FRAPPE: Full Input, Residual Output Autoencoding with Projection Pursuit Encoder
Summary
FRAPPE is a novel autoencoding framework that uses a projection pursuit encoder to predict residuals from full input, enabling efficient variable-rate image compression with fast CPU-based encoding. At high compression ratios, FRAPPE-Image achieves higher perceptual quality than AVIF with 47x faster encoding, making real-time 1080p 30fps CPU-only encoding possible.
View Cached Full Text
Cached at: 06/01/26, 07:19 AM
Paper page - FRAPPE: Full Input, Residual Output Autoencoding with Projection Pursuit Encoder
Source: https://huggingface.co/papers/2605.28992
Abstract
A novel autoencoding framework called FRAPPE uses a projection pursuit encoder to predict residuals from full input, enabling efficient variable-rate image compression with fast CPU-based encoding.
Media compression standards have reached a plateau in terms of therate-distortion-complexity trade-off, limiting the ability to offload expensive AI perception to the cloud in applications like robotics, wearables, and remote sensing. DNN-based codecs improve compression efficiency, but at a cost: they cannot easily adapt to large changes in available bitrate, and real-time encoding requires expensive, power-hungry GPUs that prohibit use on low-cost or resource-constrained platforms. To address these limitations, we propose a novelautoencoding framework(FRAPPE) that uses the Full input to predict theResidual outputvia aProjection Pursuit Encoder. FRAPPE’s encoding objective naturally sortslatent channelsby importance, allowing zero-overheadvariable-rate coding. Unlike RNN-basedlearned codecs, whose encoder consumes the previous reconstruction’s residual, or RVQ-style codecs, whose codebooks must be applied sequentially, FRAPPE’s analysis path is an embarrassingly parallelDAGofindependent input projections. Using FRAPPE, we build a variable-rateRGB image codec(FRAPPE-Image), and evaluate itsrate-distortion-complexity trade-offagainst standard image codecs. At high compression ratios (approx. 0.1 bpp) FRAPPE-Image provides higherperceptual qualitythan AVIF with 47 times faster encoding, making it capable of real-time 1080p, 30fpsCPU-only encoding. Our code and pre-trained models are available: https://github.com/UT-SysML/FRAPPE .
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2605\.28992
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2605.28992 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2605.28992 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2605.28992 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
AFP-GIC: Controllable Generative Image Compression [R]
AFP-GIC, a controllable generative image compression framework published in IEEE Access (2026), uses an asymmetric Adaptive Fused Prior Transfer pipeline to reduce hallucinations and local distortion at ultra-low bitrates, achieving 18.1% lower decoder latency and 20.5% fewer parameters than DC-VIC, with released code, benchmark data, and an interactive Hugging Face demo.
Adaptive Fused Prior Transfer for Controllable Generative Image Compression
AFP-GIC is an IEEE Access 2026 paper proposing Adaptive Fused Prior Transfer for controllable generative image compression, achieving up to 167:1 compression with a single pretrained model across five bitrate operating points and reducing decoder latency by 18.1% versus DC-VIC.
FFAvatar: Few-Shot, Feed-Forward, and Generalizable Avatar Reconstruction
FFAvatar proposes a feed-forward framework for reconstructing high-quality, animatable 3D Gaussian head avatars from few unposed images in seconds, achieving a 5.5 PSNR improvement over state-of-the-art on the NeRSemble benchmark.
SEAOTTER: Sensor Embedded Autoencoding with One-Time Transcode for Efficient Reconstruction
Introduces SEAOTTER, a compression framework for cloud robotics that combines learned latent representations with standard JPEG compatibility, achieving faster encoding/decoding and higher accuracy at extreme compression ratios.
VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders
This paper introduces VideoRAE, a representation autoencoder that leverages frozen video foundation models to create compact, reconstruction-capable, and generation-friendly video latents. It achieves state-of-the-art results on UCF-101 with faster convergence than competing autoencoders.