Search Results for author:
Found 44 papers, 17 papers with code
Reducing Annotation Burden in Physical Activity Research Using Vision-Language Models
Introduction: Data from wearable devices collected in free-living settings, and labelled with physical activity behaviours compatible with health research, are essential for both validating existing wearable-based measurement approaches and developing novel machine learning approaches.
ForestVO: Enhancing Visual Odometry in Forest Environments through ForestGlue
By combining ForestGlue with a transformer-based pose estimation model, we propose ForestVO, which estimates relative camera poses using matched 2D pixel coordinates between frames.
Image as an IMU: Estimating Camera Motion from a Single Motion-Blurred Image
In many robotics and VR/AR applications, fast camera motions cause a high level of motion blur, causing existing camera pose estimation methods to fail.
Humanity's Last Exam
However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities.
Ranked #4 on
Humanity's Last Exam
on Humanity's Last Exam
CodeMonkeys: Scaling Test-Time Compute for Software Engineering
Here, we explore this problem in the context of solving real-world GitHub issues from the SWE-bench dataset.
Olympus: A Universal Task Router for Computer Vision Tasks
We introduce Olympus, a new approach that transforms Multimodal Large Language Models (MLLMs) into a unified framework capable of handling a wide array of computer vision tasks.
MALT: Improving Reasoning with Multi-Agent LLM Training
In this paper, we present a first step toward "Multi-agent LLM training" (MALT) on reasoning problems.
Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap
The rapid proliferation of AI-manipulated or generated audio deepfakes poses serious challenges to media integrity and election security.
Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
Across multiple tasks and models, we observe that coverage -- the fraction of problems that are solved by any generated sample -- scales with the number of samples over four orders of magnitude.
Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge
In recent years, multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets, enabling them to generally understand images well.
Ranked #162 on
Visual Question Answering
on MM-Vet
Instance Segmentation
Optical Character Recognition (OCR)
+4
EVCL: Elastic Variational Continual Learning with Weight Consolidation
Continual learning aims to allow models to learn new tasks without forgetting what has been learned before.
DreamPolisher: Towards High-Quality Text-to-3D Generation via Geometric Diffusion
We present DreamPolisher, a novel Gaussian Splatting based method with geometric guidance, tailored to learn cross-view consistency and intricate detail from textual descriptions.
DIO: Dataset of 3D Mesh Models of Indoor Objects for Robotics and Computer Vision Applications
These images were processed using a photogrammetry software known as Meshroom to generate a dense surface reconstruction of the scene.
Instant Uncertainty Calibration of NeRFs Using a Meta-Calibrator
To address this, we introduce the concept of a meta-calibrator that performs uncertainty calibration for NeRFs with a single forward pass without the need for holding out any images from the target scene.
Volumetric Cloud Field Reconstruction
Volumetric phenomena, such as clouds and fog, present a significant challenge for 3D reconstruction systems due to their translucent nature and their complex interactions with light.
Towards the Probabilistic Fusion of Learned Priors into Standard Pipelines for 3D Reconstruction
While systems that pass the output of traditional multi-view stereo approaches to a network for regularisation or refinement currently seem to get the best results, it may be preferable to treat deep neural networks as separate components whose results can be probabilistically fused into geometry-based systems.
Volumetric Bundle Adjustment for Online Photorealistic Scene Capture
To the best of our knowledge, this is the first method that can achieve online photorealistic scene capture.
TermiNeRF: Ray Termination Prediction for Efficient Neural Rendering
Volume rendering using neural fields has shown great promise in capturing and synthesizing novel views of 3D scenes.
Waypoint Planning Networks
We propose waypoint planning networks (WPN), a hybrid algorithm based on LSTMs with a local kernel - a classic algorithm such as A*, and a global kernel using a learned algorithm.
End-to-End Egospheric Spatial Memory
Spatial memory, or the ability to remember and recall specific locations and objects, is central to autonomous agents' ability to carry out tasks in real environments.
Ivy: Templated Deep Learning for Inter-Framework Portability
We introduce Ivy, a templated Deep Learning (DL) framework which abstracts existing DL frameworks.
Ego-Centric Spatial Memory Networks
With our broad demonstrations, we show that ESMN represents a useful and general computation graph for embodied spatial reasoning, and the module forms a bridge between real-time mapping systems and differentiable memory architectures.
Unsupervised Path Regression Networks
We demonstrate that challenging shortest path problems can be solved via direct spline regression from a neural network, trained in an unsupervised manner (i. e. without requiring ground truth optimal paths for training).
Orientation Keypoints for 6D Human Pose Estimation
Most realtime human pose estimation approaches are based on detecting joint positions.
LaDDer: Latent Data Distribution Modelling with a Generative Prior
In this paper, we show that the performance of a learnt generative model is closely related to the model's ability to accurately represent the inferred \textbf{latent data distribution}, i. e. its topology and structural properties.
Anomaly Detection for Time Series Using VAE-LSTM Hybrid Model
In this work, we propose a VAE-LSTM hybrid model as an unsupervised approach for anomaly detection in time series.
Scalable Uncertainty for Computer Vision with Functional Variational Inference
As Deep Learning continues to yield successful applications in Computer Vision, the ability to quantify all forms of uncertainty is a paramount requirement for its safe and reliable deployment in the real-world.
PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization
In this paper, we present a novel end-to-end learning-based LiDAR relocalization framework, termed PointLoc, which infers 6-DoF poses directly using only a single point cloud as input, without requiring a pre-built map.
Robotics
DeepFactors: Real-Time Probabilistic Dense Monocular SLAM
The ability to estimate rich geometry and camera motion from monocular imagery is fundamental to future interactive robotics and augmented reality applications.
Balancing Reconstruction Quality and Regularisation in ELBO for VAEs
A trade-off exists between reconstruction quality and the prior regularisation in the Evidence Lower Bound (ELBO) loss that Variational Autoencoder (VAE) models use for learning.
Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
The framework directly regresses 3D bounding boxes for all instances in a point cloud, while simultaneously predicting a point-level mask for each instance.
Ranked #14 on
3D Instance Segmentation
on S3DIS
(mPrec metric)
WiSE-ALE: Wide Sample Estimator for Aggregate Latent Embedding
In this paper, we present a new generative model for learning latent embeddings.
X-Section: Cross-Section Prediction for Enhanced RGBD Fusion
Detailed 3D reconstruction is an important challenge with application to robotics, augmented and virtual reality, which has seen impressive progress throughout the past years.
WiSE-ALE: Wide Sample Estimator for Approximate Latent Embedding
Variational Auto-encoders (VAEs) have been very successful as methods for forming compressed latent representations of complex, often high-dimensional, data.
LS-Net: Learning to Solve Nonlinear Least Squares for Monocular Stereo
In this paper, we propose LS-Net, a neural nonlinear least squares optimization algorithm which learns to effectively optimize these cost functions even in the presence of adversities.
InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset
Datasets have gained an enormous amount of popularity in the computer vision community, from training and evaluation of Deep Learning-based methods to benchmarking Simultaneous Localization and Mapping (SLAM).
Learning to Solve Nonlinear Least Squares for Monocular Stereo
In this paper, we propose a neural nonlinear least squares optimization algorithm which learns to effectively optimize these cost functions even in the presence of adversities.
Fusion++: Volumetric Object-Level SLAM
Reconstructed objects are stored in an optimisable 6DoF pose graph which is our only persistent map representation.
CodeSLAM â Learning a Compact, Optimisable Representation for Dense Visual SLAM
Our approach is suitable for use in a keyframe-based monocular dense SLAM system: While each keyframe with a code can produce a depth map, the code can be optimised efficiently jointly with pose variables and together with the codes of overlapping keyframes to attain global consistency.
CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAM
Our approach is suitable for use in a keyframe-based monocular dense SLAM system: While each keyframe with a code can produce a depth map, the code can be optimised efficiently jointly with pose variables and together with the codes of overlapping keyframes to attain global consistency.
DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks
This paper presents a novel end-to-end framework for monocular VO by using deep Recurrent Convolutional Neural Networks (RCNNs).
3D Object Reconstruction from a Single Depth View with Adversarial Learning
In this paper, we propose a novel 3D-RecGAN approach, which reconstructs the complete 3D structure of a given object from a single arbitrary depth view using generative adversarial networks.
VidLoc: A Deep Spatio-Temporal Model for 6-DoF Video-Clip Relocalization
Machine learning techniques, namely convolutional neural networks (CNN) and regression forests, have recently shown great promise in performing 6-DoF localization of monocular images.
VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem
In this paper we present an on-manifold sequence-to-sequence learning approach to motion estimation using visual and inertial sensors.
