78 accepted papers
We introduce the problem of material-aware part grouping in untextured meshes.Many real-world shapes, such as scales of pinecones or windows of buildings, contain repeated structures that share the same material but exhibit geometric variations.When assigning materials to such meshes, these repeated
Score-function based methods for policy learning, such as REINFORCE and PPO, have delivered strong results in game-playing and robotics, yet their high variance often undermines training stability. Using pathwise policy gradients, i.e. computing a derivative by differentiating the objective function…
Offline goal-conditioned reinforcement learning (GCRL) often struggles with long-horizon tasks, where errors in value estimation accumulate and produce unreliable policies. It is typically assumed that effective long-term planning is infeasible without specialized training. In contrast, our work dem…
Rare, yet critical, scenarios pose a significant challenge in testing and evaluating autonomous driving planners. Relying solely on real-world driving scenes requires collecting massive datasets to capture these scenarios. While automatic generation of traffic scenarios appears promising, data-drive
Achieving controllable and consistent editing in dynamic 3D scenes remains a significant challenge. Previous work is largely constrained by its editing backbones, resulting in inconsistent edits and limited controllability. We propose to address this challenge using personalized diffusion models. In…
The idea of value-aware model learning, that models should produce accurate value estimates, has gained prominence in model-based reinforcement learning. The MuZero loss, which penalizes a model's value function prediction compared to the ground-truth value function, has been utilized in several pro…
Recent advances in autonomous driving are moving towards mapless approaches, where High-Definition (HD) maps are generated online directly from sensor data, reducing the need for expensive labeling and maintenance. However, the reliability of these online-generated maps remains uncertain. While inco
Direct Preference Optimization (DPO) has recently been applied as a post‑training technique for text-to-video diffusion models. To obtain training data, annotators are asked to provide preferences between two videos generated from independent noise. However, this approach prohibits fine-grained comp…
We introduce a method for using event camera data in novel view synthesis via Gaussian Splatting. Event cameras offer exceptional temporal resolution and a high dynamic range. Leveraging these capabilities allows us to effectively address the novel view synthesis challenge in the presence of fast ca…
Recent advancements in static feed-forward scene reconstruction have demonstrated significant progress in high-quality novel view synthesis. However, these models often struggle with generalizability across diverse environments and fail to effectively handle dynamic content. We present BTimer (short…
Estimating scene lighting from a single image or video remains a longstanding challenge in computer vision and graphics. Learning-based approaches are constrained by the scarcity of ground-truth HDR environment maps, which are expensive to capture and limited in diversity. While recent generative mo…
Building deep reinforcement learning (RL) agents that find a good policy with few samples has proven notoriously challenging. To achieve sample efficiency, recent work has explored updating neural networks with large numbers of gradient steps for every new sample. While such high update-to-data (UTD…
Autonomous long-horizon mobile manipulation encompasses a multitude of challenges, including scene dynamics, unexplored areas, and error recovery. Recent works have leveraged foundation models for scene-level robotic reasoning and planning. However, the performance of these methods degrades when dea
Real-world videos consist of sequences of events. Generating such sequences with precise temporal control is infeasible with existing video generators that rely on a single paragraph of text as input. When tasked with generating multiple events described using a single prompt, such methods often ign…
We present Pippo, a generative model capable of producing 1K resolution dense turnaround videos of a person from a single casually clicked photo. Pippo is a multi-view diffusion transformer and does not require any additional inputs - e.g., a fitted parametric model or camera parameters of the input…
Existing evaluation paradigms for Autonomous Vehicles (AVs) face critical limitations. Real-world evaluation is often challenging due to safety concerns and a lack of reproducibility, whereas closed-loop simulation can face insufficient realism or high computational costs. Open-loop evaluation, whil…
While vision-language-action models (VLAs) have shown promising robotic behaviors across a diverse set of manipulation tasks, they achieve limited success rates when deployed on novel tasks out of the box. To allow these policies to safely interact with their environments, we need a failure detector…
Methods for image-to-video generation have achieved impressive, photo-realistic quality. However, adjusting specific elements in generated videos, such as object motion or camera movement, is often a tedious process of trial and error, e.g., involving re-generating videos with different random seed…
Long-term temporal information is crucial for event-based perception tasks, as raw events only encode pixel brightness changes. Recent works show that when trained from scratch, recurrent models achieve better results than feedforward models in these tasks. However, when leveraging self-supervised p…
Current 3D/4D generation methods are usually optimized for photorealism, efficiency, and aesthetics. However, they often fail to preserve the semantic identity of the subject across different viewpoints. Adapting generation methods with one or few images of a specific subject (also known as Personal…
We address the challenge of relighting a single image or video, a task that demands precise scene intrinsic understanding and high-quality light transport synthesis. Existing end-to-end relighting models are often limited by the scarcity of paired multi-illumination data, restricting their ability t…
"Understanding road geometry is a critical component of the autonomous vehicle (AV) stack. While high-definition (HD) maps can readily provide such information, they suffer from high labeling and maintenance costs. Accordingly, many recent works have proposed methods for estimating HD maps online fr…
We introduce GaussianCut, a new method for interactive multiview segmentation of scenes represented as 3D Gaussians. Our approach allows for selecting the objects to be segmented by interacting with a single view. It accepts intuitive user input, such as point clicks, coarse scribbles, or text. Usin…
Object detection with event cameras benefits from the sensor's low latency and high dynamic range. However it is costly to fully label event streams for supervised training due to their high temporal resolution. To reduce this cost we present LEOD the first method for label-efficient event-based det…
Benchmarking vision-based driving policies is challenging. On one hand, open-loop evaluation with real data is easy, but these results do not reflect closed-loop performance. On the other, closed-loop evaluation is possible in simulation, but is hard to scale due to its significant computational dem…
We address the problem of multi-object 3D pose control in image diffusion models. Instead of conditioning on a sequence of text tokens, we propose to use a set of per-object representations, *Neural Assets*, to control the 3D pose of individual objects in a scene. Neural Assets are obtained by pooli…
High-definition (HD) maps have played an integral role in the development of modern autonomous vehicle (AV) stacks albeit with high associated labeling and maintenance costs. As a result many recent works have proposed methods for estimating HD maps online from sensor data enabling AVs to operate ou…
We present SPAD a novel approach for creating consistent multi-view images from text prompts or single images. To enable multi-view generation we repurpose a pretrained 2D diffusion model by extending its self-attention layers with cross-view interactions and fine-tune it on a high quality subset of…
Large-scale multi-task robotic manipulation systems often rely on text to specify the task. In this work, we explore whether a robot can learn by observing humans. To do so, the robot must understand a person's intent and perform the inferred task despite differences in the embodiments and environme…
"The success of denoising diffusion models in generating and editing images has sparked interest in using diffusion models for editing 3D scenes represented via neural radiance fields (NeRFs). However, current 3D editing methods lack a way to both pinpoint the edit location and limit changes to the…
Autonomous racing is a challenging task that requires vehicle handling at the dynamic limits of friction. While single-agent scenarios like Time Trials are solved competitively with classical model-based or model-free feedback control, multi-agent wheel-to-wheel racing poses several challenges inclu…
While significant progress has been made on the problem of generating grasps, many existing learning-based approaches still concentrate on a single embodiment, provide limited generalization to higher DoF end-effectors and cannot capture a diverse set of grasp modes. In this paper, we tackle the pro…
Building animatable and editable models of clothed humans from raw 3D scans and poses is a challenging problem. Existing reposing methods suffer from the limited expressiveness of Linear Blend Skinning (LBS), require costly mesh extraction to generate each new pose, and typically do not preserve sur…
As learning-based methods make their way from perception systems to planning/control stacks, robot control systems have started to enjoy the benefits that data-driven methods provide. Because control systems directly affect the motion of the robot, data-driven methods, especially black box approache
The popularity of Neural Radiance Fields (NeRFs) for view synthesis has led to a desire for NeRF editing tools. Here, we focus on inpainting regions in a view-consistent and controllable manner. In addition to the typical NeRF inputs and masks delineating the unwanted region in each view, we require…
Neural Radiance Fields (NeRFs) have emerged as a popular approach for novel view synthesis. While NeRFs are quickly being adapted for a wider set of applications, intuitively editing NeRF scenes is still an open challenge. One important editing task is the removal of unwanted objects from a 3D scene…
Object-centric learning aims to represent visual data with a set of object entities (a.k.a. slots), providing structured representations that enable systematic generalization. Leveraging advanced architectures like Transformers, recent approaches have made significant progress in unsupervised object…
While there has been substantial success for solving continuous control with actor-critic methods, simpler critic-only methods such as Q-learning find limited application in the associated high-dimensional action spaces. However, most actor-critic methods come at the cost of added complexity: heuris…
Camera pose estimation is a key step in standard 3D reconstruction pipelines that operates on a dense set of images of a single object or scene. However, methods for pose estimation often fail when there are only a few images available because they rely on the ability to robustly identify and match…
The field of trajectory forecasting has grown significantly in recent years, partially owing to the release of numerous large-scale, real-world human trajectory datasets for autonomous vehicles (AVs) and pedestrian motion tracking. While such datasets have been a boon for the community, they each us…
Temporal patterns (how vehicles behave in our observed past) underline our reasoning of how people drive on the road, and can explain why we make certain predictions about interactions among road agents. In this paper we propose the ConceptNet trajectory predictor - a novel prediction framework that…
Modeling multi-modal high-level intent is important for ensuring diversity in trajectory prediction. Existing approaches explore the discrete nature of human intent before predicting continuous trajectories, to improve accuracy and support explainability. However, these approaches often assume the i…
"We introduce Housekeep, a benchmark to evaluate commonsense reasoning in the home for embodied AI. In Housekeep, an embodied agent must tidy a house by rearranging misplaced objects without explicit instructions specifying which objects need to be rearranged. Instead, the agent must learn from and…
"Obtaining 3D object representations is important for creating photo-realistic simulators and collecting assets for AR/VR applications. Neural fields have shown their effectiveness in learning a continuous volumetric representation of a scene from 2D images, but acquiring object representations from…
Data-driven simulators promise high data-efficiency for driving policy learning. When used for modelling interactions, this data-efficiency becomes a bottleneck: small underlying datasets often lack interesting and challenging edge cases for learning interactive driving. We address this challenge by…
Symbolic reasoning is a key component for enabling practical use of data-driven planners in autonomous driving. In that context, deterministic finite state automata (DFA) are often used to formalize the underlying high-level decision-making process. Manual design of an effective DFA can be tedious.
Deploying fully autonomous vehicles has been a subject of intense research in both industry and academia. However, the majority of these efforts have relied heavily on High Definition (HD) prior maps. These are necessary to provide the planning and control modules a rich model of the operating envir
Simulation has the potential to transform the development of robust algorithms for mobile agents deployed in safety-critical scenarios. However, the poor photorealism and lack of diverse sensor modalities of existing simulation engines remain key hurdles towards realizing this potential. Here, we pr…
Mapping and localization using surface features is prone to failure due to environment changes such as inclement weather. Recently; Localizing Ground Penetrating Radar (LGPR) has been proposed as an alternative means of localizing using underground features that are stable over time and less affecte…
Reinforcement learning (RL) for continuous control typically employs distributions whose support covers the entire action space. In this work, we investigate the colloquially known phenomenon that trained agents often prefer actions at the boundaries of that space. We draw theoretical connections to…
Efficiency in robot learning is highly dependent on hyperparameters. Robot morphology and task structure differ widely and finding the optimal setting typically requires sequential or parallel repetition of experiments, strongly increasing the interaction count. We propose a training method that onl…
In this work, we propose a novel approach for integrating rules into traffic agent trajectory prediction. Consideration of rules is important for understanding how people behave-yet, it cannot be assumed that rules are always followed. To address this challenge, we evaluate different approaches of i
Most autonomous driving solutions require some method of localization within their environment. Typically, onboard sensors are used to localize the vehicle precisely in a previously recorded map. However, these solutions are sensitive to ambient lighting conditions such as darkness and inclement wea
In this letter, we propose a novel approach for agent motion prediction in cluttered environments. One of the main challenges in predicting agent motion is accounting for location and context-specific information. Our main contribution is the concept of learning context maps to improve the predictio
Learning competitive behaviors in multi-agent settings such as racing requires long-term reasoning about potential adversarial interactions. This paper presents Deep Latent Competition (DLC), a novel reinforcement learning algorithm that learns competitive visual control policies through self-play i
Reasoning about uncertain orientations is one of the core problems in many perception tasks such as object pose estimation or motion estimation. In these scenarios, poor illumination conditions, sensor limitations, or appearance invariance may result in highly uncertain estimates. In this work, we p…
In this work, we propose a method for integration of temporal logic formulas into a neural network. Our main contribution is a new logic optimization layer that uses differentiable optimization on the formulas’ robustness function. This allows incorporating traffic rules into deep learning based tra
In this paper, we propose a method to use semantic information to improve the use of map priors in a sparse, feature-based MonoSLAM system. To incorporate the priors, the features in the prior and SLAM maps must be associated with one another. Most existing systems build a map using SLAM and then al…
In this work, we present a data-driven simulation and training engine capable of learning end-to-end autonomous vehicle control policies using only sparse rewards. By leveraging real, human-collected trajectories through an environment, we render novel training data that allows virtual agents to dri
In this work, we present MapLite: a one-click autonomous navigation system capable of piloting a vehicle to an arbitrary desired destination point given only a sparse publicly available topometric map (from OpenStreetMap). The onboard sensors are used to segment the road region and register the topo
We present an efficient coresets-based neural network compression algorithm that sparsifies the parameters of a trained fully-connected neural network in a manner that provably approximates the network's output. Our approach is based on an importance sampling scheme that judiciously defines a sampli…
Current perception systems mostly require direct line of sight to anticipate and ultimately prevent potential collisions at intersections with other road users. We present a fully integrated autonomous system capable of detecting shadows or weak illumination changes on the ground caused by a dynamic…
Among traffic accidents in the USA, 23% of fatal and 32% of non-fatal incidents occurred at intersections. For driver assistance systems, intersection navigation remains a difficult problem that is critically important to increasing driver safety. In this letter, we examine how to navigate an unsign
Full autonomy for fixed-wing unmanned aerial vehicles (UAVs) requires the capability to autonomously detect potential landing sites in unknown and unstructured terrain, allowing for self-governed mission completion or handling of emergency situations. In this letter, we propose a perception system a
Localization in 3-D point clouds is a highly challenging task due to the complexity associated with extracting information from 3-D data. This letter proposes an incremental approach addressing this problem efficiently. The presented method first accumulates the measurements in a dynamic voxel grid
The growing popularity of autonomous systems creates a need for reliable and efficient metric pose retrieval algorithms. Currently used approaches tend to rely on nearest neighbor search of binary descriptors to perform the 2D-3D matching and guarantee realtime capabilities on mobile platforms. Thes…
Robust and accurate visual-inertial estimation is crucial to many of today's challenges in robotics. Being able to localize against a prior map and obtain accurate and drift-free pose estimates can push the applicability of such systems even further. Most of the currently available solutions, howeve
The successful deployment of many autonomous systems in part hinges on providing rigorous guarantees on their performance and safety through a formal verification method, such as reachability analysis. In this work, we present a simple-to-implement, sampling-based algorithm for reachability analysis…
Deployment of camera and laser based motion estimation systems for controlling platforms operating at high speeds, such as cars or trains, is posing increasingly challenging precision requirements on the temporal calibration of these sensors. In this work, we demonstrate a simple, low-cost system fo…
Many robotics and Augmented Reality (AR) systems that use sparse keypoint-based visual maps operate in large and highly repetitive environments, where pose tracking and localization are challenging tasks. Additionally, these systems usually face further challenges, such as limited computational powe…
A variety of end-user devices involving keypoint-based mapping systems are about to hit the market e.g. as part of smartphones, cars, robotic platforms, or virtual and augmented reality applications. Thus, the generated map data requires automated evaluation procedures that do not require experience…
In this paper, we propose a GPU parallelized SLAM system capable of using photometric and inertial data together with depth data from an active RGB-D sensor to build accurate dense 3D maps of indoor environments. We describe several extensions to existing dense SLAM techniques that allow us to opera…
Robots that are operating for extended periods of time need to be able to deal with changes in their environment and represent them adequately in their maps. In this paper, we present a novel 3D reconstruction algorithm based on an extended Truncated Signed Distance Function (TSDF) that enables to c…
Environmental conditions and external effects, such as shocks, have a significant impact on the calibration parameters of visual-inertial sensor systems. Thus long-term operation of these systems cannot fully rely on factory calibration. Since the observability of certain parameters is highly depend…
In this paper, we present an online landmark selection method for distributed long-term visual localization systems in bandwidth-constrained environments. Sharing a common map for online localization provides a fleet of autonomous vehicles with the possibility to maintain and access a consistent map…
Precisely estimating the pose of an agent in a global reference frame is a crucial goal that unlocks a multitude of robotic applications, including autonomous navigation and collaboration. In order to achieve this, current state-of-the-art localization approaches collect data provided by one or more…
In this paper we present a new estimation algorithm that allows for the combination of information from any number of process and measurement models. This adds more flexibility to the design of the estimator and in our case avoids the need for state augmentation. We achieve this by adapting the maxi…
Accurate and robust real-time map generation onboard of a fixed-wing UAV is essential for obstacle avoidance, path planning, and critical maneuvers such as autonomous take-off and landing. Due to the computational constraints, the required robustness and reliability, it remains a challenge to deploy…