activity
20182026
most citedLossy Image Compression with Normalizing Flows

22 citations · 47 across the 8 of their papers we have counts for

collaborators
Showing cs.CVShow all

17 papers · 1 filter

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2025

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…