• 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
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
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
Multi-view Object Segmentation in Space and Time
TLDR
A new approach is proposed that propagates segmentation coherence information in both space and time, hence allowing evidences in one image to be shared over the complete set, and only requires a sparse 3D sampling to propagate information between viewpoints. 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
Sparse Multi-View Consistency for Object Segmentation
TLDR
This work investigates the idea that examining measurements at the projections of a sparse set of 3D points is sufficient to achieve the goal of segmentation, and shows how other modalities such as depth may be seamlessly integrated in the model and benefit the segmentation. Expand
A Bayesian Approach for Selective Image-Based Rendering Using Superpixels
TLDR
This work proposes a Bayesian approach, modeling the rendering quality, the rendering process and the validity of the assumptions of each algorithm, and chooses the algorithm to use with Maximum a Posteriori estimation for Image-Based Rendering algorithms. Expand
Content Adaptive Optimization for Neural Image Compression
TLDR
This work introduces an iterative procedure which adapts the latent representation to the specific content the authors wish to compress while keeping the parameters of the network and the predictive model fixed and shows that this allows for an overall increase in rate-distortion performance, independently of the specific architecture used. Expand
N-tuple Color Segmentation for Multi-view Silhouette Extraction
TLDR
The n-tuple color model is introduced to express inter-view consistency when inferring in each view the foreground and background color models permitting the final segmentation in a new method to extract multiple segmentations of an object viewed by multiple cameras, given only the camera calibration. Expand
...
1
2
3
...