# CLiFT: Compressive Light-Field Tokens for Compute-Efficient and Adaptive Neural Rendering

arXiv: https://arxiv.org/abs/2507.08776 · HTML: https://mlsanity.com/paper/2507.08776/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 38 references that are in the map.
- First posted on arXiv 11 Jul 2025.

## Builds on (most cited first, 25 of 25)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [Wonder3D: Single Image to 3D using Cross-Domain Diffusion](https://mlsanity.com/paper/2310.15008/) (2023)
- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs](https://mlsanity.com/paper/2103.13744/) (2021)
- [SyncDreamer: Generating Multiview-consistent Images from a Single-view Image](https://mlsanity.com/paper/2309.03453/) (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)
- [FastNeRF: High-Fidelity Neural Rendering at 200FPS](https://mlsanity.com/paper/2103.10380/) (2021)
- [Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering](https://mlsanity.com/paper/2106.02634/) (2021)
- [ReconFusion: 3D Reconstruction with Diffusion Priors](https://mlsanity.com/paper/2312.02981/) (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)
- [LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias](https://mlsanity.com/paper/2410.17242/) (2024)
- [NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion](https://mlsanity.com/paper/2302.10109/) (2023)
- [Generalizable Patch-Based Neural Rendering](https://mlsanity.com/paper/2207.10662/) (2022)
- [Light Field Neural Rendering](https://mlsanity.com/paper/2112.09687/) (2021)
- [Learning to Render Novel Views from Wide-Baseline Stereo Pairs](https://mlsanity.com/paper/2304.08463/) (2023)
- [EscherNet: A Generative Model for Scalable View Synthesis](https://mlsanity.com/paper/2402.03908/) (2024)
- [MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction](https://mlsanity.com/paper/2402.12712/) (2024)
- [FreeVS: Generative View Synthesis on Free Driving Trajectory](https://mlsanity.com/paper/2410.18079/) (2024)
- [FreeSim: Toward Free-viewpoint Camera Simulation in Driving Scenes](https://mlsanity.com/paper/2412.03566/) (2024)
- [SlimmeRF: Slimmable Radiance Fields](https://mlsanity.com/paper/2312.10034/) (2023)

## Built on by (most cited first, 5 of 5)

- [Multi-view Pyramid Transformer: Look Coarser to See Broader](https://mlsanity.com/paper/2512.07806/) (2025)
- [DVSM: Decoder-only View Synthesis Model Done Right](https://mlsanity.com/paper/2605.29891/) (2026)
- [WorldRoPE: Probabilistic World-Centric Rotary Embedding for Multi-View Attention](https://mlsanity.com/paper/2610.16337/) (2026)
- [CoTL: Compact Token Learning for 3D Scene Representation](https://mlsanity.com/paper/2610.18446/) (2026)
- [GLoD-LVSM: Learning Geometry-Grounded Continuous-LoD Scene Representations for Large View Synthesis Models](https://mlsanity.com/paper/2610.20254/) (2026)

## Abstract (arXiv)

This paper proposes a neural rendering approach that represents a scene as "compressed light-field tokens (CLiFTs)", retaining rich appearance and geometric information of a scene. CLiFT enables compute-efficient rendering by compressed tokens, while being capable of changing the number of tokens to represent a scene or render a novel view with one trained network. Concretely, given a set of images, multi-view encoder tokenizes the images with the camera poses. Latent-space K-means selects a reduced set of rays as cluster centroids using the tokens. The multi-view ``condenser'' compresses the information of all the tokens into the centroid tokens to construct CLiFTs. At test time, given a target view and a compute budget (i.e., the number of CLiFTs), the system collects the specified number of nearby tokens and synthesizes a novel view using a compute-adaptive renderer. Extensive experiments on RealEstate10K and DL3DV datasets quantitatively and qualitatively validate our approach, achieving significant data reduction with comparable rendering quality and the highest overall rendering score, while providing trade-offs of data size, rendering quality, and rendering speed.