# GLoD-LVSM: Learning Geometry-Grounded Continuous-LoD Scene Representations for Large View Synthesis Models

arXiv: https://arxiv.org/abs/2610.20254 · HTML: https://mlsanity.com/paper/2610.20254/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Builds on (most cited first, 20 of 20)

- [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)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (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)
- [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023)
- [DepthSplat: Connecting Gaussian Splatting and Depth](https://mlsanity.com/paper/2410.13862/) (2024)
- [Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations](https://mlsanity.com/paper/2111.13152/) (2021)
- [Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians](https://mlsanity.com/paper/2403.14166/) (2024)
- [LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias](https://mlsanity.com/paper/2410.17242/) (2024)
- [MetaSapiens: Real-Time Neural Rendering with Efficiency-Aware Pruning and Accelerated Foveated Rendering](https://mlsanity.com/paper/2407.00435/) (2024)
- [RayRoPE: Projective Ray Positional Encoding for Multi-view Attention](https://mlsanity.com/paper/2601.15275/) (2026)
- [Scaling View Synthesis Transformers](https://mlsanity.com/paper/2602.21341/) (2026)
- [LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis](https://mlsanity.com/paper/2603.20176/) (2026)
- [LearnPruner: Rethinking Attention-based Token Pruning in Vision Language Models](https://mlsanity.com/paper/2604.23950/) (2026)
- [CLoD-GS: Continuous Level-of-Detail via 3D Gaussian Splatting](https://mlsanity.com/paper/2510.09997/) (2025)
- [CLiFT: Compressive Light-Field Tokens for Compute-Efficient and Adaptive Neural Rendering](https://mlsanity.com/paper/2507.08776/) (2025)
- [DVSM: Decoder-only View Synthesis Model Done Right](https://mlsanity.com/paper/2605.29891/) (2026)

## Abstract (arXiv)

Large view synthesis models (LVSMs) reconstruct scenes from sparse views and render novel views quickly, but they incur unnecessary storage and rendering costs due to token redundancy. We present GLoD-LVSM, a compact, geometry-grounded scene representation for LVSMs with continuous levels of detail. First, instead of learning a fixed set of scene anchor initializations, GLoD-LVSM learns a continuous field that initializes a flexible number of anchors to match the desired budget. A condenser then aggregates scene information into these anchors, with both the field and condenser trained end-to-end. Second, the condenser infers reference-token and anchor geometry to guide compression through geometry-grounded attention, improving rendering quality and enabling frustum culling during decoding. Compared with existing LVSM scene-compression baselines, GLoD-LVSM achieves the best trade-off between rendering quality and scene token count. Compared with the uncompressed base model, GLoD-LVSM reduces the scene-token count by 33.4% and accelerates rendering by 1.23× with no quality loss. Under a relaxed quality-loss budget, the reduction increases to 85.5%, with 3.00× rendering speedup. Further analysis reveals that view-synthesis supervision yields emergent scene depth and self-organized anchors that align with surfaces and adapt their density to local texture complexity. Beyond rendering, we further show that our scene representation also supports scene-semantic understanding, highlighting its potential for broader downstream tasks.