Research map / 3D vision / Human pose estimation
CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models
Junho Kim, Hyungjin Chung, Byung-Hoon Kim
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add cumulative reasoning at inference with dynamic-round training (ablation) | CapeLLM · MP-100 | PCK@0.20: 96.05 -> 97.28 | Improved |
| add cumulative reasoning at inference with fixed-round training (ablation) | CapeLLM · MP-100 | PCK@0.20: 96.98 -> 94.59 | Hurt |
| use fixed-round training pairing every image with all keypoints instead of LocLLM-style training (ablation) | CapeLLM · MP-100 | mPCK: 84.00 -> 91.98 | Improved |
| use spatial and relational keypoint descriptions instead of vague ones (ablation) | CapeLLM · MP-100 | mPCK: 85.98 -> 91.98 | Improved |
| add keypoint descriptions to the instruction (ablation) | CapeLLM · MP-100 | mPCK: 89.86 -> 91.98 | Improved |
| add a list of all keypoint names to the instruction (ablation) | CapeLLM · MP-100 | mPCK: 91.98 -> 90.97 | Hurt |
| diversify question expressions in instructions (ablation) | CapeLLM · MP-100 | mPCK: 91.98 -> 90.56 | Hurt |
| add a conversation outline to instructions (ablation) | CapeLLM · MP-100 | mPCK: 91.98 -> 90.63 | Hurt |
| randomly replace descriptions during training when descriptions are removed at inference (ablation) | CapeLLM · MP-100 | mPCK: 85.69 -> 88.84 | Improved |
| use 4 keypoints per round instead of 2 (ablation) | CapeLLM · MP-100 | mPCK: 89.11 -> 91.98 | Improved |
| fine-tune with LoRA instead of keeping the model frozen (ablation) | CapeLLM · MP-100 | mPCK: 88.39 -> 91.98 | Improved |
| use full-parameter fine-tuning instead of LoRA (ablation) | CapeLLM · MP-100 | mPCK: 91.98 -> 38.59 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CapeX — CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation (ICLR 2025) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation (ICLR 2025 · similarity 0.92)
- ESCAPE: Encoding Super-keypoints for Category-Agnostic Pose Estimation (CVPR 2024 · similarity 0.89)
- Meta-Point Learning and Refining for Category-Agnostic Pose Estimation (CVPR 2024 · similarity 0.88)
- PoseLLaVA: Pose Centric Multimodal LLM for Fine-Grained 3D Pose Manipulation (AAAI 2025 · similarity 0.87)
- Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models (AAAI 2025 · similarity 0.86)
- ROSE: Rotate Your Large Language Model to See (CVPR 2026 · similarity 0.86)
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.
