RGB-D salient object detection: A survey

T Zhou, DP Fan, MM Cheng, J Shen, L Shao - Computational Visual Media, 2021 - Springer
Salient object detection, which simulates human visual perception in locating the most
significant object (s) in a scene, has been widely applied to various computer vision tasks …

Salient object detection: A survey

A Borji, MM Cheng, Q Hou, H Jiang, J Li - Computational visual media, 2019 - Springer
Detecting and segmenting salient objects from natural scenes, often referred to as salient
object detection, has attracted great interest in computer vision. While many models have …

imap: Implicit map** and positioning in real-time

E Sucar, S Liu, J Ortiz… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
We show for the first time that a multilayer perceptron (MLP) can serve as the only scene
representation in a real-time SLAM system for a handheld RGB-D camera. Our network is …

Dense depth priors for neural radiance fields from sparse input views

B Roessle, JT Barron, B Mildenhall… - Proceedings of the …, 2022 - openaccess.thecvf.com
Neural radiance fields (NeRF) encode a scene into a neural representation that enables
photo-realistic rendering of novel views. However, a successful reconstruction from RGB …

3dshape2vecset: A 3d shape representation for neural fields and generative diffusion models

B Zhang, J Tang, M Niessner, P Wonka - ACM Transactions on Graphics …, 2023 - dl.acm.org
We introduce 3DShape2VecSet, a novel shape representation for neural fields designed for
generative diffusion models. Our shape representation can encode 3D shapes given as …

Monoscene: Monocular 3d semantic scene completion

AQ Cao, R De Charette - … of the IEEE/CVF Conference on …, 2022 - openaccess.thecvf.com
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 …

Neuralrecon: Real-time coherent 3d reconstruction from monocular video

J Sun, Y **e, L Chen, X Zhou… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
We present a novel framework named NeuralRecon for real-time 3D scene reconstruction
from a monocular video. Unlike previous methods that estimate single-view depth maps …

Neural rgb-d surface reconstruction

D Azinović, R Martin-Brualla… - Proceedings of the …, 2022 - openaccess.thecvf.com
Obtaining high-quality 3D reconstructions of room-scale scenes is of paramount importance
for upcoming applications in AR or VR. These range from mixed reality applications for …

Meshgpt: Generating triangle meshes with decoder-only transformers

Y Siddiqui, A Alliegro, A Artemov… - Proceedings of the …, 2024 - openaccess.thecvf.com
We introduce MeshGPT a new approach for generating triangle meshes that reflects the
compactness typical of artist-created meshes in contrast to dense triangle meshes extracted …