93 accepted papers
Energy-based predictive world models provide a powerful approach for multi-step visual planning by reasoning over latent energy landscapes rather than generating pixels. However, existing approaches face two major challenges: (i) their latent representations are typically learned in Euclidean space,
Recent advancements in Large Video Language Models (LVLMs) have highlighted their potential for multi-modal understanding, yet evaluating their factual grounding in videos remains a critical unsolved challenge. To address this gap, we introduce Video SimpleQA, the first comprehensive benchmark tailo
Current 3D Large Multimodal Models (3D LMMs) have shown tremendous potential in 3D-vision-based dialogue and reasoning. However, how to further enhance 3D LMMs to achieve fine-grained scene understanding and facilitate flexible human-agent interaction remains a challenging problem. In this work, we…
Diffusion models have recently advanced 3D human motion generation by producing smoother and more realistic sequences from natural language. However, existing approaches face two major challenges: high computational cost during training and inference, and limited scalability due to reliance on U-Net…
We propose Hier-SLAM, a semantic 3D Gaussian Splatting SLAM method featuring a novel hierarchical categorical representation, which enables accurate global 3D semantic mapping, scaling-up capability, and explicit semantic label prediction in the 3D world. The parameter usage in semantic SLAM systems
Imitation learning has unlocked the potential for robots to exhibit highly dexterous behaviours. However, it still struggles with long-horizon, multi-object tasks due to poor sample efficiency and limited generalisation. Existing methods require a substantial number of demonstrations to cover possib…
Visual navigation using only a single camera and a topological map has recently become an appealing alternative to methods that require additional sensors and 3D maps. This is typically achieved through an "image-relative" approach to estimating control from a given pair of current observation and s…
Visual navigation in robotics traditionally relies on globally-consistent 3D maps or learned controllers, which can be computationally expensive and difficult to generalize across diverse environments. In this work, we present a novel RGB-only, object-level topometric navigation pipeline that enable
In the field of autonomous driving and mobile robotics, there has been a significant shift in the methods used to create Bird’s Eye View (BEV) representations. This shift is characterised by using transformers and learning to fuse measurements from disparate vision sensors, mainly lidar and cameras,
"We propose , a text-driven method to edit a 3D scene reconstructed by the 3D Gaussian Splatting (3DGS). Our method first renders a collection of images by using the 3DGS and edits them by using a pre-trained 2D diffusion model (ControlNet) based on the input prompt, which is then used to optimise t…
"The costly and time-consuming annotation process to produce large training sets for modelling semantic LiDAR segmentation methods has motivated the development of semi-supervised learning (SSL) methods. However, such SSL approaches often concentrate on employing consistency learning only for indivi…
Autonomous robot systems have attracted increasing research attention in recent years where environment understanding is a crucial step for robot navigation human-robot interaction and decision. Real-world robot systems usually collect visual data from multiple sensors and are required to recognize…
"Human motion generation stands as a significant pursuit in generative computer vision, while achieving long-sequence and efficient motion generation remains challenging. Recent advancements in state space models (SSMs), notably Mamba, have showcased considerable promise in long sequence modeling wi…
Mapping is crucial for spatial reasoning, planning and robot navigation. Existing approaches range from metric, which require precise geometry-based optimization, to purely topological, where image-as-node based graphs lack explicit object-level reasoning and interconnectivity. In this paper, we pro…
Semantic segmentation models classify pixels into a set of known ("in-distribution") visual classes. When deployed in an open world, the reliability of these models depends on their ability to not only classify in-distribution pixels but also to detect out-of-distribution (OoD) pixels. Historicall…
Large language models (LLMs) have demonstrated impressive results in developing generalist planning agents for diverse tasks. However, grounding these plans in expansive, multi-floor, and multi-room environments presents a significant challenge for robotics. We introduce SayPlan, a scalable approach…
Event cameras open up new possibilities for robotic perception due to their low latency and high dynamic range. On the other hand, developing effective event-based vision algorithms that fully exploit the beneficial properties of event cameras remains work in progress. In this paper, we focus on eve…
Future Moon bases will likely be constructed using resources mined from the surface of the Moon. The difficulty of maintaining a human workforce on the Moon and communications lag with Earth means that mining will need to be conducted using collaborative robots with a high degree of autonomy. In thi…
The availability of large-scale video action understanding datasets has facilitated advances in the interpretation of visual scenes containing people. However, learning to recognise human actions and their social interactions in an unconstrained real-world environment comprising numerous people, wit…
We present You Only Cut Once (YOCO) for performing data augmentations. YOCO cuts one image into two pieces and performs data augmentations individually within each piece. Applying YOCO improves the diversity of the augmentation per sample and encourages neural networks to recognize objects from part…
Semantic aware reconstruction is more advantageous than geometric-only reconstruction for future robotic and AR/VR applications because it represents not only where things are, but also what things are. Object-centric mapping is a task to build an object-level reconstruction where objects are separa
Localizing objects and estimating their extent in 3D is an important step towards high-level 3D scene understanding, which has many applications in Augmented Reality and Robotics. We present ODAM, a system for 3D Object Detection, Association, and Mapping using posed RGB videos. The proposed system…
Under mild conditions on the noise level of the measurements, rotation averaging satisfies strong duality, which enables global solutions to be obtained via semidefinite programming (SDP) relaxation. However, generic solvers for SDP are rather slow in practice, even on rotation averaging instances o…
Joint forecasting of human trajectory and pose dynamics is a fundamental building block of various applications ranging from robotics and autonomous driving to surveillance systems. Predicting body dynamics requires capturing subtle information embedded in the humans' interactions with each other an…
Semantic scene completion (SSC) refers to the task of inferring the 3D semantic segmentation of a scene while simultaneously completing the 3D shapes. We propose PALNet, a novel hybrid network for SSC based on single depth. PALNet utilizes a two-stream network to extract both 2D and 3D features from
Object-oriented maps are important for scene understanding since they jointly capture geometry and semantics, allow individual instantiation and meaningful reasoning about objects. We introduce FroDO, a method for accurate 3D reconstruction of object instances from RGB video that infers their locati…
Individuals Action and Sub-group Activities in Videos","The state-of-the art solutions for human activity understanding from a video stream formulate the task as a spatio-temporal problem which requires joint localization of all individuals in the scene and classification of their actions or group a…
Video object segmentation plays a vital role to many robotic tasks, beyond the satisfied accuracy, quickly adapt to the new scenario with very limited annotations and conduct a quick inference are also important. In this paper, we are specifically concerned with the task of fast segmenting all pixel…
Multiple rotation averaging is an essential task for structure from motion, mapping, and robot navigation. The task is to estimate the absolute orientations of several cameras given some of their noisy relative orientation measurements. The conventional methods for this task seek parameters of the a…
Six degree-of-freedom pose estimation of a known object in a single image is a long-standing computer vision objective. It is classically posed as a correspondence problem between a known geometric model, such as a CAD model, and image locations. If a CAD model is not available, it is possible to us…
Deep generative models have been used in recent years to learn coherent latent representations in order to synthesize high-quality images. In this work, we propose a neural network to learn a generative model for sampling consistent indoor scene layouts. Our method learns the co-occurrences, and app…
Visual place recognition is an important problem in mobile robotics which aims to localize a robot using image information alone. Recent methods have shown promising results for place recognition under varying environmental conditions by exploiting the sequential nature of the image acquisition proc…
Smooth and seamless robot navigation while interacting with humans depends on predicting human movements. Forecasting such human dynamics often involves modeling human trajectories (global motion) or detailed body joint movements (local motion). Prior work typically tackled local and global human mo
In this paper, we seek to tackle a challenge in training low-precision networks: the notorious difficulty in propagating gradient through a low-precision network due to the non-differentiable quantization function. We propose a solution by training the low-precision network with a full-precision aux…
In this work we present a monocular visual odometry (VO) algorithm which leverages geometry-based methods and deep learning. Most existing VO/SLAM systems with superior performance are based on geometry and have to be carefully designed for different application scenarios. Moreover, most monocular s…
We propose a method that substantially improves the efficiency of deep distance metric learning based on the optimization of the triplet loss function. One epoch of such training process based on a na"ive optimization of the triplet loss function has a run-time complexity O(N^3), where N is the numb…
Ghosting artifacts caused by moving objects or misalignments is a key challenge in high dynamic range (HDR) imaging for dynamic scenes. Previous methods first register the input low dynamic range (LDR) images using optical flow before merging them, which are error-prone and cause ghosts in results.…
Deep learning models have demonstrated outstanding performance in several problems, but their training process tends to require immense amounts of computational and human resources for training and labeling, constraining the types of problems that can be tackled. Therefore, the design of effective t…
Automated design of neural network architectures tailored for a specific task is an extremely promising, albeit inherently difficult, avenue to explore. While most results in this domain have been achieved on image classification and language modelling problems, here we concentrate on dense per-pixe…
Intersection over Union (IoU) is the most popular evaluation metric used in the object detection benchmarks. However, there is a gap between optimizing the commonly used distance losses for regressing the parameters of a bounding box and maximizing this metric value. The optimal objective for a metr…
RGB images differentiate from depth as they carry more details about the color and texture information, which can be utilized as a vital complement to depth for boosting the performance of 3D semantic scene completion (SSC). SSC is composed of 3D shape completion (SC) and semantic scene labeling whi…
Deployment of deep learning models in robotics as sensory information extractors can be a daunting task to handle, even using generic GPU cards. Here, we address three of its most prominent hurdles, namely, i) the adaptation of a single model to perform multiple tasks at once (in this work, we consi…
Simultaneous Localization And Mapping (SLAM) is a fundamental problem in mobile robotics. While sparse point-based SLAM methods provide accurate camera localization, the generated maps lack semantic information. On the other hand, state of the art object detection methods provide rich information ab…
A major challenge in place recognition for autonomous driving is to be robust against appearance changes due to short-term (e.g., weather, lighting) and long-term (seasons, vegetation growth, etc.) environmental variations. A promising solution is to continuously accumulate images to maintain an ade…
Semantic segmentation and instance level segmentation made substantial progress in recent years due to the emergence of deep neural networks (DNNs). A number of deep architectures with Convolution Neural Networks (CNNs) were proposed that surpass the traditional machine learning approaches for segme…
In this work we present a self-supervised learning framework to simultaneously train two Convolutional Neural Networks (CNNs) to predict depth and surface normals from a single image. In contrast to most existing frameworks which represent outdoor scenes as fronto-parallel planes at piece-wise smoot…
Predicting the future trajectories of multiple interacting pedestrians in a scene has become an increasingly important problem for many different applications ranging from control of autonomous vehicles and social robots to security and surveillance. This problem is compounded by the presence of soc…
In this paper, we propose to train convolutional neural networks (CNNs) with both binarized weights and activations, leading to quantized models specifically for mobile devices with limited power capacity and computation resources. By assuming the same architecture to full-precision networks, previo…
3D point cloud generation is of great use for 3D scene modeling and understanding. Real-world 3D object point clouds can be properly described by a collection of low-level and high-level structures such as surfaces, geometric primitives, semantic parts,etc. In fact, there exist many differ…
Recent work has shown that CNN-based depth and ego-motion estimators can be learned using unlabelled monocular videos. However, the performance is limited by unidentified moving objects that violate the underlying static scene assumption in geometric image reconstruction. More significantly, due to…
Bundle adjustment plays a vital role in feature-based monocular SLAM. In many modern SLAM pipelines, bundle adjustment is performed to estimate the 6DOF camera trajectory and 3D map (3D point cloud) from the input feature tracks. However, two fundamental weaknesses plague SLAM systems based on bundl…
Place recognition is an essential component of Simultaneous Localization And Mapping (SLAM). Under severe appearance change, reliable place recognition is a difficult perception task since the same place is perceptually very different in the morning, at night, or over different seasons. This work ad…
We propose AffordanceNet, a new deep learning approach to simultaneously detect multiple objects and their affordances from RGB images. Our AffordanceNet has two branches: an object detection branch to localize and classify the object, and an affordance detection branch to assign each pixel in the o…
The Visual Dialogue task requires an agent to engage in a conversation about an image with a human. It represents an extension of the Visual Question Answering task in that the agent needs to answer a question about an image, but it needs to do so in light of the previous dialogue that has taken pl…
This paper addresses the semantic instance segmentation task in the open-set conditions, where input images can contain known and unknown object classes. The training process of existing semantic instance segmentation methods requires annotation masks for all object instances, which is expensive to…
Fully supervised methods for semantic segmentation require pixel-level class masks to train, the creation of which are expensive in terms of manual labour and time. In this work, we focus on weak supervision, developing a method for training a high-quality pixel-level classifier for semantic segment…
Regression trackers directly learn a mapping from regularly dense samples of target objects to soft labels, which are usually generated by a Gaussian function, to estimate target positions. Due to the potential for fast-tracking and easy implementation, regression trackers have received increasing a…
Most existing CNN-based methods for single-view 3D object reconstruction represent a 3D object as either a 3D voxel occupancy grid or multiple depth-mask image pairs. However, these representations are inefficient since empty voxels or background pixels are wasteful. We propose a novel approach that…
We present “just-in-time reconstruction” as realtime image-guided inpainting of a map with arbitrary scale and sparsity to generate a fully dense depth map for the image. In particular, our goal is to inpaint a sparse map - obtained from either a monocular visual SLAM system or a sparse sensor - usi…
In generalized zero shot learning (GZSL), the set of classes are split into seen and unseen classes, where training relies on the semantic features of the seen and unseen classes and the visual representations of only the seen classes, while testing uses the visual representations of the seen and un…
Recognising objects according to a pre-defined fixed set of class labels has been well studied in the Computer Vision. There are a great many practical applications where the subjects that may be of interest are not known beforehand, or so easily delineated, however. In many of these cases natural l…
This paper presents SceneCut, a novel approach to jointly discover previously unseen objects and non-object surfaces using a single RGB-D image. SceneCut's joint reasoning over scene semantics and geometry allows a robot to detect and segment object instances in complex scenes where modern deep lear…
This paper tackles the problem of training a deep convolutional neural network with both low-precision weights and low-bitwidth activations. Optimizing a low-precision network is very challenging since the training process can easily get trapped in a poor local minima, which results in substantial a…
Despite learning based methods showing promising results in single view depth estimation and visual odometry, most existing approaches treat the tasks in a supervised manner. Recent approaches to single view depth estimation explore the possibility of learning without full supervision via minimizing…
A robot that can carry out a natural-language instruction has been a dream since before the Jetsons cartoon series imagined a life of leisure mediated by a fleet of attentive robot helpers. It is a dream that remains stubbornly distant. However, recent advances in vision and language methods have m…
In this paper, we exploit memory-augmented neural networks to predict accurate answers to visual questions, even when those answers rarely occur in the training set. The memory network incorporates both internal and external memory blocks and selectively pays attention to each training exemplar. We…
Rigid structure-from-motion (RSfM) and non-rigid structure-from-motion (NRSfM) have long been treated in the literature as separate (different) problems. Inspired by a previous work which solved directly for 3D scene structure by factoring the relative camera poses out, we revisit the principle of "…
Data augmentation is an essential part of the training process applied to deep learning models. The motivation is that a robust training process for deep learning models depends on large annotated datasets, which are expensive to be acquired, stored and processed. Therefore a reasonable alternativ…
We address the problem of camera-to-laserscanner calibration using a checkerboard and multiple imagelaser scan pairs. Distinguishing which laser points measure the checkerboard and which lie on the background is essential to any such system. We formulate the checkerboard extraction as a combinatoria…
This paper proposes a discrete-time geometric attitude observer for fusing monocular vision with GPS velocity measurements. The observer takes the relative transformations obtained from processing monocular images with any visual odometry algorithm and fuses them with GPS velocity measurements. The…
Large-scale datasets have driven the rapid development of deep neural networks for visual recognition. However, annotating a massive dataset is expensive and time-consuming. Web images and their labels are, in comparison, much easier to obtain, but direct training on such automatially harvested imag…
We present a novel deep neural network architecture for unsupervised subspace clustering. This architecture is built upon deep auto-encoders, which non-linearly map the input data into a latent space. Our key idea is to introduce a novel self-expressive layer between the encoder and the decoder to m…
The success of deep learning techniques in the computer vision domain has triggered a range of initial investigations into their utility for visual place recognition, all using generic features from networks that were trained for other types of recognition tasks. In this paper, we train, at large sc…
Although 2D LiDAR based Simultaneous Localization and Mapping (SLAM) is a relatively mature topic nowadays, the loop closure problem remains challenging due to the lack of distinctive features in 2D LiDAR range scans. Existing research can be roughly divided into correlation based approaches e.g. sc…
This paper addresses the task of set prediction using deep learning. This is important because the output of many computer vision tasks, including image tagging and object detection, are naturally expressed as sets of entities rather than vectors. As opposed to a vector, the size of a set is not fix…
This paper presents an efficient framework for dense 3D scene reconstruction using input from a moving monocular camera. Visual SLAM (Simultaneous Localisation and Mapping) approaches based solely on geometric methods have proven to be quite capable of accurately tracking the pose of a moving camera…
Removing pixel-wise heterogeneous motion blur is challenging due to the ill-posed nature of the problem. The predominant solution is to estimate the blur kernel by adding a prior, but extensive literature on the subject indicates the difficulty in identifying a prior which is suitably informative, a…
For intelligent robots to interact in meaningful ways with their environment, they must understand both the geometric and semantic properties of the scene surrounding them. The majority of research to date has addressed these mapping challenges separately, focusing on either geometric or semantic ma…
In this paper, we present a monocular direct semi-dense SLAM (Simultaneous Localization And Mapping) method that can handle both radial distortion and rolling-shutter distortion. Such distortions are common in, but not restricted to, situations when an inexpensive wide-angle lens and a CMOS sensor a…
Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation. However, repeated subsampling operations like pooling or convolution striding in deep…
To solve deep metric learning problems and produce feature embeddings, current methodologies will commonly use a triplet model to minimise the relative distance between samples from the same class and maximise the relative distance between samples from different classes. Though successful, the train…
Recognizing how objects interact with each other is a crucial task in visual recognition. If we define the context of the interaction to be the objects involved, then most current methods can be categorized as either: (i) training a single classifier on the combination of the interaction and its con…
Recent advances in semantic image segmentation have mostly been achieved by training deep convolutional neural networks(CNNs). We show how to improve semantic segmentation through the use of contextual information; specifically, we explore 'patch-patch' context between image regions, and 'patch-back…
We tackle the problem of large-scale object detection in images, where the number of objects can be arbitrarily large, and can exhibit significant overlap/occlusion. A successful approach to modelling the large-scale nature of this problem has been via point process density functions which jointly…
In this paper, we aim to learn a mapping (or embedding) from images to a compact binary space in which Hamming distances correspond to a ranking measure for the image retrieval task. We make use of a triplet loss because this has been shown to be most effective for ranking problems. How- ever, train…
Modern SLAM systems with a depth sensor are able to reliably reconstruct dense 3D geometric maps of indoor scenes. Representing these maps in terms of meaningful entities is a step towards building semantic maps for autonomous robots. One approach is to segment the 3D maps into semantic objects usin…
Matching between two sets of objects is typically approached by finding the object pairs that collectively maximize the joint matching score. In this paper, we argue that this single solution does not necessarily lead to the optimal matching accuracy and that general one-to-one assignment problems c…
Recent innovations in training deep convolutional neural network (ConvNet) models have motivated the design of new methods to automatically learn local image descriptors. The latest deep ConvNets proposed for this task consist of a siamese network that is trained by penalising misclassification of p…
Deep structured output learning shows great promise in tasks like semantic image segmentation. We proffer a new, efficient deep structured model learning scheme, in which we show how deep Convolutional Neural Networks (CNNs) can be used to directly estimate the messages in message passing inference…
This paper addresses the problem of semantic segmentation of 3D indoor scenes reconstructed from RGB-D images.Traditionally label prediction for 3D points is tackled by employing graphical models that capture scene features and complex relations between different class labels. However, the existing…
In this paper, we revisit the joint probabilistic data association (JPDA) technique and propose a novel solution based on recent developments in finding the m-best solutions to an integer linear program. The key advantage of this approach is that it makes JPDA computationally tractable in applicatio…
Tracking-by-detection has proven to be the most successful strategy to address the task of tracking multiple targets in unconstrained scenarios. Traditionally, a set of sparse detections, generated in a preprocessing step, serves as input to a high-level tracker whose goal is to correctly associate…
Sparsity, or cardinality, as a tool for feature selection is extremely common in a vast number of current computer vision applications. The $k$-support norm is a recently proposed norm with the proven property of providing the tightest convex bound on cardinality over the Euclidean norm unit ball. I…