From the 1 of 10 linked papers with an AI index.
10 papers
N-O Cool-chic: reconcile fast encoding with lightweight decoding for neural image compression
Théophile Blard, Théo Ladune, Pierrick Philippe +2
The paper presents N-O Cool-chic, a neural image codec that eliminates the costly per‑image overfitting step by adding an encoder network, reducing encoding time by about 1000× whi…
Spatial Competition for Low-Complexity Learned Image Compression
Théophile Blard, Pierrick Philippe, Théo Ladune +2
Autoencoder-based image codecs achieve state-of-the-art compression performance but often incur high computational complexity, particularly at decoding time. This work introduces a…
Cool-chic 5.0: Faster Encoding and Inter-Feature Entropy Modeling for Overfitted Image Compression
Théo Ladune, Pierrick Philippe, Pierre Jaffuer +4
Overfitted codecs compress an image by learning a decoder tailored to the content during the encoding. As such, they trade increased encoding complexity for strong compression perf…
HyperCool: Reducing Encoding Cost in Overfitted Codecs with Hypernetworks
Pep Borrell-Tatché, Till Aczel, Théo Ladune +1
Overfitted image codecs like Cool-chic achieve strong compression by tailoring lightweight models to individual images, but their encoding is slow and computationally expensive. To…
Efficient Sub-pixel Motion Compensation in Learned Video Codecs
Théo Ladune, Thomas Leguay, Pierrick Philippe +2
Motion compensation is a key component of video codecs. Conventional codecs (HEVC and VVC) have carefully refined this coding step, with an important focus on sub-pixel motion comp…
3DOF+Quantization: 3DGS quantization for large scenes with limited Degrees of Freedom
Matthieu Gendrin, Stéphane Pateux, Théo Ladune
3D Gaussian Splatting (3DGS) is a major breakthrough in 3D scene reconstruction. With a number of views of a given object or scene, the algorithm trains a model composed of 3D gaus…