Guillaume O. Berger

Guillaume Berger, Manik Dhingra, Antoine Mercier et al. · cmu, stanford

In this work, we present QuickSRNet, an efficient super-resolution architecture for real-time applications on mobile platforms. Super-resolution clarifies, sharpens, and upscales an image to higher resolution. Applications such as gaming and video playback along with the ever-improving display capabilities of TVs, smartphones, and VR headsets are driving the need for efficient upscaling solutions. While existing deep learning-based super-resolution approaches achieve impressive results in terms of visual quality, enabling real-time DL-based super-resolution on mobile devices with compute, thermal, and power constraints is challenging. To address these challenges, we propose QuickSRNet, a simple yet effective architecture that provides better accuracy-to-latency trade-offs than existing neural architectures for single-image super resolution. We present training tricks to speed up existing residual-based super-resolution architectures while maintaining robustness to quantization. Our proposed architecture produces 1080p outputs via 2x upscaling in 2.2 ms on a modern smartphone, making it ideal for high-fps real-time applications.

Antoine Mercier, Ruan Erasmus, Yashesh Savani et al. · cmu, stanford

Real-time rendering for video games has become increasingly challenging due to the need for higher resolutions, framerates and photorealism. Supersampling has emerged as an effective solution to address this challenge. Our work introduces a novel neural algorithm for supersampling rendered content that is 4 times more efficient than existing methods while maintaining the same level of accuracy. Additionally, we introduce a new dataset which provides auxiliary modalities such as motion vectors and depth generated using graphics rendering features like viewport jittering and mipmap biasing at different resolutions. We believe that this dataset fills a gap in the current dataset landscape and can serve as a valuable resource to help measure progress in the field and advance the state-of-the-art in super-resolution techniques for gaming content.

Sunny Panchal, Apratim Bhattacharyya, Guillaume Berger et al.

Vision-language models have shown impressive progress in recent years. However, existing models are largely limited to turn-based interactions, where each turn must be stepped (i.e., prompted) by the user. Open-ended, asynchronous interactions, where an AI model may proactively deliver timely responses or feedback based on the unfolding situation in real-time, are an open challenge. In this work, we present the QEVD benchmark and dataset, which explores human-AI interaction in the challenging, yet controlled, real-world domain of fitness coaching -- a task which intrinsically requires monitoring live user activity and providing immediate feedback. The benchmark requires vision-language models to recognize complex human actions, identify possible mistakes, and provide appropriate feedback in real-time. Our experiments reveal the limitations of existing state-of-the-art vision-language models for such asynchronous situated interactions. Motivated by this, we propose a simple end-to-end streaming baseline that can respond asynchronously to human actions with appropriate feedback at the appropriate time.

Antoine Mercier, Ramin Nakhli, Mahesh Reddy et al.

Despite the latest remarkable advances in generative modeling, efficient generation of high-quality 3D assets from textual prompts remains a difficult task. A key challenge lies in data scarcity: the most extensive 3D datasets encompass merely millions of assets, while their 2D counterparts contain billions of text-image pairs. To address this, we propose a novel approach which harnesses the power of large, pretrained 2D diffusion models. More specifically, our approach, HexaGen3D, fine-tunes a pretrained text-to-image model to jointly predict 6 orthographic projections and the corresponding latent triplane. We then decode these latents to generate a textured mesh. HexaGen3D does not require per-sample optimization, and can infer high-quality and diverse objects from textual prompts in 7 seconds, offering significantly better quality-to-latency trade-offs when comparing to existing approaches. Furthermore, HexaGen3D demonstrates strong generalization to new objects or compositions.

Min-Hui Lin, Mahesh Reddy, Guillaume Berger et al.

In this paper, we present EdgeRelight360, an approach for real-time video portrait relighting on mobile devices, utilizing text-conditioned generation of 360-degree high dynamic range image (HDRI) maps. Our method proposes a diffusion-based text-to-360-degree image generation in the HDR domain, taking advantage of the HDR10 standard. This technique facilitates the generation of high-quality, realistic lighting conditions from textual descriptions, offering flexibility and control in portrait video relighting task. Unlike the previous relighting frameworks, our proposed system performs video relighting directly on-device, enabling real-time inference with real 360-degree HDRI maps. This on-device processing ensures both privacy and guarantees low runtime, providing an immediate response to changes in lighting conditions or user inputs. Our approach paves the way for new possibilities in real-time video applications, including video conferencing, gaming, and augmented reality, by allowing dynamic, text-based control of lighting conditions.

Guillaume O. Berger, Raphaël M. Jungers

We consider the problem of repetitive scenario design where one has to solve repeatedly a scenario design problem and can adjust the sample size (number of scenarios) to obtain a desired level of risk (constraint violation probability). We propose an approach to learn on the fly the optimal sample size based on observed data consisting in previous scenario solutions and their risk level. Our approach consists in learning a function that represents the pdf (probability density function) of the risk as a function of the sample size. Once this function is known, retrieving the optimal sample size is straightforward. We prove the soundness and convergence of our approach to obtain the optimal sample size for the class of fixed-complexity scenario problems, which generalizes fully-supported convex scenario programs that have been studied extensively in the scenario optimization literature. We also demonstrate the practical efficiency of our approach on a series of challenging repetitive scenario design problems, including non-fixed-complexity problems, nonconvex constraints and time-varying distributions.

Guillaume O. Berger, Raphaël M. Jungers

We investigate the Probably Approximately Correct (PAC) property of scenario decision algorithms, which refers to their ability to produce decisions with an arbitrarily low risk of violating unknown safety constraints, provided a sufficient number of realizations of these constraints are sampled. While several PAC sufficient conditions for such algorithms exist in the literature -- such as the finiteness of the VC dimension of their associated classifiers, or the existence of a compression scheme -- it remains unclear whether these conditions are also necessary. In this work, we demonstrate through counterexamples that these conditions are not necessary in general. These findings stand in contrast to binary classification learning, where analogous conditions are both sufficient and necessary for a family of classifiers to be PAC. Furthermore, we extend our analysis to stable scenario decision algorithms, a broad class that includes practical methods like scenario optimization. Even under this additional assumption, we show that the aforementioned conditions remain unnecessary. Furthermore, we introduce a novel quantity, called the dVC dimension, which serves as an analogue to the VC dimension for scenario decision algorithms. We prove that the finiteness of this dimension is a PAC necessary condition for scenario decision algorithms. This allows to (i) guide algorithm users and designers to recognize algorithms that are not PAC, and (ii) contribute to a comprehensive characterization of PAC scenario decision algorithms.

Guillaume O. Berger

Scenario decision making offers a flexible way of making decision in an uncertain environment while obtaining probabilistic guarantees on the risk of failure of the decision. The idea of this approach is to draw samples of the uncertainty and make a decision based on the samples, called "scenarios". The probabilistic guarantees take the form of a bound on the probability of sampling a set of scenarios that will lead to a decision whose risk of failure is above a given maximum tolerance. This bound can be expressed as a function of the number of sampled scenarios, the maximum tolerated risk, and some intrinsic property of the problem called the "compression size". Several such bounds have been proposed in the literature under various assumptions on the problem. We propose new bounds that improve upon the existing ones without requiring stronger assumptions on the problem.

Antoine Mercier, Guillaume Berger, Sunny Panchal et al.

End-to-end learning has taken hold of many computer vision tasks, in particular, related to still images, with task-specific optimization yielding very strong performance. Nevertheless, human-centric action recognition is still largely dominated by hand-crafted pipelines, and only individual components are replaced by neural networks that typically operate on individual frames. As a testbed to study the relevance of such pipelines, we present a new fully annotated video dataset of fitness activities. Any recognition capabilities in this domain are almost exclusively a function of human poses and their temporal dynamics, so pose-based solutions should perform well. We show that, with this labelled data, end-to-end learning on raw pixels can compete with state-of-the-art action recognition pipelines based on pose estimation. We also show that end-to-end learning can support temporally fine-grained tasks such as real-time repetition counting.