Search Results for author:
Found 9 papers, 4 papers with code
RelationField: Relate Anything in Radiance Fields
Neural radiance fields are an emerging 3D scene representation and recently even been extended to learn features for scene understanding by distilling open-vocabulary features from vision-language models.
Search3D: Hierarchical Open-Vocabulary 3D Segmentation
Existing methods for open-vocabulary 3D instance segmentation primarily focus on identifying object-level instances but struggle with finer-grained scene entities such as object parts, or regions described by generic attributes.
OpenSUN3D: 1st Workshop Challenge on Open-Vocabulary 3D Scene Understanding
This report provides an overview of the challenge hosted at the OpenSUN3D Workshop on Open-Vocabulary 3D Scene Understanding held in conjunction with ICCV 2023.
From 2D to 3D: Re-thinking Benchmarking of Monocular Depth Prediction
There have been numerous recently proposed methods for monocular depth prediction (MDP) coupled with the equally rapid evolution of benchmarking tools.
SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences
Scene graphs are a compact and explicit representation successfully used in a variety of 2D scene understanding tasks.
Ranked #1 on
3D Object Classification
on 3R-Scan
Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenes
In this paper, we adapt 3RScan - a recently introduced indoor RGB-D dataset designed for object instance re-localization - to create RIO10, a new long-term camera re-localization benchmark focused on indoor scenes.
Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions
In our work we focus on scene graphs, a data structure that organizes the entities of a scene in a graph, where objects are nodes and their relationships modeled as edges.
Ranked #3 on
3d scene graph generation
on 3DSSG
RIO: 3D Object Instance Re-Localization in Changing Indoor Environments
In this work, we introduce the task of 3D object instance re-localization (RIO): given one or multiple objects in an RGB-D scan, we want to estimate their corresponding 6DoF poses in another 3D scan of the same environment taken at a later point in time.
Fully-Convolutional Point Networks for Large-Scale Point Clouds
This work proposes a general-purpose, fully-convolutional network architecture for efficiently processing large-scale 3D data.
Ranked #29 on
Semantic Segmentation
on ScanNet
(test mIoU metric)
