# Recurrent Transition Networks for Character Locomotion

arXiv: https://arxiv.org/abs/1810.02363 · HTML: https://mlsanity.com/paper/1810.02363/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2018.

## Built on by (most cited first, 30 of 52)

- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [Robust Motion In-betweening](https://mlsanity.com/paper/2102.04942/) (2021)
- [TEACH: Temporal Action Composition for 3D Humans](https://mlsanity.com/paper/2209.04066/) (2022)
- [ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech](https://mlsanity.com/paper/2209.07556/) (2022)
- [Flexible Motion In-betweening with Diffusion Models](https://mlsanity.com/paper/2405.11126/) (2024)
- [Single Motion Diffusion](https://mlsanity.com/paper/2302.05905/) (2023)
- [Single-Shot Motion Completion with Transformer](https://mlsanity.com/paper/2103.00776/) (2021)
- [MoDi: Unconditional Motion Synthesis from Diverse Data](https://mlsanity.com/paper/2206.08010/) (2022)
- [ParCo: Part-Coordinating Text-to-Motion Synthesis](https://mlsanity.com/paper/2403.18512/) (2024)
- [DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation](https://mlsanity.com/paper/2203.08713/) (2022)
- [Real-time Controllable Motion Transition for Characters](https://mlsanity.com/paper/2205.02540/) (2022)
- [Towards Open Domain Text-Driven Synthesis of Multi-Person Motions](https://mlsanity.com/paper/2405.18483/) (2024)
- [Plan, Posture and Go: Towards Open-World Text-to-Motion Generation](https://mlsanity.com/paper/2312.14828/) (2023)
- [Conditional Motion In-betweening](https://mlsanity.com/paper/2202.04307/) (2022)
- [PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision](https://mlsanity.com/paper/2203.15625/) (2022)
- [M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Models](https://mlsanity.com/paper/2407.14502/) (2024)
- [OmniMotionGPT: Animal Motion Generation with Limited Data](https://mlsanity.com/paper/2311.18303/) (2023)
- [RSMT: Real-time Stylized Motion Transition for Characters](https://mlsanity.com/paper/2306.11970/) (2023)
- [Style-ERD: Responsive and Coherent Online Motion Style Transfer](https://mlsanity.com/paper/2203.02574/) (2022)
- [Motion Inbetweening via Deep Delta-Interpolator](https://mlsanity.com/paper/2201.06701/) (2022)
- [Continuous Intermediate Token Learning with Implicit Motion Manifold for Keyframe Based Motion Interpolation](https://mlsanity.com/paper/2303.14926/) (2023)
- [Learning to Get Up](https://mlsanity.com/paper/2205.00307/) (2022)
- [SceneMI: Motion In-betweening for Modeling Human-Scene Interactions](https://mlsanity.com/paper/2503.16289/) (2025)
- [T2M-HiFiGPT: Generating High Quality Human Motion from Textual Descriptions with Residual Discrete Representations](https://mlsanity.com/paper/2312.10628/) (2023)
- [AAMDM: Accelerated Auto-regressive Motion Diffusion Model](https://mlsanity.com/paper/2401.06146/) (2023)
- [Motion Synthesis with Sparse and Flexible Keyjoint Control](https://mlsanity.com/paper/2503.15557/) (2025)
- [SemanticBoost: Elevating Motion Generation with Augmented Textual Cues](https://mlsanity.com/paper/2310.20323/) (2023)
- [A Dual-Masked Auto-Encoder for Robust Motion Capture with Spatial-Temporal Skeletal Token Completion](https://mlsanity.com/paper/2207.07381/) (2022)
- [StableMotion: Training Motion Cleanup Models with Unpaired Corrupted Data](https://mlsanity.com/paper/2505.03154/) (2025)

## Abstract (arXiv)

Manually authoring transition animations for a complete locomotion system can be a tedious and time-consuming task, especially for large games that allow complex and constrained locomotion movements, where the number of transitions grows exponentially with the number of states. In this paper, we present a novel approach, based on deep recurrent neural networks, to automatically generate such transitions given a past context of a few frames and a target character state to reach. We present the Recurrent Transition Network (RTN), based on a modified version of the Long-Short-Term-Memory (LSTM) network, designed specifically for transition generation and trained without any gait, phase, contact or action labels. We further propose a simple yet principled way to initialize the hidden states of the LSTM layer for a given sequence which improves the performance and generalization to new motions. We both quantitatively and qualitatively evaluate our system and show that making the network terrain-aware by adding a local terrain representation to the input yields better performance for rough-terrain navigation on long transitions. Our system produces realistic and fluid transitions that rival the quality of Motion Capture-based ground-truth motions, even before applying any inverse-kinematics postprocess. Direct benefits of our approach could be to accelerate the creation of transition variations for large coverage, or even to entirely replace transition nodes in an animation graph. We further explore applications of this model in a animation super-resolution setting where we temporally decompress animations saved at 1 frame per second and show that the network is able to reconstruct motions that are hard to distinguish from un-compressed locomotion sequences.