research
∙
09/11/2023
Towards Viewpoint Robustness in Bird's Eye View Segmentation
Autonomous vehicles (AV) require that neural networks used for perceptio...
share
research
∙
08/26/2023
Semi-Supervised Semantic Segmentation via Marginal Contextual Information
We present a novel confidence refinement scheme that enhances pseudo-lab...
research
∙
05/22/2023
Fast Monocular Scene Reconstruction with Global-Sparse Local-Dense Grids
Indoor scene reconstruction from monocular images has long been sought a...
research
∙
05/02/2023
Neural LiDAR Fields for Novel View Synthesis
We present Neural Fields for LiDAR (NFL), a method to optimise a neural ...
research
∙
03/25/2023
UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes
3D instance segmentation is fundamental to geometric understanding of th...
research
∙
10/12/2022
LION: Latent Point Diffusion Models for 3D Shape Generation
Denoising diffusion models (DDMs) have shown promising results in 3D poi...
research
∙
10/06/2022
Mask3D for 3D Semantic Instance Segmentation
Modern 3D semantic instance segmentation approaches predominantly rely o...
research
∙
09/22/2022
GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images
As several industries are moving towards modeling massive 3D virtual wor...
research
∙
08/18/2022
MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentation
We propose to utilize self-supervised techniques in the 2D domain for fi...
research
∙
04/16/2022
Language-Grounded Indoor 3D Semantic Segmentation in the Wild
Recent advances in 3D semantic segmentation with deep neural networks ha...
research
∙
02/16/2022
Learning Smooth Neural Functions via Lipschitz Regularization
Neural implicit fields have recently emerged as a useful representation ...
research
∙
02/08/2022
Causal Scene BERT: Improving object detection by searching for challenging groups of data
Modern computer vision applications rely on learning-based perception mo...
research
∙
01/20/2022
Federated Learning with Heterogeneous Architectures using Graph HyperNetworks
Standard Federated Learning (FL) techniques are limited to clients with ...
research
∙
12/09/2021
Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior
Evaluating and improving planning for autonomous vehicles requires scala...
research
∙
11/26/2021
Neural Fields as Learnable Kernels for 3D Reconstruction
We present Neural Kernel Fields: a novel method for reconstructing impli...
research
∙
11/22/2021
Neural Fields in Visual Computing and Beyond
Recent advances in machine learning have created increasing interest in ...
research
∙
10/30/2021
DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer
We consider the challenging problem of predicting intrinsic object prope...
research
∙
10/05/2021
Mix3D: Out-of-Context Data Augmentation for 3D Scenes
We present Mix3D, a data augmentation technique for segmenting large-sca...
research
∙
05/17/2021
StrobeNet: Category-Level Multiview Reconstruction of Articulated Objects
We present StrobeNet, a method for category-level 3D reconstruction of a...
research
∙
04/25/2021
Vector Neurons: A General Framework for SO(3)-Equivariant Networks
Invariance and equivariance to the rotation group have been widely discu...
research
∙
03/31/2021
Spectral Unions of Partial Deformable 3D Shapes
Spectral geometric methods have brought revolutionary changes to the fie...
research
∙
03/25/2021
Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels
The success of learning with noisy labels (LNL) methods relies heavily o...
research
∙
02/17/2021
Weakly Supervised Learning of Rigid 3D Scene Flow
We propose a data-driven scene flow estimation algorithm exploiting the ...
research
∙
02/01/2021
Self-Supervised Equivariant Scene Synthesis from Video
We propose a self-supervised framework to learn scene representations fr...
research
∙
12/18/2020
Human 3D keypoints via spatial uncertainty modeling
We introduce a technique for 3D human keypoint estimation that directly ...
research
∙
12/08/2020
3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection
3D object detection is an important yet demanding task that heavily reli...
research
∙
11/26/2020
Non-Rigid Puzzles
Shape correspondence is a fundamental problem in computer graphics and v...
research
∙
11/11/2020
Learned Equivariant Rendering without Transformation Supervision
We propose a self-supervised framework to learn scene representations fr...
research
∙
08/18/2020
ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation
Many Reinforcement Learning (RL) approaches use joint control signals (p...
research
∙
07/21/2020
PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
Arguably one of the top success stories of deep learning is transfer lea...
research
∙
07/20/2020
Object-Centric Multi-View Aggregation
We present an approach for aggregating a sparse set of views of an objec...
research
∙
02/26/2020
Representation Learning Through Latent Canonicalizations
We seek to learn a representation on a large annotated data source that ...
research
∙
02/20/2020
On Learning Sets of Symmetric Elements
Learning from unordered sets is a fundamental learning setup, which is a...
research
∙
02/06/2020
Continuous Geodesic Convolutions for Learning on 3D Shapes
The majority of descriptor-based methods for geometric processing of non...
research
∙
01/29/2020
ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes
3D object detection has seen quick progress thanks to advances in deep l...
research
∙
01/27/2020
The Whole Is Greater Than the Sum of Its Nonrigid Parts
According to Aristotle, a philosopher in Ancient Greece, "the whole is g...
research
∙
04/21/2019
Deep Hough Voting for 3D Object Detection in Point Clouds
Current 3D object detection methods are heavily influenced by 2D detecto...
research
∙
12/06/2018
Self-supervised Learning of Dense Shape Correspondence
We introduce the first completely unsupervised correspondence learning a...
research
∙
08/20/2018
Class-Aware Fully-Convolutional Gaussian and Poisson Denoising
We propose a fully-convolutional neural-network architecture for image d...
research
∙
06/03/2018
Dual-Primal Graph Convolutional Networks
In recent years, there has been a surge of interest in developing deep l...
research
∙
05/24/2018
SOSELETO: A Unified Approach to Transfer Learning and Training with Noisy Labels
We present SOSELETO (SOurce SELEction for Target Optimization), a new me...
research
∙
12/01/2017
Deformable Shape Completion with Graph Convolutional Autoencoders
The availability of affordable and portable depth sensors has made scann...
research
∙
07/25/2017
Efficient Deformable Shape Correspondence via Kernel Matching
We present a method to match three dimensional shapes under non-isometri...
research
∙
01/06/2017
Deep Class Aware Denoising
The increasing demand for high image quality in mobile devices brings fo...
research
∙
01/06/2017
Deep Convolutional Denoising of Low-Light Images
Poisson distribution is used for modeling noise in photon-limited imagin...
research
∙
12/15/2016
Cloud Dictionary: Sparse Coding and Modeling for Point Clouds
With the development of range sensors such as LIDAR and time-of-flight c...
research
∙
08/03/2016
FPGA system for real-time computational extended depth of field imaging using phase aperture coding
We present a proof-of-concept end-to-end system for computational extend...
research
∙
12/06/2015
Image reconstruction from dense binary pixels
Recently, the dense binary pixel Gigavision camera had been introduced, ...
research
∙
12/04/2015
ASIST: Automatic Semantically Invariant Scene Transformation
We present ASIST, a technique for transforming point clouds by replacing...
research
∙
10/15/2015