Nesf: Neural semantic fields for generalizable semantic segmentation of 3d scenes
We present NeSF, a method for producing 3D semantic fields from posed RGB images
alone. In place of classical 3D representations, our method builds on recent work in implicit …
alone. In place of classical 3D representations, our method builds on recent work in implicit …
Learning 3d semantic segmentation with only 2d image supervision
With the recent growth of urban mapping and autonomous driving efforts, there has been an
explosion of raw 3D data collected from terrestrial platforms with lidar scanners and color …
explosion of raw 3D data collected from terrestrial platforms with lidar scanners and color …
Laterf: Label and text driven object radiance fields
Obtaining 3D object representations is important for creating photo-realistic simulations and
for collecting AR and VR assets. Neural fields have shown their effectiveness in learning a …
for collecting AR and VR assets. Neural fields have shown their effectiveness in learning a …
Contrastive lift: 3d object instance segmentation by slow-fast contrastive fusion
Instance segmentation in 3D is a challenging task due to the lack of large-scale annotated
datasets. In this paper, we show that this task can be addressed effectively by leveraging …
datasets. In this paper, we show that this task can be addressed effectively by leveraging …
S4C: Self-supervised semantic scene completion with neural fields
3D semantic scene understanding is a fundamental challenge in computer vision. It enables
mobile agents to autonomously plan and navigate arbitrary environments. SSC formalizes …
mobile agents to autonomously plan and navigate arbitrary environments. SSC formalizes …
WHU-Urban3D: An urban scene LiDAR point cloud dataset for semantic instance segmentation
With the rapid advancement of 3D sensors, there is an increasing demand for 3D scene
understanding and an increasing number of 3D deep learning algorithms have been …
understanding and an increasing number of 3D deep learning algorithms have been …
[HTML][HTML] Screening the stones of Venice: Mapping social perceptions of cultural significance through graph-based semi-supervised classification
Mapping cultural significance of heritage properties in urban environment from the
perspective of the public has become an increasingly relevant process, as highlighted by the …
perspective of the public has become an increasingly relevant process, as highlighted by the …
Real-time multi-modal semantic fusion on unmanned aerial vehicles with label propagation for cross-domain adaptation
Unmanned aerial vehicles (UAVs) equipped with multiple complementary sensors have
tremendous potential for fast autonomous or remote-controlled semantic scene analysis, eg …
tremendous potential for fast autonomous or remote-controlled semantic scene analysis, eg …
Nesf: Neural semantic fields for generalizable semantic segmentation of 3d scenes
We present NeSF, a method for producing 3D semantic fields from posed RGB images
alone. In place of classical 3D representations, our method builds on recent work in neural …
alone. In place of classical 3D representations, our method builds on recent work in neural …
Hd-ccsom: Hierarchical and dense collaborative continuous semantic occupancy mapping through label diffusion
The collaborative operation of multiple robots can make up for the shortcomings of a single
robot, such as limited field of perception or sensor failure. multirobots collaborative semantic …
robot, such as limited field of perception or sensor failure. multirobots collaborative semantic …