相关论文: ASSIST: Interactive Scene Nodes for Scalable and R…

In the last years, the research interest in visual navigation towards objects in indoor environments has grown significantly. This growth can be attributed to the recent availability of large navigation datasets in photo-realistic simulated…

Instance shape reconstruction from a 3D scene involves recovering the full geometries of multiple objects at the semantic instance level. Many methods leverage data-driven learning due to the intricacies of scene complexity and significant…

We present Neural Reflectance Fields, a novel deep scene representation that encodes volume density, normal and reflectance properties at any 3D point in a scene using a fully-connected neural network. We combine this representation with a…

The work presented in this paper is related to the use of a haptic device in an environment of robotic simulation. Such device introduces a new approach to feel and to understand the boundaries of the workspace of mechanisms as well as its…

We present DiffuScene for indoor 3D scene synthesis based on a novel scene configuration denoising diffusion model. It generates 3D instance properties stored in an unordered object set and retrieves the most similar geometry for each…

We introduce Neural Point Light Fields that represent scenes implicitly with a light field living on a sparse point cloud. Combining differentiable volume rendering with learned implicit density representations has made it possible to…

This project presents an exploration into 3D scene reconstruction of synthetic and real-world scenes using Neural Radiance Field (NeRF) approaches. We primarily take advantage of the reduction in training and rendering time of neural…

To help agents reason about scenes in terms of their building blocks, we wish to extract the compositional structure of any given scene (in particular, the configuration and characteristics of objects comprising the scene). This problem is…

This paper presents BioNeRF, a biologically plausible architecture that models scenes in a 3D representation and synthesizes new views through radiance fields. Since NeRF relies on the network weights to store the scene's 3-dimensional…

Recent conditional image synthesis approaches provide high-quality synthesized images. However, it is still challenging to accurately adjust image contents such as the positions and orientations of objects, and synthesized images often have…

In depth-sensing applications ranging from home robotics to AR/VR, it will be common to acquire 3D scans of interior spaces repeatedly at sparse time intervals (e.g., as part of regular daily use). We propose an algorithm that analyzes…

Neural Radiance Field (NeRF) is a popular method in representing 3D scenes by optimising a continuous volumetric scene function. Its large success which lies in applying volumetric rendering (VR) is also its Achilles' heel in producing…

We tackle the challenge of learning a distribution over complex, realistic, indoor scenes. In this paper, we introduce Generative Scene Networks (GSN), which learns to decompose scenes into a collection of many local radiance fields that…

TL;DR Perform 3D object editing selectively by disentangling it from the background scene. Instruct-NeRF2NeRF (in2n) is a promising method that enables editing of 3D scenes composed of Neural Radiance Field (NeRF) using text prompts.…

We propose a learned image-guided rendering technique that combines the benefits of image-based rendering and GAN-based image synthesis. The goal of our method is to generate photo-realistic re-renderings of reconstructed objects for…

Neural Radiance Field (NeRF) has been widely recognized for its excellence in novel view synthesis and 3D scene reconstruction. However, their effectiveness is inherently tied to the assumption of static scenes, rendering them susceptible…

Analyzing a visual scene by inferring the configuration of a generative model is widely considered the most flexible and generalizable approach to scene understanding. Yet, one major problem is the computational challenge of the inference…

We present a fast and simple technique to convert images into a radiance surface-based scene representation. Building on existing radiance volume reconstruction algorithms, we introduce a subtle yet impactful modification of the loss…

We present a novel method to acquire object representations from online image collections, capturing high-quality geometry and material properties of arbitrary objects from photographs with varying cameras, illumination, and backgrounds.…

From video, we reconstruct a neural volume that captures time-varying color, density, scene flow, semantics, and attention information. The semantics and attention let us identify salient foreground objects separately from the background…