Related papers: Scene Representation Networks: Continuous 3D-Struc…

We study the problem of inferring an object-centric scene representation from a single image, aiming to derive a representation that explains the image formation process, captures the scene's 3D nature, and is learned without supervision.…

We present a novel approach that converts partial and noisy RGB-D scans into high-quality 3D scene reconstructions by inferring unobserved scene geometry. Our approach is fully self-supervised and can hence be trained solely on real-world,…

Making generative models 3D-aware bridges the 2D image space and the 3D physical world yet remains challenging. Recent attempts equip a Generative Adversarial Network (GAN) with a Neural Radiance Field (NeRF), which maps 3D coordinates to…

Over the past few years, a significant progress has been made in deep convolutional neural networks (CNNs)-based image recognition. This is mainly due to the strong ability of such networks in mining discriminative object pose and parts…

Land cover maps generated from semantic segmentation of high-resolution remotely sensed images have drawn mucon in the photogrammetry and remote sensing research community. Currently, massive fine-resolution remotely sensed (FRRS) images…

Traditional Radiance Field (RF) representations capture details of a specific scene and must be trained afresh on each scene. Semantic feature fields have been added to RFs to facilitate several segmentation tasks. Generalised RF…

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…

Complex visual scenes that are composed of multiple objects, each with attributes, such as object name, location, pose, color, etc., are challenging to describe in order to train neural networks. Usually,deep learning networks are trained…

Scene labeling is a challenging classification problem where each input image requires a pixel-level prediction map. Recently, deep-learning-based methods have shown their effectiveness on solving this problem. However, we argue that the…

3D surface reconstruction from images is essential for numerous applications. Recently, Neural Radiance Fields (NeRFs) have emerged as a promising framework for 3D modeling. However, NeRFs require accurate camera poses as input, and…

We address efficient and structure-aware 3D scene representation from images. Nerflets are our key contribution -- a set of local neural radiance fields that together represent a scene. Each nerflet maintains its own spatial position,…

Recent history has seen a tremendous growth of work exploring implicit representations of geometry and radiance, popularized through Neural Radiance Fields (NeRF). Such works are fundamentally based on a (implicit) volumetric representation…

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…

Neural 3D scene reconstruction methods have achieved impressive performance when reconstructing complex geometry and low-textured regions in indoor scenes. However, these methods heavily rely on 3D data which is costly and time-consuming to…

In this study, we address the challenge of 3D scene structure recovery from monocular depth estimation. While traditional depth estimation methods leverage labeled datasets to directly predict absolute depth, recent advancements advocate…

Representing and rendering dynamic scenes from 2D images is a fundamental yet challenging problem in computer vision and graphics. This survey provides a comprehensive review of the evolution and advancements in dynamic scene representation…

Learning generalizable robotic manipulation policies remains a key challenge due to the scarcity of diverse real-world training data. While recent approaches have attempted to mitigate this through self-supervised representation learning,…

The task of generating natural images from 3D scenes has been a long standing goal in computer graphics. On the other hand, recent developments in deep neural networks allow for trainable models that can produce natural-looking images with…

A key goal of computer vision is to recover the underlying 3D structure from 2D observations of the world. In this paper we learn strong deep generative models of 3D structures, and recover these structures from 3D and 2D images via…

Implicit neural rendering techniques have shown promising results for novel view synthesis. However, existing methods usually encode the entire scene as a whole, which is generally not aware of the object identity and limits the ability to…