Search Results for author:
Found 22 papers, 12 papers with code
TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models
Given access to paired image-pointcloud (2D-3D) data, we first optimize a 3D segmentation backbone for the main task of semantic segmentation using the pointclouds and the task of 2D $\to$ 3D KD by using an off-the-shelf 2D pre-trained foundation model.
Attention-Guided Masked Autoencoders For Learning Image Representations
Masked autoencoders (MAEs) have established themselves as a powerful method for unsupervised pre-training for computer vision tasks.
Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships
We co-embed the features from a 3D scene graph prediction backbone with the feature space of powerful open world 2D vision language foundation models.
PPSURF: Combining Patches and Point Convolutions for Detailed Surface Reconstruction
3D surface reconstruction from point clouds is a key step in areas such as content creation, archaeology, digital cultural heritage, and engineering.
FATE: Feature-Agnostic Transformer-based Encoder for learning generalized embedding spaces in flow cytometry data
This limitation becomes particularly relevant in scenarios where the attributes captured during data acquisition vary across different samples.
Lang3DSG: Language-based contrastive pre-training for 3D Scene Graph prediction
While it is widely accepted that pre-training is an effective approach to improve model performance in low data regimes, in this paper, we find that existing pre-training methods are ill-suited for 3D scene graphs.
Point Neighborhood Embeddings
Additionally, we show that a neural network architecture using simple convolutions based on such embeddings is able to achieve state-of-the-art results on several tasks, outperforming recent and more complex operations.
SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction
In the field of 3D scene understanding, 3D scene graphs have emerged as a new scene representation that combines geometric and semantic information about objects and their relationships.
Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling
We achieve this by (1) learning depth-feature correlation by spatially correlate the feature maps with the depth maps to induce knowledge about the structure of the scene and (2) implementing farthest-point sampling to more effectively select relevant features by utilizing 3D sampling techniques on depth information of the scene.
ClusterNet: A Perception-Based Clustering Model for Scattered Data
Finally, we compare our approach against existing state-of-the-art clustering techniques and can show, that ClusterNet is able to generalize to unseen and out of scope data.
Weakly-Supervised Optical Flow Estimation for Time-of-Flight
Indirect Time-of-Flight (iToF) cameras are a widespread type of 3D sensor, which perform multiple captures to obtain depth values of the captured scene.
Contrastive Representation Learning for 3D Protein Structures
Learning from 3D protein structures has gained wide interest in protein modeling and structural bioinformatics.
Clean Implicit 3D Structure from Noisy 2D STEM Images
Scanning Transmission Electron Microscopes (STEMs) acquire 2D images of a 3D sample on the scale of individual cell components.
Gaussian Mixture Convolution Networks
This paper proposes a novel method for deep learning based on the analytical convolution of multidimensional Gaussian mixtures.
Variance-Aware Weight Initialization for Point Convolutional Neural Networks
Appropriate weight initialization has been of key importance to successfully train neural networks.
RADU: Ray-Aligned Depth Update Convolutions for ToF Data Denoising
Time-of-Flight (ToF) cameras are subject to high levels of noise and distortions due to Multi-Path-Interference (MPI).
Data-driven deep density estimation
Density estimation plays a crucial role in many data analysis tasks, as it infers a continuous probability density function (PDF) from discrete samples.
Intrinsic-Extrinsic Convolution and Pooling for Learning on 3D Protein Structures
Proteins perform a large variety of functions in living organisms, thus playing a key role in biology.
Enabling Viewpoint Learning through Dynamic Label Generation
Optimal viewpoint prediction is an essential task in many computer graphics applications.
Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning
We show that denoising of 3D point clouds can be learned unsupervised, directly from noisy 3D point cloud data only.
Deep-learning the Latent Space of Light Transport
Thus, we suggest a two-stage operator comprising of a 3D network that first transforms the point cloud into a latent representation, which is later on projected to the 2D output image using a dedicated 3D-2D network in a second step.
Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds
We propose an efficient and effective method to learn convolutions for non-uniformly sampled point clouds, as they are obtained with modern acquisition techniques.
