Papers › FreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier Convolutions

FreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier Convolutions

4 Oct 2022arXiv:2210.01595archive 2025-07-28

Bruno Berenguel-Baeta, Jesus Bermudez-Cameo, Jose J. Guerrero

In this work we present FreDSNet, a deep learning solution which obtains semantic 3D understanding of indoor environments from single panoramas. Omnidirectional images reveal task-specific advantages when addressing scene understanding problems due to the 360-degree contextual information about the entire environment they provide. However, the inherent characteristics of the omnidirectional images add additional problems to obtain an accurate detection and segmentation of objects or a good depth estimation. To overcome these problems, we exploit convolutions in the frequential domain obtaining a wider receptive field in each convolutional layer. These convolutions allow to leverage the whole context information from omnidirectional images. FreDSNet is the first network that jointly provides monocular depth estimation and semantic segmentation from a single panoramic image exploiting fast Fourier convolutions. Our experiments show that FreDSNet has similar performance as specific state of the art methods for semantic segmentation and depth estimation. FreDSNet code is publicly available in https://github.com/Sbrunoberenguel/FreDSNet

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

sbrunoberenguel/fredsnet officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Depth EstimationMonocular Depth EstimationScene UnderstandingSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Depth Estimation Stanford2D3D Panoramic FreDSNet RMSE 0.2727 #2 of 18 Archive leaderboard report
Depth Estimation Stanford2D3D Panoramic FreDSNet absolute relative error 0.0952 #2 of 18 Archive leaderboard report
Semantic Segmentation Stanford2D3D Panoramic FreDSNet mAcc 63.1 #18 of 25 Archive leaderboard report
Semantic Segmentation Stanford2D3D Panoramic FreDSNet mIoU 46.1% #18 of 25 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections