Related papers: ASSIST: Interactive Scene Nodes for Scalable and R…

We present a novel method for the interactive construction and rendering of extremely large molecular scenes, capable of representing multiple biological cells in atomistic detail. Our method is tailored for scenes, which are procedurally…

We present the first real-time method for inserting a rigid virtual object into a neural radiance field, which produces realistic lighting and shadowing effects, as well as allows interactive manipulation of the object. By exploiting the…

We present a method that achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views. Our algorithm represents a scene…

Sound plays a major role in human perception. Along with vision, it provides essential information for understanding our surroundings. Despite advances in neural implicit representations, learning acoustics that align with visual scenes…

Beyond novel view synthesis, Neural Radiance Fields are useful for applications that interact with the real world. In this paper, we use them as an implicit map of a given scene and propose a camera relocalization algorithm tailored for…

We present a method for composing photorealistic scenes from captured images of objects. Our work builds upon neural radiance fields (NeRFs), which implicitly model the volumetric density and directionally-emitted radiance of a scene. While…

The insertion of objects into a scene and relighting are commonly utilized applications in augmented reality (AR). Previous methods focused on inserting virtual objects using CAD models or real objects from single-view images, resulting in…

Radiance field methods, such as Neural Radiance Field or 3D Gaussian Splatting, have emerged as seminal 3D representations for synthesizing realistic novel views. For practical applications, there is ongoing research on flexible scene…

A compositional understanding of the world in terms of objects and their geometry in 3D space is considered a cornerstone of human cognition. Facilitating the learning of such a representation in neural networks holds promise for…

Implicit neural representations have shown powerful capacity in modeling real-world 3D scenes, offering superior performance in novel view synthesis. In this paper, we target a more challenging scenario, i.e., joint scene novel view…

We propose Text2Scene, a method to automatically create realistic textures for virtual scenes composed of multiple objects. Guided by a reference image and text descriptions, our pipeline adds detailed texture on labeled 3D geometries in…

In this paper, we propose a method to segment and recover a static, clean background and multiple 360$^\circ$ objects from observations of scenes at different timestamps. Recent works have used neural radiance fields to model 3D scenes and…

We tackle the task of scalable unsupervised object-centric representation learning on 3D scenes. Existing approaches to object-centric representation learning show limitations in generalizing to larger scenes as their learning processes…

Neural Radiance Fields achieve high-fidelity scene representation but suffer from costly training and rendering, while 3D Gaussian splatting offers real-time performance with strong empirical results. Recently, solutions that harness the…

Text-to-3D scene generation from natural language is highly desirable for digital content creation. However, existing methods are largely domain-restricted or reliant on predefined spatial relationships, limiting their capacity for…

Neural rendering with implicit neural networks has recently emerged as an attractive proposition for scene reconstruction, achieving excellent quality albeit at high computational cost. While the most recent generation of such methods has…

We present Virtual Elastic Objects (VEOs): virtual objects that not only look like their real-world counterparts but also behave like them, even when subject to novel interactions. Achieving this presents multiple challenges: not only do…

Rendering diffuse global illumination in real-time is often approximated by pre-computing and storing irradiance in a 3D grid of probes. As long as most of the scene remains static, probes approximate irradiance for all surfaces immersed in…

This paper addresses the challenge of reconstructing an animatable human model from a multi-view video. Some recent works have proposed to decompose a non-rigidly deforming scene into a canonical neural radiance field and a set of…

Deep generative models allow for photorealistic image synthesis at high resolutions. But for many applications, this is not enough: content creation also needs to be controllable. While several recent works investigate how to disentangle…