paperlist.ai

CVPR 2017 Papers

Conference on Computer Vision and Pattern Recognition

202620252024202320222021202020192018201720162015

Decision breakdown

783papers

Counted from the official paper list; may differ slightly from the number the conference announced.

  • Oral
    719.1%
  • Spotlight
    14418.4%
  • Poster
    56872.5%

Top 10 topics (click to filter)

No topic data yet.

Trends for all 207 research topics

Browse all papers

All783Oral71Spotlight144Poster568
3D Face Morphable Models "In-The-Wild"

James Booth, Epameinondas Antonakos, Stylianos Ploumpis, George Trigeorgis, Yannis Panagakis, Stefanos Zafeiriou

Expand abstract

3D Morphable Models (3DMMs) are powerful statistical models of 3D facial shape and texture, and among the state-of-the-art methods for reconstructing facial shape from single images. With the advent of new 3D sensors, many 3D facial datasets have been collected containing both neutral as well as expressive faces. However, all datasets are captured under controlled conditions. Thus, even though powerful 3D facial shape models can be learnt from such data, it is difficult to build statistical texture models that are sufficient to reconstruct faces captured in unconstrained conditions ("in-the-wild"). In this paper, we propose the first, to the best of our knowledge, "in-the-wild" 3DMM by combining a powerful statistical model of facial shape, which describes both identity and expression, with an "in-the-wild" texture model. We show that the employment of such an "in-the-wild" texture model greatly simplifies the fitting procedure, because there is no need to optimise with regards to the illumination parameters. Furthermore, we propose a new fast algorithm for fitting the 3DMM in arbitrary images. Finally, we have captured the first 3D facial database with relatively unconstrained conditions and report quantitative evaluations with state-of-the-art performance. Complementary qualitative reconstruction results are demonstrated on standard "in-the-wild" facial databases.

Spotlight
3D Convolutional Neural Networks for Efficient and Robust Hand Pose Estimation From Single Depth Images

Liuhao Ge, Hui Liang, Junsong Yuan, Daniel Thalmann

Expand abstract

We propose a simple, yet effective approach for real-time hand pose estimation from single depth images using three-dimensional Convolutional Neural Networks (3D CNNs). Image based features extracted by 2D CNNs are not directly suitable for 3D hand pose estimation due to the lack of 3D spatial information. Our proposed 3D CNN taking a 3D volumetric representation of the hand depth image as input can capture the 3D spatial structure of the input and accurately regress full 3D hand pose in a single pass. In order to make the 3D CNN robust to variations in hand sizes and global orientations, we perform 3D data augmentation on the training data. Experiments show that our proposed 3D CNN based approach outperforms state-of-the-art methods on two challenging hand pose datasets, and is very efficient as our implementation runs at over 215 fps on a standard computer with a single GPU.

Poster
3D Bounding Box Estimation Using Deep Learning and Geometry

Arsalan Mousavian, Dragomir Anguelov, John Flynn, Jana Kosecka

Expand abstract

We present a method for 3D object detection and pose estimation from a single image. In contrast to current techniques that only regress the 3D orientation of an object, our method first regresses relatively stable 3D object properties using a deep convolutional neural network and then combines these estimates with geometric constraints provided by a 2D object bounding box to produce a complete 3D bounding box. The first network output estimates the 3D object orientation using a novel hybrid discrete-continuous loss, which significantly outperforms the L2 loss. The second output regresses the 3D object dimensions, which have relatively little variance compared to alternatives and can often be predicted for many object types. These estimates, combined with the geometric constraints on translation imposed by the 2D bounding box, enable us to recover a stable and accurate 3D object pose. We evaluate our method on the challenging KITTI object detection benchmark [??] both on the official metric of 3D orientation estimation and also on the accuracy of the obtained 3D bounding boxes. Although conceptually simple, our method outperforms more complex and computationally expensive approaches that leverage semantic segmentation, instance level segmentation and flat ground priors [??] and sub-category detection [??][??]. Our discrete-continuous loss also produces state of the art results for 3D viewpoint estimation on the Pascal 3D+ dataset[??].

Poster