paper-with-me

홈 › Papers

A Simple, Fast and Highly-Accurate Algorithm to Recover 3D Shape from 2D Landmarks on a Single Image

2016-09-28 · Ruiqi Zhao, Yan Wang, Aleix Martinez

Three-dimensional shape reconstruction of 2D landmark points on a single image is a hallmark of human vision, but is a task that has been proven difficult for computer vision algorithms. We define a feed-forward deep neural network algorithm that can reconstruct 3D shapes from 2D landmark points almost perfectly (i.e., with extremely small reconstruction errors), even when these 2D landmarks are from a single image. Our experimental results show an improvement of up to two-fold over state-of-the-art computer vision algorithms; 3D shape reconstruction of human faces is given at a reconstruction error < .004, cars at .0022, human bodies at .022, and highly-deformable flags at an error of .0004. Our algorithm was also a top performer at the 2016 3D Face Alignment in the Wild Challenge competition (done in conjunction with the European Conference on Computer Vision, ECCV) that required the reconstruction of 3D face shape from a single image. The derived algorithm can be trained in a couple hours and testing runs at more than 1, 000 frames/s on an i7 desktop. We also present an innovative data augmentation approach that allows us to train the system efficiently with small number of samples. And the system is robust to noise (e.g., imprecise landmark points) and missing data (e.g., occluded or undetected landmark points).

📄 PDF Abstract BibTeX arXiv:1609.09058

Code (0)

등록된 구현이 없습니다.

Tasks

3D Face Alignment3D Shape ReconstructionData AugmentationFace Alignment

Similar Papers 제목 키워드 기반

Low-Rank Matrices on Graphs: Generalized Recovery & Applications

2016-05-18 · Nauman Shahid, Nathanael Perraudin, Pierre Vandergheynst

Many real world datasets subsume a linear or non-linear low-rank structure in a very low-dimensional space. Unfortunately, one often has very little or no information about the geometry of the space, resulting in a highl…

Embracing Discrete Search: A Reasonable Approach to Causal Structure Learning

2025-10-06 · Marcel Wienöbst, Leonard Henckel, Sebastian Weichwald arxiv

We present FLOP (Fast Learning of Order and Parents), a score-based causal discovery algorithm for linear models. It pairs fast parent selection with iterative Cholesky-based score updates, cutting run-times over prior a…

When in Doubt, SWAP: High-Dimensional Sparse Recovery from Correlated Measurements

2013-12-01 · NeurIPS 2013 12 · Divyanshu Vats, Richard Baraniuk

We consider the problem of accurately estimating a high-dimensional sparse vector using a small number of linear measurements that are contaminated by noise. It is well known that standard computationally tractable spar…

Vocal Bursts Intensity Prediction

Fast and Accurate Triangle Counting in Graph Streams Using Predictions

2024-09-23 · Cristian Boldrin, Fabio Vandin

In this work, we present the first efficient and practical algorithm for estimating the number of triangles in a graph stream using predictions. Our algorithm combines waiting room sampling and reservoir sampling with a …

Sparse model selection in the highly under-sampled regime

2016-03-03 · Nicola Bulso, Matteo Marsili, Yasser Roudi

We propose a method for recovering the structure of a sparse undirected graphical model when very few samples are available. The method decides about the presence or absence of bonds between pairs of variable by consider…

Model Selection