# iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Views

arXiv: https://arxiv.org/abs/2312.17250 · HTML: https://mlsanity.com/paper/2312.17250/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 83 of its 96 references that are in the map.
- First posted on arXiv 28 Dec 2023.

## 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 83)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation](https://mlsanity.com/paper/2309.16653/) (2023)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [Diffusion Probabilistic Models for 3D Point Cloud Generation](https://mlsanity.com/paper/2103.01458/) (2021)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)

## Built on by (most cited first, 14 of 14)

- [SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views](https://mlsanity.com/paper/2408.10195/) (2024)
- [ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation](https://mlsanity.com/paper/2510.23306/) (2025)
- [NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images](https://mlsanity.com/paper/2412.03517/) (2024)
- [UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image](https://mlsanity.com/paper/2411.16106/) (2024)
- [Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis](https://mlsanity.com/paper/2412.03570/) (2024)
- [Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors](https://mlsanity.com/paper/2411.15966/) (2024)
- [Sparse-View 3D Reconstruction: Recent Advances and Open Challenges](https://mlsanity.com/paper/2507.16406/) (2025)
- [ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation](https://mlsanity.com/paper/2605.21121/) (2026)
- [LucidFusion: Reconstructing 3D Gaussians with Arbitrary Unposed Images](https://mlsanity.com/paper/2410.15636/) (2024)
- [Pragmatist: Multiview Conditional Diffusion Models for High-Fidelity 3D Reconstruction from Unposed Sparse Views](https://mlsanity.com/paper/2412.08412/) (2024)
- [DAV-GSWT: Diffusion-Active-View Sampling for Data-Efficient Gaussian Splatting Wang Tiles](https://mlsanity.com/paper/2602.15355/) (2026)
- [Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction](https://mlsanity.com/paper/2604.04874/) (2026)
- [Generalizable Single-view Object Pose Estimation by Two-side Generating and Matching](https://mlsanity.com/paper/2411.15860/) (2024)
- [Landscape-Awareness for Geometric View Diffusion Model](https://mlsanity.com/paper/2605.19865/) (2026)

## Abstract (arXiv)

We present iFusion, a novel 3D object reconstruction framework that requires only two views with unknown camera poses. While single-view reconstruction yields visually appealing results, it can deviate significantly from the actual object, especially on unseen sides. Additional views improve reconstruction fidelity but necessitate known camera poses. However, assuming the availability of pose may be unrealistic, and existing pose estimators fail in sparse view scenarios. To address this, we harness a pre-trained novel view synthesis diffusion model, which embeds implicit knowledge about the geometry and appearance of diverse objects. Our strategy unfolds in three steps: (1) We invert the diffusion model for camera pose estimation instead of synthesizing novel views. (2) The diffusion model is fine-tuned using provided views and estimated poses, turned into a novel view synthesizer tailored for the target object. (3) Leveraging registered views and the fine-tuned diffusion model, we reconstruct the 3D object. Experiments demonstrate strong performance in both pose estimation and novel view synthesis. Moreover, iFusion seamlessly integrates with various reconstruction methods and enhances them.