@oliviscusAI: this tool can track perfect 3D motion. rtmlib is a lightweight pose estimation library covering full body, hands, face,…
Summary
rtmlib is a lightweight, open-source pose estimation library that supports full-body, hand, face, and animal pose tracking, built on rtmpose and vitpose models, with a built-in Gradio web UI.
View Cached Full Text
Cached at: 09/15/26, 01:34 AM
this tool can track perfect 3D motion.
rtmlib is a lightweight pose estimation library covering full body, hands, face, and 133-point wholebody tracking, built on rtmpose and vitpose models.
needs only numpy, opencv, and onnxruntime to run covers 30 named animal species alongside human pose includes a built-in gradio webui, one script to launch it runs on cpu, gpu, or openvino, models auto-download on first use
100% free. open source.
Similar Articles
TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking
TrackCraft3R repurposes video diffusion transformers for dense 3D tracking from monocular video, using dual-latent representation and temporal RoPE alignment to achieve state-of-the-art performance with 1.3x faster speed and 4.6x less peak memory than prior methods.
@simplifyinAI: A handful of well-known 3D human research projects, HumanNeRF, Neural Body, KeypointNeRF, all lean on the same open-sou…
EasyMocap is an open-source toolbox built by Zhejiang University that enables 3D human pose estimation from regular RGB videos, used by research projects like HumanNeRF, but with licensing considerations due to SMPL body models.
Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction
Scal3R improves online 3D reconstruction for long videos by using multi-reference relative pose querying with lightweight tokens and pose-graph optimization, reducing drift and achieving state-of-the-art performance.
MolmoMotion: Language-guided 3D motion forecasting
MolmoMotion is a new language-guided 3D motion forecasting model that predicts future 3D point trajectories from video frames and action descriptions, achieving stronger performance than existing methods. Alongside the model, a large dataset (MolmoMotion-1M) and a benchmark (PointMotionBench) are released.
DreamTraj: Generating 6-DoF Object Trajectories by Reading Unrendered Video Diffusion Latents
DreamTraj predicts 6-DoF object trajectories from a single RGB image and a language instruction by decoding internal video diffusion latents, eliminating the need for video, depth, or CAD models at inference. It introduces the MOVEdataset with fine-grained language-to-motion annotations and achieves state-of-the-art performance while running 4.6x faster than generate-then-extract pipelines.