• Publications
  • Influence
Normalized Cut Loss for Weakly-Supervised CNN Segmentation
TLDR
This work proposes a new principled loss function evaluating network output with criteria standard in "shallow" segmentation, e.g. normalized cut which evaluates only seeds where labels are known while normalized cut softly evaluates consistency of all pixels. Expand
On Regularized Losses for Weakly-supervised CNN Segmentation
TLDR
This approach simplifies weakly-supervised training by avoiding extra MRF/CRF inference steps or layers explicitly generating full masks, while improving both the quality and efficiency of training. Expand
A Fully Progressive Approach to Single-Image Super-Resolution
TLDR
To obtain more photorealistic results, a generative adversarial network (GAN) is designed, named ProGanSR, that follows the same progressive multi-scale design principle and constitutes a principled multi- scale approach that increases the reconstruction quality for all upsampling factors simultaneously. Expand
Neural Inter-Frame Compression for Video Coding
TLDR
This work presents an inter-frame compression approach for neural video coding that can seamlessly build up on different existing neural image codecs and proposes to compute residuals directly in latent space instead of in pixel space to reuse the same image compression network for both key frames and intermediate frames. Expand
VideoSnapping: interactive synchronization of multiple videos
TLDR
This work first derives a robust approximation of alignment quality between pairs of clips, computed as a weighted histogram of feature matches, and finds optimal temporal mappings (constituting frame correspondences) using a graph-based approach that allows for very efficient evaluation with artist constraints. Expand
Cyclic Schemes for PDE-Based Image Analysis
TLDR
This work investigates a class of efficient numerical algorithms for many partial differential equations (PDEs) in image analysis that are applicable to parabolic or elliptic PDEs that have bounded coefficients and lead to space discretisations with symmetric matrices and shows that one should use parameter cycles that result from factorisations of box filters. Expand
Blind image super-resolution with spatially variant degradations
TLDR
This work proposes a solution that relies on a degradation aware SR network to synthesize the HR image given a low resolution image and the corresponding blur kernel and presents an optimization procedure that is able to recover both the degradation kernel and the high resolution image by minimizing the error predicted by the kernel discriminator. Expand
PhaseNet for Video Frame Interpolation
TLDR
This work proposes a new approach, PhaseNet, that is designed to robustly handle challenging scenarios while also coping with larger motion, and shows that this is superior to the hand-crafted heuristics previously used in phase-based methods and compares favorably to recent deep learning based approaches for video frame interpolation on challenging datasets. Expand
Anisotropic Range Image Integration
TLDR
This paper extends the state-of-the-art approach of Zach et al.(2007) in several ways, replacing the isotropic space-variant smoothing behaviour by an anisotropic (direction-dependent) one and using the more accurate closest signed distances instead of directional signed distances when converting range images into 3D signed distance fields. Expand
Point Cloud Noise and Outlier Removal for Image-Based 3D Reconstruction
TLDR
This work presents a simple and effective method for removing noise and outliers from point sets generated by image-based 3D reconstruction techniques, which allows standard surface reconstruction methods to perform less smoothing and thus achieve higher quality surfaces with more features. Expand
...
1
2
3
4
...