Search Results for author:
Found 34 papers, 14 papers with code
SLAG: Scalable Language-Augmented Gaussian Splatting
To address this, we introduce SLAG, a multi-GPU framework for language-augmented Gaussian splatting that enhances the speed and scalability of embedding large scenes.
Robust Human Registration with Body Part Segmentation on Noisy Point Clouds
Additionally, we demonstrate that the fitted human mesh can refine body part labels, leading to improved segmentation.
Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces
We introduce the task of predicting functional 3D scene graphs for real-world indoor environments from posed RGB-D images.
ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding
Further, we push forward the state-of-the-art performance on ScanNet and ScanNet200 dataset with prevalent 3D semantic segmentation models, demonstrating the efficacy of our generated dataset.
Ranked #3 on
Semantic Segmentation
on ScanNet
(using extra training data)
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.
P2P-Bridge: Diffusion Bridges for 3D Point Cloud Denoising
In this work, we tackle the task of point cloud denoising through a novel framework that adapts Diffusion Schr\"odinger bridges to points clouds.
Improving 2D Feature Representations by 3D-Aware Fine-Tuning
In this work, we show that fine-tuning on 3D-aware data improves the quality of emerging semantic features.
OpenDAS: Open-Vocabulary Domain Adaptation for 2D and 3D Segmentation
However, this flexibility comes with a trade-off: fully-supervised closed-set methods still outperform OVS methods on base classes, that is on classes on which they have been explicitly trained.
Ranked #8 on
Open Vocabulary Semantic Segmentation
on ADE20K-150
3D Instance Segmentation
3D Open-Vocabulary Instance Segmentation
+8
Spot-Compose: A Framework for Open-Vocabulary Object Retrieval and Drawer Manipulation in Point Clouds
This allows for accurate detection directly in 3D scenes, object- and environment-aware grasp prediction, as well as robust and repeatable robotic manipulation.
OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views
Our OpenNeRF further leverages NeRF's ability to render novel views and extract open-set VLM features from areas that are not well observed in the initial posed images.
SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs
We introduce a novel problem, i. e., the localization of an input image within a multi-modal reference map represented by a database of 3D scene graphs.
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.
ICGNet: A Unified Approach for Instance-Centric Grasping
Executing a successful grasp in a cluttered environment requires multiple levels of scene understanding: First, the robot needs to analyze the geometric properties of individual objects to find feasible grasps.
SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes
Existing 3D scene understanding methods are heavily focused on 3D semantic and instance segmentation.
Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels
Therefore, we explore the use of image segmentation foundation models to automatically generate training labels for 3D segmentation.
ALSTER: A Local Spatio-Temporal Expert for Online 3D Semantic Reconstruction
Using these main contributions, our method can enable scenarios with real-time constraints and can scale to arbitrary scene sizes by processing and updating the scene only in a local region defined by the new measurement.
LABELMAKER: Automatic Semantic Label Generation from RGB-D Trajectories
Semantic annotations are indispensable to train or evaluate perception models, yet very costly to acquire.
Ranked #1 on
Semantic Segmentation
on Replica
AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation
In an iterative process, the model assigns each data point to an object (or the background), while the user corrects errors in the resulting segmentation and feeds them back into the model.
3D Segmentation of Humans in Point Clouds with Synthetic Data
We address this challenge and propose a framework for generating training data of synthetic humans interacting with real 3D scenes.
Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries
Instead, we formulate floorplan reconstruction as a single-stage structured prediction task: find a variable-size set of polygons, which in turn are variable-length sequences of ordered vertices.
Mask3D: Mask Transformer for 3D Semantic Instance Segmentation
Modern 3D semantic instance segmentation approaches predominantly rely on specialized voting mechanisms followed by carefully designed geometric clustering techniques.
Ranked #2 on
3D Instance Segmentation
on STPLS3D
3D Instance Segmentation
3D Semantic Instance Segmentation
+2
4D-StOP: Panoptic Segmentation of 4D LiDAR using Spatio-temporal Object Proposal Generation and Aggregation
Our voting-based tracklet generation method followed by geometric feature-based aggregation generates significantly improved panoptic LiDAR segmentation quality when compared to modeling the entire 4D volume using Gaussian probability distributions.
Ranked #4 on
4D Panoptic Segmentation
on SemanticKITTI
Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes
Indeed, we show that it is possible to train dense segmentation models using only bounding box labels.
3D Instance Segmentation
3D Semantic Instance Segmentation
+2
Mix3D: Out-of-Context Data Augmentation for 3D Scenes
Since scene context helps reasoning about object semantics, current works focus on models with large capacity and receptive fields that can fully capture the global context of an input 3D scene.
Ranked #26 on
Semantic Segmentation
on ScanNet
From Points to Multi-Object 3D Reconstruction
We propose a method to detect and reconstruct multiple 3D objects from a single RGB image.
3D-MPA: Multi-Proposal Aggregation for 3D Semantic Instance Segmentation
We show that grouping proposals improves over NMS and outperforms previous state-of-the-art methods on the tasks of 3D object detection and semantic instance segmentation on the ScanNetV2 benchmark and the S3DIS dataset.
SAMP: Shape and Motion Priors for 4D Vehicle Reconstruction
In this paper, we propose to use 3D shape and motion priors to regularize the estimation of the trajectory and the shape of vehicles in sequences of stereo images.
DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes
That is, the convolutional kernel weights are mapped to the local surface of a given mesh.
3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation
We show that grouping proposals improves over NMS and outperforms previous state-of-the-art methods on the tasks of 3D object detection and semantic instance segmentation on the ScanNetV2 benchmark and the S3DIS dataset.
Ranked #1 on
3D Semantic Instance Segmentation
on ScanNetV2
Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds
In a thorough ablation study, we show that the receptive field size is directly related to the performance of 3D point cloud processing tasks, including semantic segmentation and object classification.
Ranked #51 on
Semantic Segmentation
on S3DIS Area5
3D-BEVIS: Bird's-Eye-View Instance Segmentation
A lot of progress was made in the field of object classification and semantic segmentation.
Ranked #4 on
3D Semantic Instance Segmentation
on ScanNetV2
3D Instance Segmentation
3D Semantic Instance Segmentation
+5
Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds
In this paper, we present a deep learning architecture which addresses the problem of 3D semantic segmentation of unstructured point clouds.
Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds
The recently proposed PointNet architecture presents an interesting step ahead in that it can operate on unstructured point clouds, achieving encouraging segmentation results.
Keyframe-Based Visual-Inertial Online SLAM with Relocalization
Our visual-inertial SLAM system is based on a real-time capable visual-inertial odometry method that provides locally consistent trajectory and map estimates.
