arXiv subjects

Théo Ladune

Publications and source records attributed to Théo Ladune.

At least 19 recordsLinked to original sources

arXiv2026

Cool-chic 5.0: Faster Encoding and Inter-Feature Entropy Modeling for Overfitted Image Compression

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 performance and low decoding complexity. This work introduces Cool-chic 5.0, the latest version in the Cool-chic series of overfitted codecs, featuring an updated decoder architecture and an improved optimization process. Cool-chic 5.0 outperforms all overfitted codecs with 10 times less encoding iterations. It offers -11% rate reduction compared to the state-of-the-art conventional codec H.266/VVC. It is also competitive with modern autoencoders such as MLIC++ while featuring a decoding complexity 250 times lower. This work is made open-source at https://github.com/Orange-OpenSource/Cool-Chic.

eess.IV↗

arXiv2026

N-O Cool-chic: reconcile fast encoding with lightweight decoding for neural image compression

Overfitted image codecs achieve strong compression performance and low decoder complexity by learning a lightweight decoder for each image. Such codecs include Cool-chic, which presents image coding performance on par with VVC while requiring around 2000 multiplications per decoded pixel. However, the encoding time associated with overfitted codecs may be prohibitively long for real-time applications, posing a challenge to their practical implementation in such scenarios. To address this issue, this paper proposes to decrease the encoding complexity of Cool-chic by bypassing the overfitting procedure and complementing the decoder with an encoder network. The proposed non-overfitted (N-O) Cool-chic, significantly reduces encoding complexity by a factor of 1000 compared to Cool-chic, while maintaining competitive performance.

eess.IV↗

arXiv2026

Spatial Competition for Low-Complexity Learned Image Compression

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 low-complexity learned image compression framework based on spatial competition between multiple specialized neural codecs. For each image region, the encoder selects the codec that best matches the local content according to a rate-distortion cost. A mode map is transmitted as side information to indicate the per-region codec selection. At decoding time, this mode map-based selection guides reconstruction while preserving the complexity of a single codec. This design enables per-image adaptation with low decoding complexity and fast encoding. On the CLIC 2020 dataset, our method achieves up to -14.5% rate reduction compared to a single codec and reaches HEVC-level performance with a decoding complexity of 1433 MACs per pixel.

eess.IV↗

arXiv2025

Efficient Sub-pixel Motion Compensation in Learned Video Codecs

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 compensation. On the other hand, learned codecs achieve sub-pixel motion compensation through simple bilinear filtering. This paper offers to improve learned codec motion compensation by drawing inspiration from conventional codecs. It is shown that the usage of more advanced interpolation filters, block-based motion information and finite motion accuracy lead to better compression performance and lower decoding complexity. Experimental results are provided on the Cool-chic video codec, where we demonstrate a rate decrease of more than 10% and a lowering of motion-related decoding complexity from 391 MAC per pixel to 214 MAC per pixel. All contributions are made open-source at https://github.com/Orange-OpenSource/Cool-Chic

cs.MM↗

arXiv2025

HyperCool: Reducing Encoding Cost in Overfitted Codecs with Hypernetworks

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 accelerate encoding, Non-Overfitted (N-O) Cool-chic replaces the per-image optimization with a learned inference model, trading compression performance for encoding speed. We introduce HyperCool, a hypernetwork architecture that mitigates this trade-off. Building upon the N-O Cool-chic framework, HyperCool generates content-adaptive parameters for a Cool-chic decoder in a single forward pass, tailoring the decoder to the input image without requiring per-image fine-tuning. Our method achieves a 4.9% rate reduction over N-O Cool-chic with minimal computational overhead. Furthermore, the output of our hypernetwork provides a strong initialization for further optimization, reducing the number of steps needed to approach fully overfitted model performance. With fine-tuning, HEVC-level compression is achieved with 60.4% of the encoding cost of the fully overfitted Cool-chic. This work proposes a practical method to accelerate encoding in overfitted image codecs, improving their viability in scenarios with tight compute budgets.

eess.IV↗

arXiv2025

3DOF+Quantization: 3DGS quantization for large scenes with limited Degrees of Freedom

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 gaussians, which enables the production of novel views from arbitrary points of view. This freedom of movement is referred to as 6DoF for 6 degrees of freedom: a view is produced for any position (3 degrees), orientation of camera (3 other degrees). On large scenes, though, the input views are acquired from a limited zone in space, and the reconstruction is valuable for novel views from the same zone, even if the scene itself is almost unlimited in size. We refer to this particular case as 3DoF+, meaning that the 3 degrees of freedom of camera position are limited to small offsets around the central position. Considering the problem of coordinate quantization, the impact of position error on the projection error in pixels is studied. It is shown that the projection error is proportional to the squared inverse distance of the point being projected. Consequently, a new quantization scheme based on spherical coordinates is proposed. Rate-distortion performance of the proposed method are illustrated on the well-known Garden scene.

cs.CV↗

arXiv2025

Adam SLAM - the last mile of camera calibration with 3DGS

The quality of the camera calibration is of major importance for evaluating progresses in novel view synthesis, as a 1-pixel error on the calibration has a significant impact on the reconstruction quality. While there is no ground truth for real scenes, the quality of the calibration is assessed by the quality of the novel view synthesis. This paper proposes to use a 3DGS model to fine tune calibration by backpropagation of novel view color loss with respect to the cameras parameters. The new calibration alone brings an average improvement of 0.4 dB PSNR on the dataset used as reference by 3DGS. The fine tuning may be long and its suitability depends on the criticity of training time, but for calibration of reference scenes, such as Mip-NeRF 360, the stake of novel view quality is the most important.

cs.CV↗

arXiv2025

BOGausS: Better Optimized Gaussian Splatting

3D Gaussian Splatting (3DGS) proposes an efficient solution for novel view synthesis. Its framework provides fast and high-fidelity rendering. Although less complex than other solutions such as Neural Radiance Fields (NeRF), there are still some challenges building smaller models without sacrificing quality. In this study, we perform a careful analysis of 3DGS training process and propose a new optimization methodology. Our Better Optimized Gaussian Splatting (BOGausS) solution is able to generate models up to ten times lighter than the original 3DGS with no quality degradation, thus significantly boosting the performance of Gaussian Splatting compared to the state of the art.

cs.CV↗

arXiv2025

Improved Encoding for Overfitted Video Codecs

Overfitted neural video codecs offer a decoding complexity orders of magnitude smaller than their autoencoder counterparts. Yet, this low complexity comes at the cost of limited compression efficiency, in part due to their difficulty capturing accurate motion information. This paper proposes to guide motion information learning with an optical flow estimator. A joint rate-distortion optimization is also introduced to improve rate distribution across the different frames. These contributions maintain a low decoding complexity of 1300 multiplications per pixel while offering compression performance close to the conventional codec HEVC and outperforming other overfitted codecs. This work is made open-source at https://orange-opensource.github.io/Cool-Chic/

eess.IV↗

arXiv2024

Upsampling Improvement for Overfitted Neural Coding

Neural image compression, based on auto-encoders and overfitted representations, relies on a latent representation of the coded signal. This representation needs to be compact and uses low resolution feature maps. In the decoding process, those latents are upsampled and filtered using stacks of convolution filters and non linear elements to recover the decoded image. Therefore, the upsampling process is crucial in the design of a neural coding scheme and is of particular importance for overfitted codecs where the network parameters, including the upsampling filters, are part of the representation. This paper addresses the improvement of the upsampling process in order to reduce its complexity and limit the number of parameters. A new upsampling structure is presented whose improvements are illustrated within the Cool-Chic overfitted image coding framework. The proposed approach offers a rate reduction of 4.7%. The code is provided.

eess.IV↗

arXiv2024

Overfitted image coding at reduced complexity

Overfitted image codecs offer compelling compression performance and low decoder complexity, through the overfitting of a lightweight decoder for each image. Such codecs include Cool-chic, which presents image coding performance on par with VVC while requiring around 2000 multiplications per decoded pixel. This paper proposes to decrease Cool-chic encoding and decoding complexity. The encoding complexity is reduced by shortening Cool-chic training, up to the point where no overfitting is performed at all. It is also shown that a tiny neural decoder with 300 multiplications per pixel still outperforms HEVC. A near real-time CPU implementation of this decoder is made available at https://orange-opensource.github.io/Cool-Chic/.

eess.IV↗

arXiv2024

Cool-chic video: Learned video coding with 800 parameters

We propose a lightweight learned video codec with 900 multiplications per decoded pixel and 800 parameters overall. To the best of our knowledge, this is one of the neural video codecs with the lowest decoding complexity. It is built upon the overfitted image codec Cool-chic and supplements it with an inter coding module to leverage the video's temporal redundancies. The proposed model is able to compress videos using both low-delay and random access configurations and achieves rate-distortion close to AVC while out-performing other overfitted codecs such as FFNeRV. The system is made open-source: orange-opensource.github.io/Cool-Chic.

eess.IV↗

arXiv2024

ED: Perceptually tuned Enhanced Compression Model

This paper summarises the design of the candidate ED for the Challenge on Learned Image Compression 2024. This candidate aims at providing an anchor based on conventional coding technologies to the learning-based approaches mostly targeted in the challenge. The proposed candidate is based on the Enhanced Compression Model (ECM) developed at JVET, the Joint Video Experts Team of ITU-T VCEG and ISO/IEC MPEG. Here, ECM is adapted to the challenge objective: to maximise the perceived quality, the encoding is performed according to a perceptual metric, also the sequence selection is performed in a perceptual manner to fit the target bit per pixel objectives. The primary objective of this candidate is to assess the recent developments in video coding standardisation and in parallel to evaluate the progress made by learning-based techniques. To this end, this paper explains how to generate coded images fulfilling the challenge requirements, in a reproducible way, targeting the maximum performance.

eess.IV↗

arXiv2024

Cool-Chic: Perceptually Tuned Low Complexity Overfitted Image Coder

This paper summarises the design of the Cool-Chic candidate for the Challenge on Learned Image Compression. This candidate attempts to demonstrate that neural coding methods can lead to low complexity and lightweight image decoders while still offering competitive performance. The approach is based on the already published overfitted lightweight neural networks Cool-Chic, further adapted to the human subjective viewing targeted in this challenge.

eess.IV↗

arXiv2023

CAwa-NeRF: Instant Learning of Compression-Aware NeRF Features

Modeling 3D scenes by volumetric feature grids is one of the promising directions of neural approximations to improve Neural Radiance Fields (NeRF). Instant-NGP (INGP) introduced multi-resolution hash encoding from a lookup table of trainable feature grids which enabled learning high-quality neural graphics primitives in a matter of seconds. However, this improvement came at the cost of higher storage size. In this paper, we address this challenge by introducing instant learning of compression-aware NeRF features (CAwa-NeRF), that allows exporting the zip compressed feature grids at the end of the model training with a negligible extra time overhead without changing neither the storage architecture nor the parameters used in the original INGP paper. Nonetheless, the proposed method is not limited to INGP but could also be adapted to any model. By means of extensive simulations, our proposed instant learning pipeline can achieve impressive results on different kinds of static scenes such as single object masked background scenes and real-life scenes captured in our studio. In particular, for single object masked background scenes CAwa-NeRF compresses the feature grids down to 6% (1.2 MB) of the original size without any loss in the PSNR (33 dB) or down to 2.4% (0.53 MB) with a slight virtual loss (32.31 dB).

cs.CV↗

arXiv2023

Low-complexity Overfitted Neural Image Codec

We propose a neural image codec at reduced complexity which overfits the decoder parameters to each input image. While autoencoders perform up to a million multiplications per decoded pixel, the proposed approach only requires 2300 multiplications per pixel. Albeit low-complexity, the method rivals autoencoder performance and surpasses HEVC performance under various coding conditions. Additional lightweight modules and an improved training process provide a 14% rate reduction with respect to previous overfitted codecs, while offering a similar complexity. This work is made open-source at https://orange-opensource.github.io/Cool-Chic/

eess.IV↗

arXiv2023

COOL-CHIC: Coordinate-based Low Complexity Hierarchical Image Codec

We introduce COOL-CHIC, a Coordinate-based Low Complexity Hierarchical Image Codec. It is a learned alternative to autoencoders with 629 parameters and 680 multiplications per decoded pixel. COOL-CHIC offers compression performance close to modern conventional MPEG codecs such as HEVC and is competitive with popular autoencoder-based systems. This method is inspired by Coordinate-based Neural Representations, where an image is represented as a learned function which maps pixel coordinates to RGB values. The parameters of the mapping function are then sent using entropy coding. At the receiver side, the compressed image is obtained by evaluating the mapping function for all pixel coordinates. COOL-CHIC implementation is made open-source.

eess.IV↗

arXiv2022

AIVC: Artificial Intelligence based Video Codec

This paper introduces AIVC, an end-to-end neural video codec. It is based on two conditional autoencoders MNet and CNet, for motion compensation and coding. AIVC learns to compress videos using any coding configurations through a single end-to-end rate-distortion optimization. Furthermore, it offers performance competitive with the recent video coder HEVC under several established test conditions. A comprehensive ablation study is performed to evaluate the benefits of the different modules composing AIVC. The implementation is made available at https://orange-opensource.github.io/AIVC/.

cs.NE↗