6.9k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Meta (United Kingdom)GB158 papers
- Meta (Israel)IL62 papers
- Menlo SchoolUS51 papers
- New York UniversityUS49 papers
- Carnegie Mellon UniversityUS33 papers
- University of California, BerkeleyUS31 papers
- The University of Texas at AustinUS28 papers
- Google (United States)US27 papers
- Georgia Institute of TechnologyUS26 papers
- Stanford UniversityUS25 papers
- Cornell UniversityUS24 papers
- University of WashingtonUS20 papers
30 papers · 2 filters
SelfPose: 3D Egocentric Pose Estimation from a Headset Mounted Camera
Denis Tome, Thiemo Alldieck, Patrick Peluse +4
We present a solution to egocentric 3D body pose estimation from monocular images captured from downward looking fish-eye cameras installed on the rim of a head mounted VR device.…
Semantic MapNet: Building Allocentric Semantic Maps and Representations from Egocentric Views
Vincent Cartillier, Zhile Ren, Neha Jain +3
We study the task of semantic mapping - specifically, an embodied agent (a robot or an egocentric AI assistant) is given a tour of a new environment and asked to build an allocentr…
Flow-edge Guided Video Completion
Chen Gao, Ayush Saraf, Jia-Bin Huang +1
We present a new flow-based video completion algorithm. Previous flow completion methods are often unable to retain the sharpness of motion boundaries. Our method first extracts an…
SPAN: Spatial Pyramid Attention Network forImage Manipulation Localization
Xuefeng Hu, Zhihan Zhang, Zhenye Jiang +3
We present a novel framework, Spatial Pyramid Attention Network (SPAN) for detection and localization of multiple types of image manipulations. The proposed architecture efficientl…
AUTO3D: Novel view synthesis through unsupervisely learned variational viewpoint and global 3D representation
Xiaofeng Liu, Tong Che, Yiqun Lu +3
This paper targets on learning-based novel view synthesis from a single or limited 2D images without the pose supervision. In the viewer-centered coordinates, we construct an end-t…
Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild
Jason Y. Zhang, Sam Pepose, Hanbyul Joo +3
We present a method that infers spatial arrangements and shapes of humans and objects in a globally consistent 3D scene, all from a single image in-the-wild captured in an uncontro…
What leads to generalization of object proposals?
Rui Wang, Dhruv Mahajan, Vignesh Ramanathan
Object proposal generation is often the first step in many detection models. It is lucrative to train a good proposal model, that generalizes to unseen classes. This could help sca…
Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction
David Novotny, Roman Shapovalov, Andrea Vedaldi
We propose the Canonical 3D Deformer Map, a new representation of the 3D shape of common object categories that can be learned from a collection of 2D images of independent objects…
PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations
Edgar Tretschk, Ayush Tewari, Vladislav Golyanik +3
Implicit surface representations, such as signed-distance functions, combined with deep learning have led to impressive models which can represent detailed shapes of objects with a…
Fully Dynamic Inference with Deep Neural Networks
Wenhan Xia, Hongxu Yin, Xiaoliang Dai +1
Modern deep neural networks are powerful and widely applicable models that extract task-relevant information through multi-level abstraction. Their cross-domain success, however, i…
Real-time Semantic Segmentation with Fast Attention
Ping Hu, Federico Perazzi, Fabian Caba Heilbron +4
In deep CNN based models for semantic segmentation, high accuracy relies on rich spatial context (large receptive fields) and fine spatial details (high resolution), both of which…
Neural Sparse Voxel Fields
Lingjie Liu, Jiatao Gu, Kyaw Zaw Lin +2
Photo-realistic free-viewpoint rendering of real-world scenes using classical computer graphics techniques is challenging, because it requires the difficult step of capturing detai…
PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
Saining Xie, Jiatao Gu, Demi Guo +3
Arguably one of the top success stories of deep learning is transfer learning. The finding that pre-training a network on a rich source set (eg., ImageNet) can help boost performan…
HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Loss
Yurun Tian, Axel Barroso-Laguna, Tony Ng +2
Recent works show that local descriptor learning benefits from the use of L2 normalisation, however, an in-depth analysis of this effect lacks in the literature. In this paper, we…
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
Mathilde Caron, Ishan Misra, Julien Mairal +3
Unsupervised image representations have significantly reduced the gap with supervised pretraining, notably with the recent achievements of contrastive learning methods. These contr…
Progressive Skeletonization: Trimming more fat from a network at initialization
Pau de Jorge, Amartya Sanyal, Harkirat S. Behl +3
Recent studies have shown that skeletonization (pruning parameters) of networks \textit{at initialization} provides all the practical benefits of sparsity both at inference and tra…
Benefits of temporal information for appearance-based gaze estimation
Cristina Palmero, Oleg V. Komogortsev, Sachin S. Talathi
State-of-the-art appearance-based gaze estimation methods, usually based on deep learning techniques, mainly rely on static features. However, temporal trace of eye gaze contains u…
Consistent Video Depth Estimation
Xuan Luo, Jia-Bin Huang, Richard Szeliski +2
We present an algorithm for reconstructing dense, geometrically consistent depth for all pixels in a monocular video. We leverage a conventional structure-from-motion reconstructio…
Evaluation Metrics for Conditional Image Generation
Yaniv Benny, Tomer Galanti, Sagie Benaim +1
We present two new metrics for evaluating generative models in the class-conditional image generation setting. These metrics are obtained by generalizing the two most popular uncon…
3D Photography using Context-aware Layered Depth Inpainting
Meng-Li Shih, Shih-Yang Su, Johannes Kopf +1
We propose a method for converting a single RGB-D input image into a 3D photo - a multi-layer representation for novel view synthesis that contains hallucinated color and depth str…
Deep Space-Time Video Upsampling Networks
Jaeyeon Kang, Younghyun Jo, Seoung Wug Oh +2
Video super-resolution (VSR) and frame interpolation (FI) are traditional computer vision problems, and the performance have been improving by incorporating deep learning recently.…
Structural-analogy from a Single Image Pair
Sagie Benaim, Ron Mokady, Amit Bermano +2
The task of unsupervised image-to-image translation has seen substantial advancements in recent years through the use of deep neural networks. Typically, the proposed solutions lea…
Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation
Edoardo Remelli, Shangchen Han, Sina Honari +2
We present a lightweight solution to recover 3D pose from multi-view images captured with spatially calibrated cameras. Building upon recent advances in interpretable representatio…
SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation
Chenfeng Xu, Bichen Wu, Zining Wang +4
LiDAR point-cloud segmentation is an important problem for many applications. For large-scale point cloud segmentation, the \textit{de facto} method is to project a 3D point cloud…