Papers › Motion Inbetweening via Deep Δ-Interpolator

Motion Inbetweening via Deep Δ-Interpolator

18 Jan 2022arXiv:2201.06701archive 2025-07-28

Boris N. Oreshkin, Antonios Valkanas, Félix G. Harvey, Louis-Simon Ménard, Florent Bocquelet, Mark J. Coates

We show that the task of synthesizing human motion conditioned on a set of key frames can be solved more accurately and effectively if a deep learning based interpolator operates in the delta mode using the spherical linear interpolator as a baseline. We empirically demonstrate the strength of our approach on publicly available datasets achieving state-of-the-art performance. We further generalize these results by showing that the Δ-regime is viable with respect to the reference of the last known frame (also known as the zero-velocity model). This supports the more general conclusion that operating in the reference frame local to input frames is more accurate and robust than in the global (world) reference frame advocated in previous work. Our code is publicly available at https://github.com/boreshkinai/delta-interpolator.

PaperPDFCode

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

Code

boreshkinai/delta-interpolator officialmentioned in paperpytorch 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

Motion Synthesis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Motion Synthesis LaFAN1 $\Delta$-interpolator L2P@15 0.47 #1 of 4 Archive leaderboard report
Motion Synthesis LaFAN1 $\Delta$-interpolator L2P@30 1.00 #1 of 4 Archive leaderboard report
Motion Synthesis LaFAN1 $\Delta$-interpolator L2P@5 0.13 #1 of 4 Archive leaderboard report
Motion Synthesis LaFAN1 $\Delta$-interpolator L2Q@15 0.32 #1 of 4 Archive leaderboard report
Motion Synthesis LaFAN1 $\Delta$-interpolator L2Q@30 0.57 #1 of 4 Archive leaderboard report
Motion Synthesis LaFAN1 $\Delta$-interpolator L2Q@5 0.11 #1 of 4 Archive leaderboard report
Motion Synthesis LaFAN1 $\Delta$-interpolator NPSS@15 0.0217 #1 of 4 Archive leaderboard report
Motion Synthesis LaFAN1 $\Delta$-interpolator NPSS@30 0.1217 #1 of 4 Archive leaderboard report
Motion Synthesis LaFAN1 $\Delta$-interpolator NPSS@5 0.0014 #1 of 4 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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