Interactive 3D point cloud segmentation enables efficient annotation of complex 3D scenes through user-guided prompts. However, current approaches are typically restricted in scope to a single domain (indoor or outdoor), and to a single form of user interaction (either spatial clicks or textual prompts). Moreover, training on multiple datasets often leads to negative transfer, resulting in domain-specific tools that lack generalizability. To address these limitations, we present SNAP (Segment aNything in Any Point cloud), a unified model for interactive 3D segmentation that supports both point-based and text-based prompts across diverse domains. Our approach achieves cross-domain generalizability by training on 7 datasets spanning indoor, outdoor, and aerial environments, while employing domain-adaptive normalization to prevent negative transfer. For text-prompted segmentation, we automatically generate mask proposals without human intervention and match them against CLIP embeddings of textual queries, enabling both panoptic and open-vocabulary segmentation. Extensive experiments demonstrate that SNAP consistently delivers high-quality segmentation results. We achieve state-of-the-art performance on 8 out of 9 zero-shot benchmarks for spatial-prompted segmentation and demonstrate competitive results on all 5 text-prompted benchmarks. These results show that a unified model can match or exceed specialized domain-specific approaches, providing a practical tool for scalable 3D annotation. Project page is at https://neu-vi.github.io/SNAP/

Recent advances in 3D scene reconstruction, such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting, have demonstrated remarkable results in novel view synthesis and dynamic scene representation. Despite these successes, existing approaches rely on time-synchronized multi-view imagery captured using specialized camera rigs in controlled environments. This reliance limits their applicability in uncontrolled, unbounded dynamic scenes. In this work, we propose a novel Unmanned Aerial Vehicle (UAV) based multi-view capture system that leverages GNSS Pulse Per Second (PPS) signals for precise frame synchronization across multiple cameras. Our system eliminates the need for fixed infrastructure, enabling flexible and scalable data collection for dynamic scene reconstruction in diverse environments. In addition to the system architecture, we also introduce a dataset of synchronized multi-view images captured in unbounded outdoor scenes from four synchronized UAVs, each carrying a stereo camera rig. We benchmark several 3D and 4D representation methods on our dataset and highlight the challenges associated with data collection in unstructured outdoor settings such as sparse views, varied lighting conditions, visual degradation etc. Our hardware configuration details, software details and dataset is available at https://github.com/neufieldrobotics/Dynamic_Mapping.

Real-time high-accuracy optical flow estimation is critical for a variety of real-world robotic applications. However, current learning-based methods often struggle to balance accuracy and computational efficiency: methods that achieve high accuracy typically demand substantial processing power, while faster approaches tend to sacrifice precision. These fast approaches specifically falter in their generalization capabilities and do not perform well across diverse real-world scenarios. In this work, we revisit the limitations of the SOTA methods and present NeuFlow-V2, a novel method that offers both — high accuracy in real-world datasets coupled with low computational overhead. In particular, we introduce a novel light-weight backbone and a fast refinement module to keep computational demands tractable while delivering accurate optical flow. Experimental results on synthetic and real-world datasets demonstrate that NeuFlow-V2 provides similar accuracy to SOTA methods while achieving 10x-70x speedups. It is capable of running at over 20 FPS on 512x384 resolution images on a Jetson Orin Nano. The full training and evaluation code is available at https://github.com/ neufieldrobotics/NeuFlow_v2.

Visual SLAM with thermal imagery remains a difficult problem for many state of the art (SOTA) algorithms. Compared with visible spectrum imagery, thermal imagery generally has lower contrast, higher noise, and tends to have lower resolution, making for challenging front-end data association. Thermal imagery also presents a difficult problem for long term relocalization and map reuse, because the relative temperatures of objects in thermal imagery tend to change dramatically from day to night. Feature descriptors typically used for relocalization in SLAM are unable to maintain consistency over these diurnal changes. We show that learned feature descriptors can be used within existing bag of word based localization schemes to dramatically improve place recognition across large temporal gaps in thermal imagery. In order to demonstrate the effectiveness of our trained vocabulary, we have developed a baseline SLAM system, integrating learned features and matching into a classical SLAM algorithm. Our system demonstrates good local tracking on challenging thermal imagery, and relocalization that overcomes dramatic day to night thermal appearance changes. Our code and datasets are available here: https://github.com/neufieldrobotics/IRSLAM_Baseline

Evaluating autonomous ground vehicles requires evaluating their mobility performance. Since autonomous vehicles are envisioned to make decisions in a variety of situations and environments too diverse to practically assess with only physical testing, their development, and evaluation will necessarily include the use of simulations. These simulations must represent reality sufficiently to represent the decisions that the vehicles would make in real-world. In this paper we present our Scoping Autonomous Vehicle Simulation (SAVeS) platform for benchmarking the performance of simulated environments for autonomous ground vehicle testing1.

Ferroelectric FET (FeFET) is a highly promising emerging non-volatile memory (NVM) technology, especially for binarized neural network (BNN) inference on the low-power edge. The reliability of such devices, however, inherently depends on temperature. Hence, changes in temperature during run time manifest themselves as changes in bit error rates. In this work, we reveal the temperature-dependent bit error model of FeFET memories, evaluate its effect on BNN accuracy, and propose countermeasures. We begin on the transistor level and accurately model the impact of temperature on bit error rates of FeFET. This analysis reveals temperature-dependent asymmetric bit error rates. Afterwards, on the application level, we evaluate the impact of the temperature-dependent bit errors on the accuracy of BNNs. Under such bit errors, the BNN accuracy drops to unacceptable levels when no countermeasures are employed. We propose two countermeasures: (1) Training BNNs for bit error tolerance by injecting bit flips into the BNN data, and (2) applying a bit error rate assignment algorithm (BERA) which operates in a layer-wise manner and does not inject bit flips during training. In experiments, the BNNs, to which the countermeasures are applied to, effectively tolerate temperature-dependent bit errors for the entire range of operating temperature.