FLIF: Free lossless image format based on MANIAC compression

By Jon Sneyers, Pieter Wuille. 2016

165 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jun Zhu
2. Zhenguo Li
3. Yoshua Bengio
4. Max Welling
5. Luc Van Gool
6. Chongxuan Li
7. Shifeng Zhang
8. Pieter Abbeel

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Jun Zhu
3. Ming-Hsuan Yang
4. Dacheng Tao
5. Chen Change Loy
6. Zhenguo Li
7. Alan L. Yuille
8. Xiaogang Wang

In Signal Processing

1. Max Welling
2. Zhenguo Li
3. Shifeng Zhang
4. Ning Kang
5. Jun Zhu
6. Chongxuan Li
7. Rianne van den Berg
8. Emiel Hoogeboom

Citations in the corpus

• Fast Lossless Neural Compression with Integer-Only Discrete Flows (2022, methodology): “Neural compressors have achieved superior compression ratios on standard datasets than traditional lossless compression methods, such as JPEG2000 (Group et al., 2000), PNG (Boutell & Lane, 1997) and ELIF (Sneyers & Wuille, 2016).”
• Latent Variable Models (2019, methodology): “Similar to the way that we use FLIF to code the first images for our experiments, one could initially code images using a fully observed model then switch to a faster latent variable model once a stack of bits has been built up.”
• iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression (2021, background): “From Table 3, one can observe that for high resolution images, conventional coders, e.g., FLIF, still have advantage over learning based methods, while they tend to underperform learning based methods on small scale images.”
• Practical Full Resolution Learned Lossless Image Compression (2018, methodology): “The current state-of-the-art (non-learned) algorithm is FLIF [36].”
• Integer Discrete Flows and Lossless Compression (2019, background): “Dataset IDF IDF† PNG JPEG2000 FLIF [29] BZIP2 CIFAR10 3.”
• IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression (2020, methodology): “Lastly FLIF [44] uses an adaptive entropy coder that selects the local context model using a per-image learned decision tree.”
• HiLLoC: Lossless Image Compression with Hierarchical Latent Variable Models (2019, methodology): “Similar to the way that we use FLIF to code the first images for our experiments, one could initially code images using a fully observed model then switch to a faster latent variable model once a stack of bits has been built up.”