|
youtu.be
|
Challenges and Opportunities of Mobile Manipulation
|
|
youtu.be
|
Towards a Foundation Model for 4D Lidar
|
|
youtu.be
|
3D Scene Intelligence
|
|
youtu.be
|
Hierarchical Methods for Task-driven and Dynamic Scene Understanding
|
|
youtu.be
|
Efficient Repurposing of T2I Representations Across Modalities
|
|
youtu.be
|
Functionality Understanding and Segmentation in 3D Scenes
|
|
research.nvidia.com
|
<p class="title is-4">Laura Leal-Taixé</p>
<p class="subtitle is-6">Senior Research Manager at NVIDIA</p>
|
|
schmluk.github.io
|
<div class="column">
<p class="title is-4">Lukas Schmid</p>
<p class="subtitle is-6">Research Scientist at MIT</p>
</div>
|
|
web.stanford.edu
|
<div class="column">
<p class="title is-4">Jeannette Bohg</p>
<p class="subtitle is-6">Assistant Professor for Robotics at Stanford University</p>
</div>
|
|
ommer-lab.com
|
<div class="column">
<p class="title is-4">Björn Ommer</p>
<p class="subtitle is-6"></p>
</div>
|
|
linkedin.com
|
<div class="column">
<p class="title is-4">Afshin Dehghan</p>
<p class="subtitle is-6">Senior AI/ML Manager</p>
</div>
|
|
scenefun3d.github.io
|
SceneFun3D benchmark
|
|
scenefun3d.github.io
|
SceneFun3D Documentation
|
|
eval.ai
|
Benchmark Submission Portal
|
|
scenefun3d.github.io
|
Benchmark Submission Instructions
|
|
cvpr.thecvf.com
|
CVPR 2025 guidelines for poster preparation
|
|
github.com
|
official CVPR 2025
|
|
openreview.net
|
OpenReview
|
|
openaccess.thecvf.com
|
Proceedings
|
|
openaccess.thecvf.com
|
Enforcing View-Consistency in Class-Agnostic 3D Segmentation Fields
|
|
openaccess.thecvf.com
|
DCSEG: Decoupled 3D Open-Set Segmentation using Gaussian Splatting
|
|
openaccess.thecvf.com
|
HAECcity: Open-Vocabulary Scene Understanding of City-Scale Point Clouds with Superpoint Graph Clustering
|
|
openaccess.thecvf.com
|
Segment Any Primitive: Zero-Shot 3D Primitive Segmentation from Point Cloud
|
|
openaccess.thecvf.com
|
ForesightNav: Learning Scene Imagination for Efficient Exploration
|
|
openaccess.thecvf.com
|
OpenSplat3D: Open-Vocabulary 3D Instance Segmentation using Gaussian Splatting
|
|
arxiv.org
|
Online Language Splatting
|
|
arxiv.org
|
Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields
|
|
arxiv.org
|
<b>CrossOver: 3D Scene Cross-Modal Alignment</b>
|
|
arxiv.org
|
Пустой анкор
|
|
arxiv.org
|
FunGraph: Functionality Aware 3D Scene Graphs Generation from 2D and 3D Data
|
|
arxiv.org
|
Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis
|
|
concept-fusion.github.io
|
ConceptFusion: Open-set Multimodal 3D Mapping
|
|
pengsongyou.github.io
|
OpenScene: 3D Scene Understanding with Open
Vocabularies
|
|
lerf.io
|
LERF: Language Embedded Radiance Fields
|
|
pfnet-research.github.io
|
Decomposing NeRF for Editing
via Feature Field Distillation
|
|
semantic-abstraction.cs.columbia.edu
|
Semantic Abstraction: Open-World 3D Scene
Understanding from 2D Vision-Language Models
|
|
rozdavid.github.io
|
Language-Grounded Indoor 3D Semantic Segmentation in
the Wild
|
|
3dlg-hcvc.github.io
|
MultiScan: Scalable RGBD Scanning for 3D
Environments with Articulated Objects
|
|
github.com
|
ODISE: Open-Vocabulary Panoptic Segmentation with
Text-to-Image Diffusion Models
|
|
github.com
|
Weakly Supervised 3D Open-Vocabulary Segmentation
|
|
arxiv.org
|
Multi-CLIP: Contrastive Vision-Language Pre-training for
Question Answering tasks in 3D Scenes
|
|
openmask3d.github.io
|
OpenMask3D: Open-Vocabulary 3D Instance Segmentation
|
|
arxiv.org
|
CLIP-FO3D: Learning Free Open-world 3D Scene
Representations from 2D Dense CLIP
|
|
tsagkas.github.io
|
VL-Fields: Towards Language-Grounded Neural Implicit
Spatial Representations
|
|
openaccess.thecvf.com
|
PLA:
Language-Driven Open-Vocabulary 3D Scene Understanding
|
|
arxiv.org
|
RegionPLC: Regional Point-Language Contrastive Learning
for Open-World 3D Scene Understanding
|
|
arxiv.org
|
OpenIns3D: Snap and Lookup for 3D open-vocabulary
Instance Segmentation
|
|
concept-graphs.github.io
|
ConceptGraphs:
Open-Vocabulary 3D Scene Graphs for Perception and Planning
|
|
openaccess.thecvf.com
|
Open-Vocabulary
Point-Cloud Object Detection without 3D Annotation
|
|
github.com
|
CoDA: Collaborative Novel
Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection
|
|
scenefun3d.github.io
|
SceneFun3D: Fine-Grained Functionality and Affordance Understanding
in 3D Scenes
|
|
github.com
|
Clio: Real-time Task-Driven Open-Set 3D Scene Graphs
|
|
francisengelmann.github.io
|
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/francis.jpg" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Francis Engelmann</p>
<p class="subtitle is-7">Stanford</p>
</div>
</div>
</div>
</div>
|
|
aycatakmaz.github.io
|
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/ayca.jpg" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Ayca Takmaz</p>
<p class="subtitle is-7">ETH Zurich</p>
</div>
</div>
</div>
</div>
|
|
alexdelitzas.github.io
|
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/alex.jpeg" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Alex Delitzas</p>
<p class="subtitle is-7">ETH Zurich, MPI</p>
</div>
</div>
</div>
</div>
|
|
github.com
|
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/elisabetta.png" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Elisabetta Fedele</p>
<p class="subtitle is-7">ETH Zurich</p>
</div>
</div>
</div>
</div>
|
|
github.com
|
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/johanna.jpg" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Johanna Wald</p>
<p class="subtitle is-7">Google</p>
</div>
</div>
</div>
</div>
|
|
katadam.github.io
|
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/kata.png" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Katerina Adam</p>
<p class="subtitle is-7">NTUA</p>
</div>
</div>
</div>
</div>
|
|
jonasschult.github.io
|
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="https://jonasschult.github.io/images/profile.jpg" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Jonas Schult</p>
<p class="subtitle is-7">Meta</p>
</div>
</div>
</div>
</div>
|
|
zuriabauer.com
|
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="https://zuriabauer.com/assets/images/ZBauer.png" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Zuria Bauer</p>
<p class="subtitle is-7">ETH Zurich</p>
</div>
</div>
</div>
</div>
|
|
orlitany.github.io
|
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/or.jpg" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Or Litany</p>
<p class="subtitle is-7">NVIDIA, Technion</p>
</div>
</div>
</div>
</div>
|
|
federicotombari.github.io
|
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/federico.jpg" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Federico Tombari</p>
<p class="subtitle is-7">TUM, Google</p>
</div>
</div>
</div>
</div>
|
|
people.inf.ethz.ch
|
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/marc.jpg" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Marc Pollefeys</p>
<p class="subtitle is-7">ETHZ, Microsoft</p>
</div>
</div>
</div>
</div>
|
|
geometry.stanford.edu
|
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/leonidas.jpg" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Leonidas Guibas</p>
<p class="subtitle is-7">Stanford</p>
</div>
</div>
</div>
</div>
|
WordPress