Egogaussian: Dynamic scene understanding from egocentric video with 3d gaussian splatting
D Zhang, G Li, J Li, M Bressieux, O Hilliges… - ar**
The semantically interactive radiance field has always been an appealing task for its
potential to facilitate user-friendly and automated real-world 3D scene understanding …
potential to facilitate user-friendly and automated real-world 3D scene understanding …
3D-Aware Instance Segmentation and Tracking in Egocentric Videos
Egocentric videos present unique challenges for 3D scene understanding due to rapid
camera motion, frequent object occlusions, and limited object visibility. This paper …
camera motion, frequent object occlusions, and limited object visibility. This paper …
SLGaussian: Fast Language Gaussian Splatting in Sparse Views
3D semantic field learning is crucial for applications like autonomous navigation, AR/VR,
and robotics, where accurate comprehension of 3D scenes from limited viewpoints is …
and robotics, where accurate comprehension of 3D scenes from limited viewpoints is …
Estimating Body and Hand Motion in an Ego-sensed World
We present EgoAllo, a system for human motion estimation from a head-mounted device.
Using only egocentric SLAM poses and images, EgoAllo guides sampling from a conditional …
Using only egocentric SLAM poses and images, EgoAllo guides sampling from a conditional …
SAMa: Material-aware 3D selection and segmentation
Decomposing 3D assets into material parts is a common task for artists and creators, yet
remains a highly manual process. In this work, we introduce Select Any Material (SAMa), a …
remains a highly manual process. In this work, we introduce Select Any Material (SAMa), a …
T-3DGS: Removing Transient Objects for 3D Scene Reconstruction
V Pryadilshchikov, A Markin, A Komarichev… - arxiv preprint arxiv …, 2024 - arxiv.org
We propose a novel framework to remove transient objects from input videos for 3D scene
reconstruction using Gaussian Splatting. Our framework consists of the following steps. In …
reconstruction using Gaussian Splatting. Our framework consists of the following steps. In …
3D Gaussian Splatting for Human-Robot Interaction
S Bowser, SM Lukin - The 1st InterAI Workshop: Interactive AI for …, 2024 - openreview.net
In order to assist a humans' ability to make decisions in uncertain and high-stakes scenarios,
eg, disaster relief, we aim to provide an interactive and “smart” visual model of an …
eg, disaster relief, we aim to provide an interactive and “smart” visual model of an …
EgoMe: Follow Me via Egocentric View in Real World
When interacting with the real world, human often take the egocentric (first-person) view as a
benchmark, naturally transferring behaviors observed from a exocentric (third-person) view …
benchmark, naturally transferring behaviors observed from a exocentric (third-person) view …
3D Gaussian Splatting in Robotics: A Survey
Dense 3D representations of the environment have been a long-term goal in the robotics
field. While previous Neural Radiance Fields (NeRF) representation have been prevalent for …
field. While previous Neural Radiance Fields (NeRF) representation have been prevalent for …