Acquisition and Rendering of Transparent and Refractive Objects

By W. Matusik, H. Pfister, Remo Ziegler, A. Ngan, L. McMillan. Rendering Techniques, 2002

736 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/a8d9e563cf7c947a972f31b36f2818e58df0be96

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Face detection, pose estimation, and landmark localization in the wild (2012, methodology): “Most methods use explicit 3D models [6, 17] or 2D view-based models [30, 10, 21].”
The Fastest Pedestrian Detector in the West (2010, methodology): “Through numerous strategies, including cascades [28], coarse-to-fine search [17], distance transforms [13], branch and bound search [19], and many others, the classification stage can be made quite fast.”
Synergistic Face Detection and Pose Estimation with Energy-Based Models (2004, background): “The table shows that our results on the TILTED and PROFILE sets are similar to those of the two Jones & Viola detectors, and even approach those of the Rowley et al and Schneiderman & Kanade nonreal-time detectors.”
Survey on RGB, 3D, Thermal, and Multimodal Approaches for Facial Expression Recognition: History, Trends, and Affect-related Applications (2016, methodology): “For RGB images, Viola and Jones [60] still is one of the most used algorithms [10], [61], [177].”
A Survey on Human Motion Analysis from Depth Data (2013, unknown): “RGB Appearance-based Methods Appearance-based methods usually discretize the head pose space and learn separate detectors for subsets of poses [44, 45].”
Measuring Gender Bias in News Images (2015, methodology): “Following this, we took each URL extracted from the news articles, and attempted to download the image, performing face recognition on the image using the Viola-Jones algorithm [10] in OpenCV [2].”
Random Forests for Real Time 3D Face Analysis (2012, methodology): “2D Appearance-Based Methods These methods usually discretize the head pose space and learn separate detectors for subsets of poses (Jones and Viola 2003).”
Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes (2012, background): “Learning-based systems generalize well to the objects of particular class like human faces [6], cars [7, 8], or”
Face Detection using Deep Learning: An Improved Faster RCNN Approach (2017, background): “One simple strategy was to combine multiple detectors that had been trained separately for different views or poses[20][21][22].”
Probabilistic boosting-tree: learning discriminative models for classification, recognition, and clustering (2005, methodology): “There has been significant progress made recently in the area of face detection [ 21 , 17, 16, 10, 6], most of which focuses on faces in frontal view.”
Robust hand detection (2004, methodology): “To achieve this, we use a very fast and accurate learning-based object detection method that was recently proposed and extended by Viola and Jones [10, 5], primarily applied to face detection.”
Real Time Head Pose Estimation from Consumer Depth Cameras (2011, background): “Examples of appearance-based methods are [13] and [17], where the head pose space is discretized and separate detectors are learned for each segment.”
FDDB: A benchmark for face detection in unconstrained settings (2010, background): “• multi-view: out-of-plane rotations are binned into a pre-determined set of views [7, 9, 12];”
Detecting Object Boundaries Using Low-, Mid-, and High-level Information (2007, background): “different Haar filters with different sizes at various locations [ 22 ], and histogram features on various Gabor functions.”
SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection (2018, background): “A typical way of reducing the variance is partitioning samples by pose [18,20,34], rotation [36] or resolution [25,35].”
Real time head pose estimation with random regression forests (2011, background): “Due to its relevance and to the challenges posed by the problem, there has been considerable effort in the computer vision community to develop fast and reliable algorithms for head pose estimation.”