# Learning Stable Canonical Worlds for Novel View Synthesis and Beyond

arXiv: https://arxiv.org/abs/2606.23027 · HTML: https://mlsanity.com/paper/2606.23027/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 49 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Builds on (most cited first, 30 of 37)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images](https://mlsanity.com/paper/2403.14627/) (2024)
- [DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision](https://mlsanity.com/paper/2312.16256/) (2023)
- [Splatter Image: Ultra-Fast Single-View 3D Reconstruction](https://mlsanity.com/paper/2312.13150/) (2023)
- [DepthSplat: Connecting Gaussian Splatting and Depth](https://mlsanity.com/paper/2410.13862/) (2024)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images](https://mlsanity.com/paper/2410.24207/) (2024)
- [Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image](https://mlsanity.com/paper/2012.09855/) (2020)
- [AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views](https://mlsanity.com/paper/2505.23716/) (2025)
- [COLMAP-Free 3D Gaussian Splatting](https://mlsanity.com/paper/2312.07504/) (2023)
- [FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views](https://mlsanity.com/paper/2502.12138/) (2025)
- [Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness](https://mlsanity.com/paper/1911.12012/) (2019)
- [latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction](https://mlsanity.com/paper/2403.16292/) (2024)
- [GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering](https://mlsanity.com/paper/2402.10128/) (2024)
- [FreeSplat: Generalizable 3D Gaussian Splatting Towards Free-View Synthesis of Indoor Scenes](https://mlsanity.com/paper/2405.17958/) (2024)
- [VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction](https://mlsanity.com/paper/2509.19297/) (2025)
- [NeuralFusion: Online Depth Fusion in Latent Space](https://mlsanity.com/paper/2011.14791/) (2020)
- [SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting](https://mlsanity.com/paper/2411.17190/) (2024)
- [No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views](https://mlsanity.com/paper/2508.01171/) (2025)
- [YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting](https://mlsanity.com/paper/2511.07321/) (2025)
- [ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS](https://mlsanity.com/paper/2505.23734/) (2025)
- [EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis](https://mlsanity.com/paper/2503.20168/) (2025)

## Abstract (arXiv)

Feed-forward Gaussian splatting (FFGS) facilitates real-time novel view synthesis, yet current methods often remain tied to view-dependent predictions. As more input views are added, they may accumulate noisy or redundant evidence instead of converging to a stable scene representation. In this paper, we introduce CanonicalGS, a feed-forward pipeline that maps cluttered multi-view observations into a stable, scene-centric representation. CanonicalGS first extracts view-centric evidence from depth, semantic features, and uncertainty estimates, and then aggregates this evidence in a canonical latent world using uncertainty-aware fusion. By emphasizing reliable observations while suppressing uncertain or redundant ones, CanonicalGS produces representations that scale more effectively for novel view synthesis and transfer to downstream visual perception tasks. Experiments show up to a 2.5 dB improvement in peak signal-to-noise ratio for synthesizing novel views and an 11% gain in semantic segmentation accuracy.