# Direct Reward Fine-Tuning on Poses for Single Image to 3D Human in the Wild

arXiv: https://arxiv.org/abs/2603.02619 · HTML: https://mlsanity.com/paper/2603.02619/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 43 of its 49 references that are in the map.
- First posted on arXiv 3 Mar 2026.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 30 of 43)

- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020)
- [AI Choreographer: Music Conditioned 3D Dance Generation with AIST++](https://mlsanity.com/paper/2101.08779/) (2021)
- [DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16381/) (2023)
- [Directly Fine-Tuning Diffusion Models on Differentiable Rewards](https://mlsanity.com/paper/2309.17400/) (2023)
- [Aligning Text-to-Image Models using Human Feedback](https://mlsanity.com/paper/2302.12192/) (2023)
- [Aligning Text-to-Image Diffusion Models with Reward Backpropagation](https://mlsanity.com/paper/2310.03739/) (2023)
- [Human Preference Score: Better Aligning Text-to-Image Models with Human Preference](https://mlsanity.com/paper/2303.14420/) (2023)
- [ICON: Implicit Clothed humans Obtained from Normals](https://mlsanity.com/paper/2112.09127/) (2021)
- [ARCH: Animatable Reconstruction of Clothed Humans](https://mlsanity.com/paper/2004.04572/) (2020)
- [PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop](https://mlsanity.com/paper/2103.16507/) (2021)
- [Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors](https://mlsanity.com/paper/2105.01859/) (2021)
- [Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset](https://mlsanity.com/paper/2307.00818/) (2023)
- [Monocular, One-stage, Regression of Multiple 3D People](https://mlsanity.com/paper/2008.12272/) (2020)
- [ECON: Explicit Clothed humans Optimized via Normal integration](https://mlsanity.com/paper/2212.07422/) (2022)
- [ARCH++: Animation-Ready Clothed Human Reconstruction Revisited](https://mlsanity.com/paper/2108.07845/) (2021)
- [PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images](https://mlsanity.com/paper/2207.06400/) (2022)
- [Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing](https://mlsanity.com/paper/2204.08906/) (2022)
- [TeCH: Text-guided Reconstruction of Lifelike Clothed Humans](https://mlsanity.com/paper/2308.08545/) (2023)
- [Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention](https://mlsanity.com/paper/2405.11616/) (2024)
- [SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction](https://mlsanity.com/paper/2312.06704/) (2023)
- [SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion](https://mlsanity.com/paper/2311.15855/) (2023)

## Abstract (arXiv)

Single-view 3D human reconstruction has achieved remarkable progress through the adoption of multi-view diffusion models, yet the recovered 3D humans often exhibit unnatural poses. This phenomenon becomes pronounced when reconstructing 3D humans with dynamic or challenging poses, which we attribute to the limited scale of available 3D human datasets with diverse poses. To address this limitation, we introduce DrPose, Direct Reward fine-tuning algorithm on Poses, which enables post-training of a multi-view diffusion model on diverse poses without requiring expensive 3D human assets. DrPose trains a model using only human poses paired with single-view images, employing a direct reward fine-tuning to maximize PoseScore, which is our proposed differentiable reward that quantifies consistency between a generated multi-view latent image and a ground-truth human pose. This optimization is conducted on DrPose15K, a novel dataset that was constructed from an existing human motion dataset and a pose-conditioned video generative model. Constructed from abundant human pose sequence data, DrPose15K exhibits a broader pose distribution compared to existing 3D human datasets. We validate our approach through evaluation on conventional benchmark datasets, in-the-wild images, and a newly constructed benchmark, with a particular focus on assessing performance on challenging human poses. Our results demonstrate consistent qualitative and quantitative improvements across all benchmarks. Project page: https://seunguk-do.github.io/drpose.