Jamie Shotton

Anthony Hu, Gianluca Corrado, Nicolas Griffiths et al.

An accurate model of the environment and the dynamic agents acting in it offers great potential for improving motion planning. We present MILE: a Model-based Imitation LEarning approach to jointly learn a model of the world and a policy for autonomous driving. Our method leverages 3D geometry as an inductive bias and learns a highly compact latent space directly from high-resolution videos of expert demonstrations. Our model is trained on an offline corpus of urban driving data, without any online interaction with the environment. MILE improves upon prior state-of-the-art by 31% in driving score on the CARLA simulator when deployed in a completely new town and new weather conditions. Our model can predict diverse and plausible states and actions, that can be interpretably decoded to bird's-eye view semantic segmentation. Further, we demonstrate that it can execute complex driving manoeuvres from plans entirely predicted in imagination. Our approach is the first camera-only method that models static scene, dynamic scene, and ego-behaviour in an urban driving environment. The code and model weights are available at https://github.com/wayveai/mile.

Kaylene C. Stocking, Zak Murez, Vijay Badrinarayanan et al.

Object-centric representations enable autonomous driving algorithms to reason about interactions between many independent agents and scene features. Traditionally these representations have been obtained via supervised learning, but this decouples perception from the downstream driving task and could harm generalization. In this work we adapt a self-supervised object-centric vision model to perform object decomposition using only RGB video and the pose of the vehicle as inputs. We demonstrate that our method obtains promising results on the Waymo Open perception dataset. While object mask quality lags behind supervised methods or alternatives that use more privileged information, we find that our model is capable of learning a representation that fuses multiple camera viewpoints over time and successfully tracks many vehicles and pedestrians in the dataset. Code for our model is available at https://github.com/wayveai/SOCS.

Long Chen, Oleg Sinavski, Jan Hünermann et al. · cmu

Large Language Models (LLMs) have shown promise in the autonomous driving sector, particularly in generalization and interpretability. We introduce a unique object-level multimodal LLM architecture that merges vectorized numeric modalities with a pre-trained LLM to improve context understanding in driving situations. We also present a new dataset of 160k QA pairs derived from 10k driving scenarios, paired with high quality control commands collected with RL agent and question answer pairs generated by teacher LLM (GPT-3.5). A distinct pretraining strategy is devised to align numeric vector modalities with static LLM representations using vector captioning language data. We also introduce an evaluation metric for Driving QA and demonstrate our LLM-driver's proficiency in interpreting driving scenarios, answering questions, and decision-making. Our findings highlight the potential of LLM-based driving action generation in comparison to traditional behavioral cloning. We make our benchmark, datasets, and model available for further exploration.

Jannik Zürn, Paul Gladkov, Sofía Dudas et al. · oxford

We present WayveScenes101, a dataset designed to help the community advance the state of the art in novel view synthesis that focuses on challenging driving scenes containing many dynamic and deformable elements with changing geometry and texture. The dataset comprises 101 driving scenes across a wide range of environmental conditions and driving scenarios. The dataset is designed for benchmarking reconstructions on in-the-wild driving scenes, with many inherent challenges for scene reconstruction methods including image glare, rapid exposure changes, and highly dynamic scenes with significant occlusion. Along with the raw images, we include COLMAP-derived camera poses in standard data formats. We propose an evaluation protocol for evaluating models on held-out camera views that are off-axis from the training views, specifically testing the generalisation capabilities of methods. Finally, we provide detailed metadata for all scenes, including weather, time of day, and traffic conditions, to allow for a detailed model performance breakdown across scene characteristics. Dataset and code are available at https://github.com/wayveai/wayve_scenes.

Erroll Wood, Tadas Baltrusaitis, Charlie Hewitt et al.

Landmarks often play a key role in face analysis, but many aspects of identity or expression cannot be represented by sparse landmarks alone. Thus, in order to reconstruct faces more accurately, landmarks are often combined with additional signals like depth images or techniques like differentiable rendering. Can we keep things simple by just using more landmarks? In answer, we present the first method that accurately predicts 10x as many landmarks as usual, covering the whole head, including the eyes and teeth. This is accomplished using synthetic training data, which guarantees perfect landmark annotations. By fitting a morphable model to these dense landmarks, we achieve state-of-the-art results for monocular 3D face reconstruction in the wild. We show that dense landmarks are an ideal signal for integrating face shape information across frames by demonstrating accurate and expressive facial performance capture in both monocular and multi-view scenarios. This approach is also highly efficient: we can predict dense landmarks and fit our 3D face model at over 150FPS on a single CPU thread. Please see our website: https://microsoft.github.io/DenseLandmarks/.

Anthony Hu, Lloyd Russell, Hudson Yeo et al.

Autonomous driving promises transformative improvements to transportation, but building systems capable of safely navigating the unstructured complexity of real-world scenarios remains challenging. A critical problem lies in effectively predicting the various potential outcomes that may emerge in response to the vehicle's actions as the world evolves. To address this challenge, we introduce GAIA-1 ('Generative AI for Autonomy'), a generative world model that leverages video, text, and action inputs to generate realistic driving scenarios while offering fine-grained control over ego-vehicle behavior and scene features. Our approach casts world modeling as an unsupervised sequence modeling problem by mapping the inputs to discrete tokens, and predicting the next token in the sequence. Emerging properties from our model include learning high-level structures and scene dynamics, contextual awareness, generalization, and understanding of geometry. The power of GAIA-1's learned representation that captures expectations of future events, combined with its ability to generate realistic samples, provides new possibilities for innovation in the field of autonomy, enabling enhanced and accelerated training of autonomous driving technology.

Shu Ishida, Gianluca Corrado, George Fedoseev et al.

We propose LangProp, a framework for iteratively optimizing code generated by large language models (LLMs), in both supervised and reinforcement learning settings. While LLMs can generate sensible coding solutions zero-shot, they are often sub-optimal. Especially for code generation tasks, it is likely that the initial code will fail on certain edge cases. LangProp automatically evaluates the code performance on a dataset of input-output pairs, catches any exceptions, and feeds the results back to the LLM in the training loop, so that the LLM can iteratively improve the code it generates. By adopting a metric- and data-driven training paradigm for this code optimization procedure, one could easily adapt findings from traditional machine learning techniques such as imitation learning, DAgger, and reinforcement learning. We show LangProp's applicability to general domains such as Sudoku and CartPole, as well as demonstrate the first proof of concept of automated code optimization for autonomous driving in CARLA. We show that LangProp can generate interpretable and transparent policies that can be verified and improved in a metric- and data-driven way. Our code is available at https://github.com/shuishida/LangProp.

Ana-Maria Marcu, Long Chen, Jan Hünermann et al.

We introduce LingoQA, a novel dataset and benchmark for visual question answering in autonomous driving. The dataset contains 28K unique short video scenarios, and 419K annotations. Evaluating state-of-the-art vision-language models on our benchmark shows that their performance is below human capabilities, with GPT-4V responding truthfully to 59.6% of the questions compared to 96.6% for humans. For evaluation, we propose a truthfulness classifier, called Lingo-Judge, that achieves a 0.95 Spearman correlation coefficient to human evaluations, surpassing existing techniques like METEOR, BLEU, CIDEr, and GPT-4. We establish a baseline vision-language model and run extensive ablation studies to understand its performance. We release our dataset and benchmark as an evaluation platform for vision-language models in autonomous driving.

Lloyd Russell, Anthony Hu, Lorenzo Bertoni et al.

Generative models offer a scalable and flexible paradigm for simulating complex environments, yet current approaches fall short in addressing the domain-specific requirements of autonomous driving - such as multi-agent interactions, fine-grained control, and multi-camera consistency. We introduce GAIA-2, Generative AI for Autonomy, a latent diffusion world model that unifies these capabilities within a single generative framework. GAIA-2 supports controllable video generation conditioned on a rich set of structured inputs: ego-vehicle dynamics, agent configurations, environmental factors, and road semantics. It generates high-resolution, spatiotemporally consistent multi-camera videos across geographically diverse driving environments (UK, US, Germany). The model integrates both structured conditioning and external latent embeddings (e.g., from a proprietary driving model) to facilitate flexible and semantically grounded scene synthesis. Through this integration, GAIA-2 enables scalable simulation of both common and rare driving scenarios, advancing the use of generative world models as a core tool in the development of autonomous systems. Videos are available at https://wayve.ai/thinking/gaia-2.

Katrin Renz, Long Chen, Ana-Maria Marcu et al.

In this technical report, we present CarLLaVA, a Vision Language Model (VLM) for autonomous driving, developed for the CARLA Autonomous Driving Challenge 2.0. CarLLaVA uses the vision encoder of the LLaVA VLM and the LLaMA architecture as backbone, achieving state-of-the-art closed-loop driving performance with only camera input and without the need for complex or expensive labels. Additionally, we show preliminary results on predicting language commentary alongside the driving output. CarLLaVA uses a semi-disentangled output representation of both path predictions and waypoints, getting the advantages of the path for better lateral control and the waypoints for better longitudinal control. We propose an efficient training recipe to train on large driving datasets without wasting compute on easy, trivial data. CarLLaVA ranks 1st place in the sensor track of the CARLA Autonomous Driving Challenge 2.0 outperforming the previous state of the art by 458% and the best concurrent submission by 32.6%.

Erroll Wood, Tadas Baltrušaitis, Charlie Hewitt et al.

We demonstrate that it is possible to perform face-related computer vision in the wild using synthetic data alone. The community has long enjoyed the benefits of synthesizing training data with graphics, but the domain gap between real and synthetic data has remained a problem, especially for human faces. Researchers have tried to bridge this gap with data mixing, domain adaptation, and domain-adversarial training, but we show that it is possible to synthesize data with minimal domain gap, so that models trained on synthetic data generalize to real in-the-wild datasets. We describe how to combine a procedurally-generated parametric 3D face model with a comprehensive library of hand-crafted assets to render training images with unprecedented realism and diversity. We train machine learning systems for face-related tasks such as landmark localization and face parsing, showing that synthetic data can both match real data in accuracy as well as open up new approaches where manual labelling would be impossible.

Stephan J. Garbin, Marek Kowalski, Matthew Johnson et al.

Recent work on Neural Radiance Fields (NeRF) showed how neural networks can be used to encode complex 3D environments that can be rendered photorealistically from novel viewpoints. Rendering these images is very computationally demanding and recent improvements are still a long way from enabling interactive rates, even on high-end hardware. Motivated by scenarios on mobile and mixed reality devices, we propose FastNeRF, the first NeRF-based system capable of rendering high fidelity photorealistic images at 200Hz on a high-end consumer GPU. The core of our method is a graphics-inspired factorization that allows for (i) compactly caching a deep radiance map at each position in space, (ii) efficiently querying that map using ray directions to estimate the pixel values in the rendered image. Extensive experiments show that the proposed method is 3000 times faster than the original NeRF algorithm and at least an order of magnitude faster than existing work on accelerating NeRF, while maintaining visual quality and extensibility.

Tadas Baltrusaitis, Erroll Wood, Virginia Estellers et al.

Analysis of faces is one of the core applications of computer vision, with tasks ranging from landmark alignment, head pose estimation, expression recognition, and face recognition among others. However, building reliable methods requires time-consuming data collection and often even more time-consuming manual annotation, which can be unreliable. In our work we propose synthesizing such facial data, including ground truth annotations that would be almost impossible to acquire through manual annotation at the consistency and scale possible through use of synthetic data. We use a parametric face model together with hand crafted assets which enable us to generate training data with unprecedented quality and diversity (varying shape, texture, expression, pose, lighting, and hair).

Jingjing Shen, Thomas J. Cashman, Qi Ye et al.

Realtime perceptual and interaction capabilities in mixed reality require a range of 3D tracking problems to be solved at low latency on resource-constrained hardware such as head-mounted devices. Indeed, for devices such as HoloLens 2 where the CPU and GPU are left available for applications, multiple tracking subsystems are required to run on a continuous, real-time basis while sharing a single Digital Signal Processor. To solve model-fitting problems for HoloLens 2 hand tracking, where the computational budget is approximately 100 times smaller than an iPhone 7, we introduce a new surface model: the `Phong surface'. Using ideas from computer graphics, the Phong surface describes the same 3D shape as a triangulated mesh model, but with continuous surface normals which enable the use of lifting-based optimization, providing significant efficiency gains over ICP-based methods. We show that Phong surfaces retain the convergence benefits of smoother surface models, while triangle meshes do not.

Stephan J. Garbin, Marek Kowalski, Matthew Johnson et al.

Generating photorealistic images of human faces at scale remains a prohibitively difficult task using computer graphics approaches. This is because these require the simulation of light to be photorealistic, which in turn requires physically accurate modelling of geometry, materials, and light sources, for both the head and the surrounding scene. Non-photorealistic renders however are increasingly easy to produce. In contrast to computer graphics approaches, generative models learned from more readily available 2D image data have been shown to produce samples of human faces that are hard to distinguish from real data. The process of learning usually corresponds to a loss of control over the shape and appearance of the generated images. For instance, even simple disentangling tasks such as modifying the hair independently of the face, which is trivial to accomplish in a computer graphics approach, remains an open research question. In this work, we propose an algorithm that matches a non-photorealistic, synthetically generated image to a latent vector of a pretrained StyleGAN2 model which, in turn, maps the vector to a photorealistic image of a person of the same pose, expression, hair, and lighting. In contrast to most previous work, we require no synthetic training data. To the best of our knowledge, this is the first algorithm of its kind to work at a resolution of 1K and represents a significant leap forward in visual realism.

Marek Kowalski, Stephan J. Garbin, Virginia Estellers et al.

Our ability to sample realistic natural images, particularly faces, has advanced by leaps and bounds in recent years, yet our ability to exert fine-tuned control over the generative process has lagged behind. If this new technology is to find practical uses, we need to achieve a level of control over generative networks which, without sacrificing realism, is on par with that seen in computer graphics and character animation. To this end we propose ConfigNet, a neural face model that allows for controlling individual aspects of output images in semantically meaningful ways and that is a significant step on the path towards finely-controllable neural rendering. ConfigNet is trained on real face images as well as synthetic face renders. Our novel method uses synthetic data to factorize the latent space into elements that correspond to the inputs of a traditional rendering pipeline, separating aspects such as head pose, facial expression, hair style, illumination, and many others which are very hard to annotate in real data. The real images, which are presented to the network without labels, extend the variety of the generated images and encourage realism. Finally, we propose an evaluation criterion using an attribute detection network combined with a user study and demonstrate state-of-the-art individual control over attributes in the output images.

Alexander Krull, Eric Brachmann, Sebastian Nowozin et al.

State-of-the-art computer vision algorithms often achieve efficiency by making discrete choices about which hypotheses to explore next. This allows allocation of computational resources to promising candidates, however, such decisions are non-differentiable. As a result, these algorithms are hard to train in an end-to-end fashion. In this work we propose to learn an efficient algorithm for the task of 6D object pose estimation. Our system optimizes the parameters of an existing state-of-the art pose estimation system using reinforcement learning, where the pose estimation system now becomes the stochastic policy, parametrized by a CNN. Additionally, we present an efficient training algorithm that dramatically reduces computation time. We show empirically that our learned pose estimation procedure makes better use of limited resources and improves upon the state-of-the-art on a challenging dataset. Our approach enables differentiable end-to-end training of complex algorithmic pipelines and learns to make optimal use of a given computational budget.

Eric Brachmann, Alexander Krull, Sebastian Nowozin et al.

RANSAC is an important algorithm in robust optimization and a central building block for many computer vision applications. In recent years, traditionally hand-crafted pipelines have been replaced by deep learning pipelines, which can be trained in an end-to-end fashion. However, RANSAC has so far not been used as part of such deep learning pipelines, because its hypothesis selection procedure is non-differentiable. In this work, we present two different ways to overcome this limitation. The most promising approach is inspired by reinforcement learning, namely to replace the deterministic hypothesis selection by a probabilistic selection for which we can derive the expected loss w.r.t. to all learnable parameters. We call this approach DSAC, the differentiable counterpart of RANSAC. We apply DSAC to the problem of camera localization, where deep learning has so far failed to improve on traditional approaches. We demonstrate that by directly minimizing the expected loss of the output camera poses, robustly estimated by RANSAC, we achieve an increase in accuracy. In the future, any deep learning pipeline can use DSAC as a robust optimization component.

Yani Ioannou, Duncan Robertson, Darko Zikic et al.

This paper investigates the connections between two state of the art classifiers: decision forests (DFs, including decision jungles) and convolutional neural networks (CNNs). Decision forests are computationally efficient thanks to their conditional computation property (computation is confined to only a small region of the tree, the nodes along a single branch). CNNs achieve state of the art accuracy, thanks to their representation learning capabilities. We present a systematic analysis of how to fuse conditional computation with representation learning and achieve a continuum of hybrid models with different ratios of accuracy vs. efficiency. We call this new family of hybrid models conditional networks. Conditional networks can be thought of as: i) decision trees augmented with data transformation operators, or ii) CNNs, with block-diagonal sparse weight matrices, and explicit data routing functions. Experimental validation is performed on the common task of image classification on both the CIFAR and Imagenet datasets. Compared to state of the art CNNs, our hybrid models yield the same accuracy with a fraction of the compute cost and much smaller number of parameters.

Yani Ioannou, Duncan Robertson, Jamie Shotton et al.

We propose a new method for creating computationally efficient convolutional neural networks (CNNs) by using low-rank representations of convolutional filters. Rather than approximating filters in previously-trained networks with more efficient versions, we learn a set of small basis filters from scratch; during training, the network learns to combine these basis filters into more complex filters that are discriminative for image classification. To train such networks, a novel weight initialization scheme is used. This allows effective initialization of connection weights in convolutional layers composed of groups of differently-shaped filters. We validate our approach by applying it to several existing CNN architectures and training these networks from scratch using the CIFAR, ILSVRC and MIT Places datasets. Our results show similar or higher accuracy than conventional CNNs with much less compute. Applying our method to an improved version of VGG-11 network using global max-pooling, we achieve comparable validation accuracy using 41% less compute and only 24% of the original VGG-11 model parameters; another variant of our method gives a 1 percentage point increase in accuracy over our improved VGG-11 model, giving a top-5 center-crop validation accuracy of 89.7% while reducing computation by 16% relative to the original VGG-11 model. Applying our method to the GoogLeNet architecture for ILSVRC, we achieved comparable accuracy with 26% less compute and 41% fewer model parameters. Applying our method to a near state-of-the-art network for CIFAR, we achieved comparable accuracy with 46% less compute and 55% fewer parameters.

James Steven Supancic, Gregory Rogez, Yi Yang et al.

Hand pose estimation has matured rapidly in recent years. The introduction of commodity depth sensors and a multitude of practical applications have spurred new advances. We provide an extensive analysis of the state-of-the-art, focusing on hand pose estimation from a single depth frame. To do so, we have implemented a considerable number of systems, and will release all software and evaluation code. We summarize important conclusions here: (1) Pose estimation appears roughly solved for scenes with isolated hands. However, methods still struggle to analyze cluttered scenes where hands may be interacting with nearby objects and surfaces. To spur further progress we introduce a challenging new dataset with diverse, cluttered scenes. (2) Many methods evaluate themselves with disparate criteria, making comparisons difficult. We define a consistent evaluation criteria, rigorously motivated by human experiments. (3) We introduce a simple nearest-neighbor baseline that outperforms most existing systems. This implies that most systems do not generalize beyond their training sets. This also reinforces the under-appreciated point that training data is as important as the model itself. We conclude with directions for future progress.