Search Results for author:
Found 35 papers, 26 papers with code
Convolutional Neural Networks for joint object detection and pose estimation: A comparative study
In this paper we study the application of convolutional neural networks for jointly detecting objects depicted in still images and estimating their 3D pose.
A MRF Shape Prior for Facade Parsing With Occlusions
We present a new shape prior formalism for segmentation of rectified facade images.
Efficient 2D and 3D Facade Segmentation using Auto-Context
This paper introduces a fast and efficient segmentation technique for 2D images and 3D point clouds of building facades.
Crafting a multi-task CNN for viewpoint estimation
Convolutional Neural Networks (CNNs) were recently shown to provide state-of-the-art results for object category viewpoint estimation.
Robust SfM with Little Image Overlap
Usual Structure-from-Motion (SfM) techniques require at least trifocal overlaps to calibrate cameras and reconstruct a scene.
Virtual Training for a Real Application: Accurate Object-Robot Relative Localization without Calibration
Localizing an object accurately with respect to a robot is a key step for autonomous robotic manipulation.
Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objects
Most deep pose estimation methods need to be trained for specific object instances or categories.
Surface Reconstruction from 3D Line Segments
In man-made environments such as indoor scenes, when point-based 3D reconstruction fails due to the lack of texture, lines can still be detected and used to support surfaces.
FKAConv: Feature-Kernel Alignment for Point Cloud Convolution
Recent state-of-the-art methods for point cloud processing are based on the notion of point convolution, for which several approaches have been proposed.
Ranked #1 on
LIDAR Semantic Segmentation
on Paris-Lille-3D
Spherical Perspective on Learning with Normalization Layers
Normalization Layers (NLs) are widely used in modern deep-learning architectures.
FLOT: Scene Flow on Point Clouds Guided by Optimal Transport
Our main finding is that FLOT can perform as well as the best existing methods on synthetic and real-world datasets while requiring much less parameters and without using multiscale analysis.
Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild
In this paper, we tackle the problems of few-shot object detection and few-shot viewpoint estimation.
Ranked #14 on
Few-Shot Object Detection
on MS-COCO (30-shot)
Pixel-Pair Occlusion Relationship Map(P2ORM): Formulation, Inference & Application
The former provides a way to generate large-scale accurate occlusion datasets while, based on the latter, we propose a novel method for task-independent pixel-level occlusion relationship estimation from single images.
PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning
We experimented on Pascal3D+, ObjectNet3D and Pix3D in a cross-dataset fashion, with both seen and unseen classes.
Scalable Surface Reconstruction with Delaunay-Graph Neural Networks
We introduce a novel learning-based, visibility-aware, surface reconstruction method for large-scale, defect-laden point clouds.
Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds
While there has been a number of studies on Zero-Shot Learning (ZSL) for 2D images, its application to 3D data is still recent and scarce, with just a few methods limited to classification.
Ranked #1 on
Generalized Zero-Shot Learning
on ScanNet
Localizing Objects with Self-Supervised Transformers and no Labels
We also show that training a class-agnostic detector on the discovered objects boosts results by another 7 points.
Ranked #4 on
Weakly-Supervised Object Localization
on CUB-200-2011
(Top-1 Localization Accuracy metric)
PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds
Rigid registration of point clouds with partial overlaps is a longstanding problem usually solved in two steps: (a) finding correspondences between the point clouds; (b) filtering these correspondences to keep only the most reliable ones to estimate the transformation.
NeeDrop: Self-supervised Shape Representation from Sparse Point Clouds using Needle Dropping
There has been recently a growing interest for implicit shape representations.
POCO: Point Convolution for Surface Reconstruction
To overcome this limitation, a few approaches infer latent vectors on a coarse regular 3D grid or on 3D patches, and interpolate them to answer occupancy queries.
Ranked #1 on
3D Reconstruction
on ShapeNet
Deep Surface Reconstruction from Point Clouds with Visibility Information
Most current neural networks for reconstructing surfaces from point clouds ignore sensor poses and only operate on raw point locations.
Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data
In this context, we propose a self-supervised pre-training method for 3D perception models that is tailored to autonomous driving data.
Take One Gram of Neural Features, Get Enhanced Group Robustness
Predictive performance of machine learning models trained with empirical risk minimization (ERM) can degrade considerably under distribution shifts.
A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation
We propose a simple, yet powerful approach for unsupervised object segmentation in videos.
Ranked #1 on
Unsupervised Video Object Segmentation
on SegTrack v2
(Jaccard (Mean) metric)
ALSO: Automotive Lidar Self-supervision by Occupancy estimation
The core idea is to train the model on a pretext task which is the reconstruction of the surface on which the 3D points are sampled, and to use the underlying latent vectors as input to the perception head.
RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving
(c) We refine pixel-wise predictions with a convolutional decoder and a skip connection from the convolutional stem to combine low-level but fine-grained features of the the convolutional stem with the high-level but coarse predictions of the ViT encoder.
Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation
Semantic segmentation of point clouds in autonomous driving datasets requires techniques that can process large numbers of points efficiently.
Ranked #4 on
LIDAR Semantic Segmentation
on nuScenes
(val mIoU metric)
A Survey and Benchmark of Automatic Surface Reconstruction from Point Clouds
We present a comprehensive survey and benchmark of both traditional and learning-based methods for surface reconstruction from point clouds.
SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation
Learning models on one labeled dataset that generalize well on another domain is a difficult task, as several shifts might happen between the data domains.
You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation
Assuming that images of the point clouds are available, which is common, our method relies on powerful unsupervised image features to measure the diversity of the point clouds.
DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion
We present an innovative approach to 3D Human Pose Estimation (3D-HPE) by integrating cutting-edge diffusion models, which have revolutionized diverse fields, but are relatively unexplored in 3D-HPE.
Three Pillars improving Vision Foundation Model Distillation for Lidar
In particular, thanks to our scalable distillation method named ScaLR, we show that scaling the 2D and 3D backbones and pretraining on diverse datasets leads to a substantial improvement of the feature quality.
BEVContrast: Self-Supervision in BEV Space for Automotive Lidar Point Clouds
We present a surprisingly simple and efficient method for self-supervision of 3D backbone on automotive Lidar point clouds.
ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation
Monocular 3D human pose estimation (3D-HPE) is an inherently ambiguous task, as a 2D pose in an image might originate from different possible 3D poses.
Pixel-Pair Occlusion Relationship Map (P2ORM): Formulation, Inference & Application
Inference & Application","We formalize concepts around geometric occlusion in 2D images (i. e., ignoring semantics), and propose a novel unified formulation of both occlusion boundaries and occlusion orientations via a pixel-pair occlusion relation.
