Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors
Wonbong Jang, Philippe Weinzaepfel, Vincent Leroy, Lourdes Agapito, Jérôme Revaud
2025Year
29Top-tier citations
Abstract
Figure 1. Qualitative comparison of raw 3D reconstructions between DUSt3R and Pow3R for the image pair on the left. DUSt3R cannot leverage auxiliary information potentially available at test time, resulting in noisy and low-resolution estimates, whereas Pow3R allows to inject such priors at test time in a versatile manner, enabling new capabilities such as high-resolution processing as a direct by-product.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers29
- Depth Anything 3: Recovering the Visual Space from Any ViewsHaotong Lin, Sili Chen, Jun Hao Liew, Donny Y. Chen et al.ICLR 2026 · 720 citations
- VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) ManifoldDominic Maggio, Hyungtae Lim, Luca CarloneNeurIPS 2025 · 176 citations
- WorldMirror: Universal 3D World Reconstruction with Any-Prior PromptingYifan Liu, Zhiyuan Min, Zhenwei Wang, Junta Wu et al.ICML 2026 · 58 citations
- Any4D: Unified Feed-Forward Metric 4D ReconstructionJay Karhade, Nikhil Varma Keetha, Yuchen Zhang, Tanisha Gupta et al.CVPR 2026 · 35 citations
- V-DPM: 4D Video Reconstruction with Dynamic Point MapsEdgar Sucar, Eldar Insafutdinov, Zihang Lai, Andrea VedaldiCVPR 2026 · 29 citations
Builds on31
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- Vision Transformers for Dense PredictionRené Ranftl, Alexey Bochkovskiy, Vladlen KoltunICCV 2021 · 2,647 citations
- Habitat: A Platform for Embodied AI ResearchManolis Savva, Jitendra Malik, Devi Parikh, Dhruv Batra et al.ICCV 2019 · 1,863 citations
Related papers
- VisFusion: Visibility-Aware Online 3D Scene Reconstruction from VideosHuiyu Gao, Wei Mao, Miaomiao LiuCVPR 2023
- Test3R: Learning to Reconstruct 3D at Test TimeYuheng Yuan, Qiuhong Shen, Shizun Wang, Xingyi Yang et al.NeurIPS 2025 · 19 citations
- Can Generative Video Models Help Pose Estimation?Ruojin Cai, Jason Y. Zhang, Philipp Henzler, Zhengqi Li et al.CVPR 2025
- DUSt3R: Geometric 3D Vision Made EasyShuzhe Wang, Vincent Leroy, Yohann Cabon, Boris Chidlovskii et al.CVPR 2024 · 302 citations
- Real3D: Towards Scaling Large Reconstruction Models with Real ImagesHanwen Jiang, Qixing Huang, Georgios PavlakosICCV 2025 · 3 citations
