AJAHR: Amputated Joint Aware 3D Human Mesh Recovery
Not on the map. Why?
Abstract (arXiv)
Existing human mesh recovery methods assume a standard human body structure, overlooking diverse anatomical conditions such as limb loss. This assumption introduces bias when applied to individuals with amputations - a limitation further exacerbated by the scarcity of suitable datasets. To address this gap, we propose Amputated Joint Aware 3D Human Mesh Recovery (AJAHR), which is an adaptive pose estimation framework that improves mesh reconstruction for individuals with limb loss. Our model integrates a body-part amputation classifier, jointly trained with the mesh recovery network, to detect potential amputations. We also introduce Amputee 3D (A3D), which is a synthetic dataset offering a wide range of amputee poses for robust training. While maintaining competitive performance on non-amputees, our approach achieves state-of-the-art results for amputated individuals. Additional materials can be found at the project webpage.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 37 of its 57 references that are in the map. First posted on arXiv 24 Sep 2025.
Builds on
37 of 57 references.
References · 37
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2023GPT-4 Technical Reportcited by 18,132
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 2023Segment Anythingcited by 8,158
- 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
- 2017Neural Discrete Representation Learningcited by 4,650
- 2016Gaussian Error Linear Units (GELUs)cited by 3,431
- 2018CBAM: Convolutional Block Attention Modulecited by 2,463
- 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
25 more
- 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
- 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
- 2017End-to-end Recovery of Human Shape and Posecited by 883
- 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 730
- 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
- 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
- 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 577
- 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
- 2017AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actionscited by 449
- 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 344
- 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
- 2018Learning 3D Human Dynamics from Videocited by 315
- 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 283
- 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
- 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 229
- 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
- 20233D Human Pose Estimation via Intuitive Physicscited by 100
- 2017Self-supervised Learning of Motion Capturecited by 97
- 2023EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wildcited by 95
- 2024TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representationcited by 93
- 2024Score-Guided Diffusion for 3D Human Recoverycited by 39
- 20233D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimationcited by 28
- 2023Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial Sports Field Registrationcited by 13
- 2024WheelPose: Data Synthesis Techniques to Improve Pose Estimation Performance on Wheelchair Userscited by 5
- 2023Diffusion Models Enable Zero-Shot Pose Estimation for Lower-Limb Prosthetic Userscited by 1
Built on by
Citing papers per year: 2026: 3.
3 papers.
- 2026ResiHMR: Residual-Limb Aware Single-Image 3D Human Mesh Recovery for Individuals with Limb Losscited by 0
- 2026Toward Inclusive Avatar Design with Limb Differences Through Artificial Intelligencecited by 0
- 2026Prosthesis-Aware 3D Human Pose Estimation: A Dataset and Benchmark for RSP Userscited by 0
- 2026Prosthesis-Aware 3D Human Pose Estimation: A Dataset and Benchmark for RSP Users16 Sep 2026
- 2026Toward Inclusive Avatar Design with Limb Differences Through Artificial Intelligence13 Jul 2026
- 2026ResiHMR: Residual-Limb Aware Single-Image 3D Human Mesh Recovery for Individuals with Limb Loss30 Apr 2026