---
title: "CaliSplat: Sparse Gaussian Fitting and Calibrated Rate Allocation for Image Compression"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.04413v1"
permalink: "https://feed.astralor.com/items/itm_d98f29e32a1a88bc9eadfd96"
published: "2026-11-03T06:50:17.000Z"
score: 59
channel: "tech"
tags: ["推理效率","CaliSplat","Sparse Gaussian Fitting","Calibrated Rate Allocation","Image Compression","Gaussian","However"]
---

# CaliSplat: Sparse Gaussian Fitting and Calibrated Rate Allocation for Image Compression

## At a glance

2D Gaussian representations provide an explicit and lightweight alternative for image representation, enabling fast deterministic decoding without a heavy neural synthesis network. However, existing per-image Gaussian c…

## Key points

- 2D Gaussian representations provide an explicit and lightweight alternative for image representation, enabling fast deterministic decoding without a heavy neural synthesis network.
- However, existing per-image Gaussian codecs still require costly image-specific optimization to determine how limited Gaussian capacity should be distributed across heterogeneous regions.
- We introduce CaliSplat, an optimization-efficient Gaussian image codec that selectively explores candidate representations and globally allocates a constrained Gaussian budget.

## Full text

2D Gaussian representations provide an explicit and lightweight alternative for image representation, enabling fast deterministic decoding without a heavy neural synthesis network. However, existing per-image Gaussian codecs still require costly image-specific optimization to determine how limited Gaussian capacity should be distributed across heterogeneous regions. We introduce CaliSplat, an optimization-efficient Gaussian image codec that selectively explores candidate representations and globally allocates a constrained Gaussian budget. We exploit the closed-form reconstruction error of the single-Gaussian case as an inexpensive measure of local difficulty, fitting higher-capacity candidates only in regions where additional Gaussians are likely to be useful. To reduce selection errors caused by mismatched convergence rates across candidate sizes, a small set of longer-horizon fits is used to calibrate short-horizon distortion estimates before global budget-aware selection. The selected representation is then compressed into a bitstream. Across standard and large image datasets, CaliSplat achieves competitive or superior rate--distortion performance while reducing per-image fitting time by $3.0\times$--$15.7\times$ compared with representative Gaussian codecs. It further maintains high-throughput deterministic decoding at $175.9$--$478.2$~MP/s. These results demonstrate that content-adaptive Gaussian compression can substantially reduce per-image optimization cost while preserving strong reconstruction quality and efficient explicit decoding.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_d98f29e32a1a88bc9eadfd96