53 citations · 125 across the 19 of their papers we have counts for
22 papers
αDepth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion
Xiang Zhang, Yang Zhang, Lukas Mehl +3
Accurately modeling soft boundaries, e.g., hair and defocus blur, is a fundamental challenge in stereo conversion due to the ambiguous blending of foreground and background. Existi…
UniFixer: A Universal Reference-Guided Fixer for Diffusion-Based View Synthesis
Sihan Chen, Xiang Zhang, Yang Zhang +2
With the recent surge of generative models, diffusion-based approaches have become mainstream for view synthesis tasks, either in an explicit depth-warp-inpaint or in an implicit e…
Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views
Xiang Zhang, Yang Zhang, Lukas Mehl +2
Soft boundaries, like thin hairs, are commonly observed in natural and computer-generated imagery, but they remain challenging for 3D vision due to the ambiguous mixing of foregrou…
StableDPT: Temporal Stable Monocular Video Depth Estimation
Ivan Sobko, Hayko Riemenschneider, Markus Gross +1
Applying single image Monocular Depth Estimation (MDE) models to video sequences introduces significant temporal instability and flickering artifacts. We propose a novel approach t…
RenderFlow: Single-Step Neural Rendering via Flow Matching
Shenghao Zhang, Runtao Liu, Christopher Schroers +1
Conventional physically based rendering (PBR) pipelines generate photorealistic images through computationally intensive light transport simulations. Although recent deep learning…
Leveraging Diffusion Models for Stylization using Multiple Style Images
Dan Ruta, Abdelaziz Djelouah, Raphael Ortiz +1
Recent advances in latent diffusion models have enabled exciting progress in image style transfer. However, several key issues remain. For example, existing methods still struggle…
Efficient All-Pairs Correlation Volume Sampling for Optical Flow Estimation
Karlis Martins Briedis, Markus Gross, Christopher Schroers
Recent optical flow estimation methods often employ local cost sampling from a dense all-pairs correlation volume. This results in quadratic computational and memory complexity in…
Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compression
Lucas Relic, Roberto Azevedo, Yang Zhang +2
Generative neural image compression supports data representation at extremely low bitrate, synthesizing details at the client and consistently producing highly realistic images. By…
High-Fidelity Novel View Synthesis via Splatting-Guided Diffusion
Xiang Zhang, Yang Zhang, Lukas Mehl +2
Despite recent advances in Novel View Synthesis (NVS), generating high-fidelity views from single or sparse observations remains a significant challenge. Existing splatting-based a…
Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion
Manuel Kansy, Jacek Naruniec, Christopher Schroers +2
Recent years have seen a tremendous improvement in the quality of video generation and editing approaches. While several techniques focus on editing appearance, few address motion.…
BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation
Xiang Zhang, Bingxin Ke, Hayko Riemenschneider +5
By training over large-scale datasets, zero-shot monocular depth estimation (MDE) methods show robust performance in the wild but often suffer from insufficient detail. Although re…
Lossy Image Compression with Foundation Diffusion Models
Lucas Relic, Roberto Azevedo, Markus Gross +1
Incorporating diffusion models in the image compression domain has the potential to produce realistic and detailed reconstructions, especially at extremely low bitrates. Previous m…
Revitalizing Legacy Video Content: Deinterlacing with Bidirectional Information Propagation
Zhaowei Gao, Mingyang Song, Christopher Schroers +1
Due to old CRT display technology and limited transmission bandwidth, early film and TV broadcasts commonly used interlaced scanning. This meant each field contained only half of t…
Controllable Inversion of Black-Box Face Recognition Models via Diffusion
Manuel Kansy, Anton Raël, Graziana Mignone +4
Face recognition models embed a face image into a low-dimensional identity vector containing abstract encodings of identity-specific facial features that allow individuals to be di…
Microdosing: Knowledge Distillation for GAN based Compression
Leonhard Helminger, Roberto Azevedo, Abdelaziz Djelouah +2
Recently, significant progress has been made in learned image and video compression. In particular the usage of Generative Adversarial Networks has lead to impressive results in th…
Blind Image Restoration with Flow Based Priors
Leonhard Helminger, Michael Bernasconi, Abdelaziz Djelouah +2
Image restoration has seen great progress in the last years thanks to the advances in deep neural networks. Most of these existing techniques are trained using full supervision wit…
Lossy Image Compression with Normalizing Flows
Leonhard Helminger, Abdelaziz Djelouah, Markus Gross +1
Deep learning based image compression has recently witnessed exciting progress and in some cases even managed to surpass transform coding based approaches that have been establishe…
Content Adaptive Optimization for Neural Image Compression
Joaquim Campos, Simon Meierhans, Abdelaziz Djelouah +1
The field of neural image compression has witnessed exciting progress as recently proposed architectures already surpass the established transform coding based approaches. While, s…
Deep Video Color Propagation
Simone Meyer, Victor Cornillère, Abdelaziz Djelouah +2
Traditional approaches for color propagation in videos rely on some form of matching between consecutive video frames. Using appearance descriptors, colors are then propagated both…
On Regularized Losses for Weakly-supervised CNN Segmentation
Meng Tang, Federico Perazzi, Abdelaziz Djelouah +3
Minimization of regularized losses is a principled approach to weak supervision well-established in deep learning, in general. However, it is largely overlooked in semantic segment…
Normalized Cut Loss for Weakly-supervised CNN Segmentation
Meng Tang, Abdelaziz Djelouah, Federico Perazzi +2
Most recent semantic segmentation methods train deep convolutional neural networks with fully annotated masks requiring pixel-accuracy for good quality training. Common weakly-supe…
PhaseNet for Video Frame Interpolation
Simone Meyer, Abdelaziz Djelouah, Brian McWilliams +3
Most approaches for video frame interpolation require accurate dense correspondences to synthesize an in-between frame. Therefore, they do not perform well in challenging scenarios…