# Matisse: Evidence-Space Reasoning for Active 3D Reconstruction

arXiv: https://arxiv.org/abs/2609.38746 · HTML: https://mlsanity.com/paper/2609.38746/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 40 of its 52 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Builds on (most cited first, 30 of 40)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items](https://mlsanity.com/paper/2204.11918/) (2022)
- [MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation](https://mlsanity.com/paper/2302.08113/) (2023)
- [MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction](https://mlsanity.com/paper/2206.00665/) (2022)
- [SAM 3D: 3Dfy Anything in Images](https://mlsanity.com/paper/2511.16624/) (2025)
- [Native and Compact Structured Latents for 3D Generation](https://mlsanity.com/paper/2512.14692/) (2025)
- [ActiveNeRF: Learning where to See with Uncertainty Estimation](https://mlsanity.com/paper/2209.08546/) (2022)
- [latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction](https://mlsanity.com/paper/2403.16292/) (2024)
- [Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision](https://mlsanity.com/paper/2306.11719/) (2023)
- [Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fields](https://mlsanity.com/paper/2209.08409/) (2022)
- [FUEL: Fast UAV Exploration using Incremental Frontier Structure and Hierarchical Planning](https://mlsanity.com/paper/2010.11561/) (2020)
- [An Efficient Sampling-based Method for Online Informative Path Planning in Unknown Environments](https://mlsanity.com/paper/1909.09548/) (2019)
- [BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference](https://mlsanity.com/paper/2310.11142/) (2023)
- [ActiveGS: Active Scene Reconstruction Using Gaussian Splatting](https://mlsanity.com/paper/2412.17769/) (2024)
- [Conffusion: Confidence Intervals for Diffusion Models](https://mlsanity.com/paper/2211.09795/) (2022)
- [ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splatting](https://mlsanity.com/paper/2410.21955/) (2024)
- [Active Neural Mapping](https://mlsanity.com/paper/2308.16246/) (2023)
- [NARUTO: Neural Active Reconstruction from Uncertain Target Observations](https://mlsanity.com/paper/2402.18771/) (2024)
- [VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction](https://mlsanity.com/paper/2601.19887/) (2026)
- [Neural Visibility Field for Uncertainty-Driven Active Mapping](https://mlsanity.com/paper/2406.06948/) (2024)
- [Generative Uncertainty in Diffusion Models](https://mlsanity.com/paper/2502.20946/) (2025)
- [Shedding Light on Large Generative Networks: Estimating Epistemic Uncertainty in Diffusion Models](https://mlsanity.com/paper/2406.18580/) (2024)
- [MACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervision](https://mlsanity.com/paper/2303.03315/) (2023)
- [ActiveGAMER: Active GAussian Mapping through Efficient Rendering](https://mlsanity.com/paper/2501.06897/) (2025)
- [MV-SAM3D: Adaptive Multi-View Fusion for Layout-Aware 3D Generation](https://mlsanity.com/paper/2603.11633/) (2026)
- [SCONE: Surface Coverage Optimization in Unknown Environments by Volumetric Integration](https://mlsanity.com/paper/2208.10449/) (2022)
- [GauSS-MI: Gaussian Splatting Shannon Mutual Information for Active 3D Reconstruction](https://mlsanity.com/paper/2504.21067/) (2025)

## Abstract (arXiv)

How can a 3D reconstruction system acquire and retain useful information to understand the geometry of a scene from partial views under a limited computation budget? Existing active view acquisition methods typically estimate uncertainty over observed or instantiated geometry, limiting their ability to reason about unseen structure, while long-horizon reconstruction methods often retain redundant observations. We introduce Matisse, a training-free framework that unifies active reconstruction and keyframe selection by leveraging evidence provided by a pretrained generative 3D model. Matisse estimates Evidential Uncertainty from cross-attention evidence associated with 3D latent tokens and derives an Evidential Information Gain to guide both view acquisition and keyframe selection based on the expected reduction in posterior entropy. Matisse supports multi-object scenes through occlusion-aware, object-balanced aggregation and propagates uncertainty through intermediate latents to avoid full reconstruction during planning. Matisse reduces Chamfer distance by 12.7%, 3.8%, and 9.2% on GSO30, YCB-V, and Replica, respectively, relative to the best baseline on each dataset, and achieves a 1.50× end-to-end speedup over the best active reconstruction baseline on GSO30 with the same reconstruction backend. In the GSO30 keyframe selection experiment for long-horizon reconstruction, Matisse achieves comparable Chamfer distance using 14% of the input views compared with Stream3D.