Papers › D2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos
D2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos
Christian Schmidt, Ali Athar, Sabarinath Mahadevan, Bastian Leibe
Despite receiving significant attention from the research community, the task of segmenting and tracking objects in monocular videos still has much room for improvement. Existing works have simultaneously justified the efficacy of dilated and deformable convolutions for various image-level segmentation tasks. This gives reason to believe that 3D extensions of such convolutions should also yield performance improvements for video-level segmentation tasks. However, this aspect has not yet been explored thoroughly in existing literature. In this paper, we propose Dynamic Dilated Convolutions (D2Conv3D): a novel type of convolution which draws inspiration from dilated and deformable convolutions and extends them to the 3D (spatio-temporal) domain. We experimentally show that D2Conv3D can be used to improve the performance of multiple 3D CNN architectures across multiple video segmentation related benchmarks by simply employing D2Conv3D as a drop-in replacement for standard convolutions. We further show that D2Conv3D out-performs trivial extensions of existing dilated and deformable convolutions to 3D. Lastly, we set a new state-of-the-art on the DAVIS 2016 Unsupervised Video Object Segmentation benchmark. Code is made publicly available at https://github.com/Schmiddo/d2conv3d.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Unsupervised Video Object Segmentation | DAVIS 2016 val | D2Conv3D | F | 86.5 | #8 of 25 | Archive leaderboard | report |
| Unsupervised Video Object Segmentation | DAVIS 2016 val | D2Conv3D | G | 86.0 | #8 of 25 | Archive leaderboard | report |
| Unsupervised Video Object Segmentation | DAVIS 2016 val | D2Conv3D | J | 85.5 | #8 of 25 | Archive leaderboard | report |
| Video Instance Segmentation | OVIS validation | D2Conv3D (ResNet-50) | AP50 | 33.8 | #42 of 44 | Archive leaderboard | report |
| Video Instance Segmentation | OVIS validation | D2Conv3D (ResNet-50) | AP75 | 13.7 | #42 of 44 | Archive leaderboard | report |
| Video Instance Segmentation | OVIS validation | D2Conv3D (ResNet-50) | mask AP | 15.2 | #42 of 44 | 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
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