Théo Ladune

Omnia Mahmoud, Théo Ladune, Matthieu Gendrin

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).

Thomas Leguay, Théo Ladune, Pierrick Philippe et al.

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.

Théo Ladune, Pierrick Philippe

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/.

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 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.

Matthieu Gendrin, Stéphane Pateux, Xiaoran Jiang et al.

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.

Stéphane Pateux, Matthieu Gendrin, Luce Morin et al.

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.

Théo Ladune, Pierrick Philippe, Wassim Hamidouche et al.

This paper introduces a practical learned video codec. Conditional coding and quantization gain vectors are used to provide flexibility to a single encoder/decoder pair, which is able to compress video sequences at a variable bitrate. The flexibility is leveraged at test time by choosing the rate and GOP structure to optimize a rate-distortion cost. Using the CLIC21 video test conditions, the proposed approach shows performance on par with HEVC.

Théo Ladune, Pierrick Philippe, Wassim Hamidouche et al.

This paper introduces a new method for inter-frame coding based on two complementary autoencoders: MOFNet and CodecNet. MOFNet aims at computing and conveying the Optical Flow and a pixel-wise coding Mode selection. The optical flow is used to perform a prediction of the frame to code. The coding mode selection enables competition between direct copy of the prediction or transmission through CodecNet. The proposed coding scheme is assessed under the Challenge on Learned Image Compression 2020 (CLIC20) P-frame coding conditions, where it is shown to perform on par with the state-of-the-art video codec ITU/MPEG HEVC. Moreover, the possibility of copying the prediction enables to learn the optical flow in an end-to-end fashion i.e. without relying on pre-training and/or a dedicated loss term.

Théo Ladune, Pierrick Philippe, Wassim Hamidouche et al.

In this paper, a mode selection network (ModeNet) is proposed to enhance deep learning-based video compression. Inspired by traditional video coding, ModeNet purpose is to enable competition among several coding modes. The proposed ModeNet learns and conveys a pixel-wise partitioning of the frame, used to assign each pixel to the most suited coding mode. ModeNet is trained alongside the different coding modes to minimize a rate-distortion cost. It is a flexible component which can be generalized to other systems to allow competition between different coding tools. Mod-eNet interest is studied on a P-frame coding task, where it is used to design a method for coding a frame given its prediction. ModeNet-based systems achieve compelling performance when evaluated under the Challenge on Learned Image Compression 2020 (CLIC20) P-frame coding track conditions.

Théo Ladune, Pierrick Philippe, Wassim Hamidouche et al.

In this paper, we propose to enhance learned image compression systems with a richer probability model for the latent variables. Previous works model the latents with a Gaussian or a Laplace distribution. Inspired by binary arithmetic coding , we propose to signal the latents with three binary values and one integer, with different probability models. A relaxation method is designed to perform gradient-based training. The richer probability model results in a better entropy coding leading to lower rate. Experiments under the Challenge on Learned Image Compression (CLIC) test conditions demonstrate that this method achieves 18% rate saving compared to Gaussian or Laplace models.