Research map / Video / Video generation
NeRM: Learning Neural Representations for High-Framerate Human Motion Synthesis
Dong Wei, Huaijiang Sun, Bin Li, Xiaoning Sun, Shengxiang Hu, Weiqing Li, Jianfeng Lu
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes NeRM, a neural-representation approach for synthesizing high-framerate human motion that handles varied-framerate training data without downsampling or discarding samples.
Problem
Generating realistic high-framerate human motion is hard because training data have varied framerates, high framerates cause heavy memory burden, and generative models sample slowly; prior methods downsample or discard data, losing information.
Approach
Learns neural representations of human motion so that generation can be done at arbitrary (high) framerate, instead of compromising by downsampling training data or discarding low-framerate samples.
Closest papers by meaning
- Implicit Neural Representations for Variable Length Human Motion Generation (ECCV 2022 · similarity 0.89)
- NeRMo: Learning Implicit Neural Representations for 3D Human Motion Prediction (ECCV 2024 · similarity 0.89)
- A Neural Temporal Model for Human Motion Prediction (CVPR 2019 · similarity 0.88)
- Move-in-2D: 2D-Conditioned Human Motion Generation (CVPR 2025 · similarity 0.87)
- AMD: Autoregressive Motion Diffusion (AAAI 2024 · similarity 0.87)
- Generative Pre-trained Autoregressive Diffusion Transformer (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
