# Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation

arXiv: https://arxiv.org/abs/2605.03359 · HTML: https://mlsanity.com/paper/2605.03359/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 68 of its 89 references that are in the map.
- First posted on arXiv 5 May 2026.

## Builds on (most cited first, 30 of 68)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [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)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [Diffusion Probabilistic Models for 3D Point Cloud Generation](https://mlsanity.com/paper/2103.01458/) (2021)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items](https://mlsanity.com/paper/2204.11918/) (2022)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation](https://mlsanity.com/paper/2302.08113/) (2023)
- [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020)
- [3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models](https://mlsanity.com/paper/2301.11445/) (2023)
- [CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets](https://mlsanity.com/paper/2406.13897/) (2024)
- [GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images](https://mlsanity.com/paper/2209.11163/) (2022)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models](https://mlsanity.com/paper/2404.07191/) (2024)
- [ABO: Dataset and Benchmarks for Real-World 3D Object Understanding](https://mlsanity.com/paper/2110.06199/) (2021)
- [OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation](https://mlsanity.com/paper/2301.07525/) (2023)
- [MapAnything: Universal Feed-Forward Metric 3D Reconstruction](https://mlsanity.com/paper/2509.13414/) (2025)
- [Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion](https://mlsanity.com/paper/2212.06135/) (2022)
- [ICON: Implicit Clothed humans Obtained from Normals](https://mlsanity.com/paper/2112.09127/) (2021)
- [3D Neural Field Generation using Triplane Diffusion](https://mlsanity.com/paper/2211.16677/) (2022)

## Built on by (most cited first, 4 of 4)

- [X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras](https://mlsanity.com/paper/2607.12993/) (2026)
- [ReconPlusGen: Injecting Reconstruction Prior into Multi-view 3D Generation through Noise Inversion and Modulation](https://mlsanity.com/paper/2609.11129/) (2026)
- [SPOON: Towards Coherent Compositional 3D Scene Generation from Uncalibrated Multi-view Images](https://mlsanity.com/paper/2609.39590/) (2026)
- [UniForge3D: Joint 3D Reconstruction and Generation in a Shared Anchor-Guided Space](https://mlsanity.com/paper/2610.15357/) (2026)

## Abstract (arXiv)

Recent trends in sparse-view 3D reconstruction have taken two different paths: feed-forward reconstruction that predicts pixel-aligned point maps without a complete geometry, and generative 3D reconstruction that generates complete geometry but often with poor input-alignment. We present Mix3R, a novel generative 3D reconstruction method which mixes feed-forward reconstruction and 3D generation into a single framework in an aligned manner. Mix3R generates a 3D shape in two stages: a sparse voxel generation stage and a textured geometry generation stage. Unlike pure generative methods, our first-stage generation jointly produces a coarse 3D structure (sparse voxels), per-view point maps and camera parameters aligned to that 3D structure. This is made possible by introducing a Mixture-of-Transformers architecture that inserts global self-attentions to a feed-forward reconstruction model and a 3D generative model, both pretrained on large-scale data. This design effectively retains the pretrained priors but enables better 2D-3D alignment. Based on the initial aligned generations of sparse 3D voxels and point maps, we compute an overlap-based attention bias that is directly added to another pretrained textured geometry generation model, enabling it to correctly place input textures onto generated shapes in a training-free manner. Our design brings mutual benefits to both feed-forward reconstruction and 3D generation: The feed-forward branch learns to ground its predictions to a generative 3D prior, and conversely, the 3D generation branch is conditioned on geometrically informative features from the feed-forward branch. As a result, our method produces 3D shapes with better input alignment compared with pure 3D generative methods, together with camera pose estimations more accurate than previous feed-forward reconstruction methods. Our project page is at https://jsnln.github.io/mix3r/