# Depth-SIMS: Semi-Parametric Image and Depth Synthesis

Source: [Depth-SIMS: Semi-Parametric Image and Depth Synthesis](<https://www.sota2.com/research/paper/68fa6cb81e209131cea35959>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:17:38.470Z

Authors: Valentina Musat, Daniele De Martini, Matthew Gadd, Paul Newman

Published: 2022-03-07T13:58:32.000Z

## Abstract

In this paper we present a compositing image synthesis method that generates RGB canvases with well aligned segmentation maps and sparse depth maps, coupled with an in-painting network that transforms the RGB canvases into high quality RGB images and the sparse depth maps into pixel-wise dense depth maps. We benchmark our method in terms of structural alignment and image quality, showing an increase in mIoU over SOTA by 3.7 percentage points and a highly competitive FID. Furthermore, we analyse the quality of the generated data as training data for semantic segmentation and depth completion, and show that our approach is more suited for this purpose than other methods.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2203.03405>)

[PDF](<https://arxiv.org/pdf/2203.03405.pdf>)