# latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction

arXiv: https://arxiv.org/abs/2403.16292 · HTML: https://mlsanity.com/paper/2403.16292/

## Key facts

- Cited by 118 papers in the map (data through 14 Oct 2026).
- Builds on 74 of its 82 references that are in the map.
- First posted on arXiv 24 Mar 2024.

## Builds on (most cited first, 30 of 74)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [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)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [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)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [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)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (2021)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2012.00926/) (2020)
- [Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision](https://mlsanity.com/paper/1912.07372/) (2019)
- [GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2007.02442/) (2020)
- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction](https://mlsanity.com/paper/2109.00512/) (2021)
- [SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering](https://mlsanity.com/paper/2311.12775/) (2023)

## Built on by (most cited first, 30 of 118)

- [DepthSplat: Connecting Gaussian Splatting and Depth](https://mlsanity.com/paper/2410.13862/) (2024)
- [Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs](https://mlsanity.com/paper/2408.13912/) (2024)
- [ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model](https://mlsanity.com/paper/2408.16767/) (2024)
- [MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds](https://mlsanity.com/paper/2412.06974/) (2024)
- [Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image](https://mlsanity.com/paper/2406.04343/) (2024)
- [MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views](https://mlsanity.com/paper/2411.04924/) (2024)
- [MEt3R: Measuring Multi-View Consistency in Generated Images](https://mlsanity.com/paper/2501.06336/) (2025)
- [FreeSplat: Generalizable 3D Gaussian Splatting Towards Free-View Synthesis of Indoor Scenes](https://mlsanity.com/paper/2405.17958/) (2024)
- [TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers](https://mlsanity.com/paper/2408.13770/) (2024)
- [FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent](https://mlsanity.com/paper/2404.15259/) (2024)
- [Bolt3D: Generating 3D Scenes in Seconds](https://mlsanity.com/paper/2503.14445/) (2025)
- [HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction](https://mlsanity.com/paper/2410.06245/) (2024)
- [STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes](https://mlsanity.com/paper/2501.00602/) (2024)
- [Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images](https://mlsanity.com/paper/2503.13439/) (2025)
- [GGHead: Fast and Generalizable 3D Gaussian Heads](https://mlsanity.com/paper/2406.09377/) (2024)
- [PhysMotion: Physics-Grounded Dynamics From a Single Image](https://mlsanity.com/paper/2411.17189/) (2024)
- [L3DG: Latent 3D Gaussian Diffusion](https://mlsanity.com/paper/2410.13530/) (2024)
- [FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction](https://mlsanity.com/paper/2412.09573/) (2024)
- [SeaSplat: Representing Underwater Scenes with 3D Gaussian Splatting and a Physically Grounded Image Formation Model](https://mlsanity.com/paper/2409.17345/) (2024)
- [Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation](https://mlsanity.com/paper/2412.21117/) (2024)
- [Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction](https://mlsanity.com/paper/2601.04090/) (2026)
- [Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey](https://mlsanity.com/paper/2507.14501/) (2025)
- [StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generation](https://mlsanity.com/paper/2501.05763/) (2025)
- [LM-Gaussian: Boost Sparse-view 3D Gaussian Splatting with Large Model Priors](https://mlsanity.com/paper/2409.03456/) (2024)
- [DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness](https://mlsanity.com/paper/2503.22677/) (2025)
- [PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splatting](https://mlsanity.com/paper/2412.12096/) (2024)
- [MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data](https://mlsanity.com/paper/2412.14166/) (2024)
- [CamCtrl3D: Single-Image Scene Exploration with Precise 3D Camera Control](https://mlsanity.com/paper/2501.06006/) (2025)
- [EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis](https://mlsanity.com/paper/2503.20168/) (2025)
- [MVGS: Multi-view Regulated Gaussian Splatting for Novel View Synthesis](https://mlsanity.com/paper/2410.02103/) (2024)

## Abstract (arXiv)

We present latentSplat, a method to predict semantic Gaussians in a 3D latent space that can be splatted and decoded by a light-weight generative 2D architecture. Existing methods for generalizable 3D reconstruction either do not scale to large scenes and resolutions, or are limited to interpolation of close input views. latentSplat combines the strengths of regression-based and generative approaches while being trained purely on readily available real video data. The core of our method are variational 3D Gaussians, a representation that efficiently encodes varying uncertainty within a latent space consisting of 3D feature Gaussians. From these Gaussians, specific instances can be sampled and rendered via efficient splatting and a fast, generative decoder. We show that latentSplat outperforms previous works in reconstruction quality and generalization, while being fast and scalable to high-resolution data.