# PoseCrafter: Extreme Pose Estimation with Hybrid Video Synthesis

arXiv: https://arxiv.org/abs/2510.19527 · HTML: https://mlsanity.com/paper/2510.19527/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 39 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Builds on (most cited first, 29 of 29)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision](https://mlsanity.com/paper/2312.16256/) (2023)
- [MoCoGAN: Decomposing Motion and Content for Video Generation](https://mlsanity.com/paper/1707.04993/) (2017)
- [DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors](https://mlsanity.com/paper/2310.12190/) (2023)
- [ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis](https://mlsanity.com/paper/2409.02048/) (2024)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2](https://mlsanity.com/paper/2112.14683/) (2021)
- [Temporal Generative Adversarial Nets with Singular Value Clipping](https://mlsanity.com/paper/1611.06624/) (2016)
- [Patch2Pix: Epipolar-Guided Pixel-Level Correspondences](https://mlsanity.com/paper/2012.01909/) (2020)
- [Video Pixel Networks](https://mlsanity.com/paper/1610.00527/) (2016)
- [Latent Video Transformer](https://mlsanity.com/paper/2006.10704/) (2020)
- [RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild](https://mlsanity.com/paper/2208.05963/) (2022)
- [ToonCrafter: Generative Cartoon Interpolation](https://mlsanity.com/paper/2405.17933/) (2024)
- [SparsePose: Sparse-View Camera Pose Regression and Refinement](https://mlsanity.com/paper/2211.16991/) (2022)
- [NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations](https://mlsanity.com/paper/2306.09109/) (2023)
- [Extreme Rotation Estimation using Dense Correlation Volumes](https://mlsanity.com/paper/2104.13530/) (2021)
- [Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion](https://mlsanity.com/paper/1901.00063/) (2018)
- [PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization](https://mlsanity.com/paper/1505.07427/) (2015)
- [Can Generative Video Models Help Pose Estimation?](https://mlsanity.com/paper/2412.16155/) (2024)
- [Extreme Rotation Estimation in the Wild](https://mlsanity.com/paper/2411.07096/) (2024)

## Built on by (most cited first, 1 of 1)

- [Emergent Extreme-View Geometry in 3D Foundation Models](https://mlsanity.com/paper/2511.22686/) (2025)

## Abstract (arXiv)

Pairwise camera pose estimation from sparsely overlapping image pairs remains a critical and unsolved challenge in 3D vision. Most existing methods struggle with image pairs that have small or no overlap. Recent approaches attempt to address this by synthesizing intermediate frames using video interpolation and selecting key frames via a self-consistency score. However, the generated frames are often blurry due to small overlap inputs, and the selection strategies are slow and not explicitly aligned with pose estimation. To solve these cases, we propose Hybrid Video Generation (HVG) to synthesize clearer intermediate frames by coupling a video interpolation model with a pose-conditioned novel view synthesis model, where we also propose a Feature Matching Selector (FMS) based on feature correspondence to select intermediate frames appropriate for pose estimation from the synthesized results. Extensive experiments on Cambridge Landmarks, ScanNet, DL3DV-10K, and NAVI demonstrate that, compared to existing SOTA methods, PoseCrafter can obviously enhance the pose estimation performances, especially on examples with small or no overlap.