Unlabeled LiDAR logs, in autonomous driving applications, are inherently a gold mine of dense 3D geometry hiding in plain sight - yet they are almost useless without human labels, highlighting a dominant cost barrier for autonomous-perception research. In this work we tackle this bottleneck by leveraging temporal-geometric consistency across LiDAR sweeps to lift and fuse cues from text and 2 Dvision foundation models directly into 3D, without any manual input. We introduce an unsupervised multimodal pseudo-labeling method relying on strong geometric priors learned from temporally accumulated LiDAR maps, alongside with a novel iterative update rule that enforces joint geometric-semantic consistency, and vice-versa detecting moving objects from inconsistencies. Our method simultaneously produces 3D semantic labels, 3D bounding boxes, and dense LiDAR scans, demonstrating robust generalization across three datasets. We experimentally validate that our method compares favorably to existing semantic segmentation and object detection pseudo-labeling methods, which often require additional manual supervision. We confirm that even a small fraction of our geometrically consistent, densified LiDAR improves depth prediction by 51.5 % and 22.0 % MAE in the 80-150 and 150-250 meters range, respectively.

We introduce a novel dataset and evaluation approach for long-range depth prediction of small objects that enables consistent comparison across direct time-of-flight (ToF) sensors and learned depth estimation methods. In autonomous driving, accurate depth perception is essential for identifying and locating surrounding elements and determining safe driving paths. Traditional depth metrics focus on distance accuracy but fail to evaluate a key factor at long ranges: distinguishing small, slightly elevated structures from the ground - crucial for anticipating obstacles and making safe driving decisions. At far distances, imagebased systems suffer from resolution limitations that tend to oversmooth the ground plane, causing elevated objects to be mistaken as texture patterns on the surface. Conversely, scanning LiDAR systems may return only a single point from an elevated object due to steep incident angles and sparse returns, preventing accurate differentiation from the ground. This hampers a fair comparison of object presence and shape. To address this, we propose a framework that evaluates how well the estimated point clouds preserve semantic content relative to ground-truth data. We leverage neural network-based feature extraction to assess structural similarity, enabling a modality-agnostic evaluation of object-level fidelity. Our method also supports analysis of the trade-off between resolution and accuracy, investigating performances across sensor types - such as highresolution cameras versus LiDAR - and conditions, including day and night scenarios. This enables a more comprehensive understanding of the capabilities and limitations of current depth prediction approaches in real-world settings.

Achieving robust stereo 3D imaging under diverse illumination conditions is challenging due to the limited dynamic range of conventional cameras, causing existing stereo depth estimation methods to suffer from under- or over-exposed images. In this paper, we propose dual-exposure stereo that combines auto-exposure control and dual-exposure bracketing to achieve stereo 3D imaging with extended dynamic range. Specifically, we capture stereo image pairs with alternating dual exposures, which automatically adapt to scene illumination and effectively distribute the scene dynamic range across the dual-exposure frames. We then estimate stereo depth from these dual-exposure stereo images by compensating for motion between consecutive frames. To validate our approach, we develop a robotic vision system, acquire real-world HDR stereo video datasets, and generate additional synthetic datasets. Experimental results demonstrate that our method outperforms existing exposure control methods.

Outside of urban hubs, autonomous cars and trucks have to master driving on intercity highways. Safe, long-distance highway travel at speeds exceeding 100 km/h demands perception distances of at least 250 m, which is about five times the 50-100m typically addressed in city driving, to allow sufficient planning and braking margins. Increasing the perception ranges also allows to extend autonomy from light two-ton passenger vehicles to large-scale forty-ton trucks, which need a longer planning horizon due to their high inertia. However, most existing perception approaches focus on shorter ranges and rely on Bird's Eye View (BEV) representations, which incur quadratic increases in memory and compute costs as distance grows. To overcome this limitation, we built on top of a sparse representation and introduced an efficient 3D encoding of multi-modal and temporal features, along with a novel self-supervised pre-training scheme that enables large-scale learning from unlabeled camera-LiDAR data. Our approach extends perception distances to 250 meters and achieves an 26.6% improvement in mAP in object detection and a decrease of 30.5% in Chamfer Distance in LiDAR forecasting compared to existing methods, reaching distances up to 250 meters. Project Page: https://light.princeton.edu/lrs4fusion/

Depth estimation is a cornerstone computer vision application that is critical for scene understanding and autonomous driving. In real-world scenarios, achieving reliable depth perception under adverse weather—e.g. in fog and rain—is crucial to ensure safety and system robustness. However, quantitatively evaluating the performances of depth estimation methods in these scenarios is challenging due to the difficulty of obtaining ground truth data. A promising approach is using weather chambers to simulate diverse weather conditions in a controlled environment. However, current datasets are limited in distance and lack a dense ground truth. To address this gap, we introduce a novel evaluation benchmark that extends depth evaluation up to 200 meters under clear, foggy, and rainy conditions. To this end, we employ a multimodal sensor setup, including state-of-the-art stereo RGB, RCCB, Gated camera systems, and a long-range LiDAR sensor. Moreover, we record a digital twin of the test facility sampled at a millimeter scale using a high-end geodesic laser scanner. This comprehensive benchmark allows for the evaluation of different models and multiple sensing modalities in a more precise and accurate manner, as well as at far distances. Data and code will be released upon publication.

Gated cameras flood-illuminate a scene and capture the time-gated impulse response of a scene. By employing nanosecond-scale gates, existing sensors are capable of capturing mega-pixel gated images, delivering dense depth improving on today's LiDAR sensors in spatial resolution and depth precision. Although gated depth estimation methods deliver a million of depth estimates per frame, their res-olution is still an order below existing RGB imaging methods. In this work, we combine high-resolution stereo HDR RCCB cameras with gated imaging, allowing us to exploit depth cues from active gating, multi-view RGB and multi-view NIR sensing - multi-view and gated cues across the entire spectrum. The resulting capture system consists only of low-cost CMOS sensors and flood-illumination. We pro-pose a novel stereo-depth estimation method that is capa-ble of exploiting these multi-modal multi-view depth cues, including the active illumination that is measured by the RCCB camera when removing the IR-cut filter. The pro-posed method achieves accurate depth at long ranges, out-performing the next best existing method by 39% for ranges of 100 to 220 m in MAE on accumulated LiDAR ground-truth. Our code, models and datasets are available here11https://light.princeton.edu/gatedrccbstereo/.