cs.CVNov 2, 2026

Image Guided Depth Upsampling using Anisotropic Total Generalized Variation

Authors: David Ferstl, Christian Reinbacher, Rene Ranftl, Matthias Rüther, Horst Bischof

Organizations: Graz University of Technology, Institute for Computer Graphics and Vision, Inffeldgasse 16, 8010 Graz, AUSTRIA

Abstract

In this work we present a novel method for the challenging problem of depth image upsampling. Modern depth cameras such as Kinect or Time of Flight cameras deliver dense, high quality depth measurements but are limited in their lateral resolution. To overcome this limitation we formulate a convex optimization problem using higher order regularization for depth image upsampling. In this optimization an anisotropic diffusion tensor, calculated from a high resolution intensity image, is used to guide the upsampling. We derive a numerical algorithm based on a primaldual formulation that is efficiently parallelized and runs at multiple frames per second. We show that this novel upsampling clearly outperforms state of the art approaches in terms of speed and accuracy on the widely used Middlebury 2007 datasets. Furthermore, we introduce novel datasets with highly accurate groundtruth, which, for the first time, enable to benchmark depth upsampling methods using real sensor data.

Figures & tables

Explore similar work

CardsList
  1. Depth from Defocus via Direct Optimization

    Feb 18, 2026Holly Jackson, Caleb Adams, Ignacio Lopez-Francos +1alternating minimizationDepth Estimation

  2. Metric Depth Estimation from Arbitrarily Degraded Low-Resolution Depth Prompts

    Feb 10, 2026Kun Wang, Yun Zhu, Pan Zhou +1Depth EstimationMetric Depth Estimation

  3. Depth-to-Image Synthesis-Driven Generative Unguided Depth Completion

    Sep 5, 2026Jiayi Yuan, Na Zhao, De Wen SohDepth Completion