Papers
arxiv:2507.08776

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

Published on Jul 11
· Submitted by EricW123456 on Jul 14
Authors:
,
,
,
,

Abstract

A neural rendering method uses compressed light-field tokens to efficiently represent scenes and render novel views with varying compute budgets.

AI-generated summary

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.

Community

Paper submitter

We represent a 3D scene as compressed light-field tokens (CLiFTs) that enable adaptive neural rendering with configurable compute budgets, providing flexible trade-offs between rendering speed, representation storage, and visual quality. Check demos on the project page: https://clift-nvs.github.io/.

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2507.08776 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2507.08776 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2507.08776 in a Space README.md to link it from this page.

Collections including this paper 3