Papers › M-FUSE: Multi-frame Fusion for Scene Flow Estimation

M-FUSE: Multi-frame Fusion for Scene Flow Estimation

12 Jul 2022arXiv:2207.05704archive 2025-07-28

Lukas Mehl, Azin Jahedi, Jenny Schmalfuss, Andrés Bruhn

Recently, neural network for scene flow estimation show impressive results on automotive data such as the KITTI benchmark. However, despite of using sophisticated rigidity assumptions and parametrizations, such networks are typically limited to only two frame pairs which does not allow them to exploit temporal information. In our paper we address this shortcoming by proposing a novel multi-frame approach that considers an additional preceding stereo pair. To this end, we proceed in two steps: Firstly, building upon the recent RAFT-3D approach, we develop an improved two-frame baseline by incorporating an advanced stereo method. Secondly, and even more importantly, exploiting the specific modeling concepts of RAFT-3D, we propose a U-Net architecture that performs a fusion of forward and backward flow estimates and hence allows to integrate temporal information on demand. Experiments on the KITTI benchmark do not only show that the advantages of the improved baseline and the temporal fusion approach complement each other, they also demonstrate that the computed scene flow is highly accurate. More precisely, our approach ranks second overall and first for the even more challenging foreground objects, in total outperforming the original RAFT-3D method by more than 16%. Code is available at https://github.com/cv-stuttgart/M-FUSE.

PaperPDFCode

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

Code

cv-stuttgart/m-fuse 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

Scene Flow Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Flow Estimation Spring M-FUSE (F) 1px total 34.896 #1 of 6 Archive leaderboard report
Scene Flow Estimation Spring M-FUSE (K) 1px total 62.490 #4 of 6 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.

Methods

Concatenated Skip ConnectionConvolutionMax PoolingReLUU-Net

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