Papers › GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction

GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction

19 Dec 2023arXiv:2312.11850archive 2025-07-28

Xinshun Wang, Qiongjie Cui, Chen Chen, Mengyuan Liu

The past few years has witnessed the dominance of Graph Convolutional Networks (GCNs) over human motion prediction.Various styles of graph convolutions have been proposed, with each one meticulously designed and incorporated into a carefully-crafted network architecture. This paper breaks the limits of existing knowledge by proposing Universal Graph Convolution (UniGC), a novel graph convolution concept that re-conceptualizes different graph convolutions as its special cases. Leveraging UniGC on network-level, we propose GCNext, a novel GCN-building paradigm that dynamically determines the best-fitting graph convolutions both sample-wise and layer-wise. GCNext offers multiple use cases, including training a new GCN from scratch or refining a preexisting GCN. Experiments on Human3.6M, AMASS, and 3DPW datasets show that, by incorporating unique module-to-network designs, GCNext yields up to 9x lower computational cost than existing GCN methods, on top of achieving state-of-the-art performance.

PaperPDFCode

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

Code

bradleywang0416/gcnext 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

Human Pose ForecastingHuman motion predictionUnitymotion prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Human Pose Forecasting 3DPW GCNext Average MPJPE (mm) 1000 msec 72.0 #3 of 7 Archive leaderboard report
Human Pose Forecasting AMASS GCNext Average MPJPE (mm) 1000 msec 65.3 #2 of 11 Archive leaderboard report
Human Pose Forecasting Human3.6M GCNext Average MPJPE (mm) @ 1000 ms 64.7 #1 of 33 Archive leaderboard report
Human Pose Forecasting Human3.6M GCNext Average MPJPE (mm) @ 400ms 30.5 #1 of 33 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

ConvolutionGCN

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