, multi-shot narratives, which are the essence of storytelling. We bridge this "narrative gap" with HoloCine, a model that…
3D scene generation is in high demand across various domains, including virtual reality, gaming, and the film industry. Owing to the powerful generative capabilities of text-to-image diffusion models that provide reliable priors, the…
Recent advances in 3D scene generation produce visually appealing output, but current representations hinder artists' workflows that require modifiable 3D textured mesh scenes for visual effects and game development. Despite significant…
Holistic 3D human-scene reconstruction is a crucial and emerging research area in robot perception. A key challenge in holistic 3D human-scene reconstruction is to generate a physically plausible 3D scene from a single monocular RGB image.…
Holographic display can show pictures in the way that looks like the same with the real world, and is thought as the ultimate display technology. But due to the complexity of the traditional holographic technique, it can hardly be applied…
Generating explorable 3D scenes from a single image is a highly challenging problem in 3D vision. Existing methods struggle to support free exploration, often producing severe geometric distortions and noisy artifacts when the viewpoint…
Reconstructing metrically accurate humans and their surrounding scenes from a single image is crucial for virtual reality, robotics, and comprehensive 3D scene understanding. However, existing methods struggle with depth ambiguity,…