171 citations · 283 across the 29 of their papers we have counts for
29 papers · 1 filter
ScenarioControl: Vision-Language Controllable Vectorized Latent Scenario Generation
Lili Gao, Yanbo Xu, William Koch +8
We introduce ScenarioControl, the first vision-language control mechanism for learned driving scenario generation. Given a text prompt or an input image, Scenario-Control synthesiz…
Telescope: Learnable Hyperbolic Foveation for Ultra-Long-Range Object Detection
Parker Ewen, Dmitriy Rivkin, Mario Bijelic +1
Autonomous highway driving, especially for long-haul heavy trucks, requires detecting objects at long ranges beyond 500 meters to satisfy braking distance requirements at high spee…
ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation
Dmitriy Rivkin, Parker Ewen, Lili Gao +5
Recent video diffusion models achieve high-quality generation through recurrent frame processing where each frame generation depends on previous frames. However, this recurrent mec…
TruckDrive: Long-Range Autonomous Highway Driving Dataset
Filippo Ghilotti, Edoardo Palladin, Samuel Brucker +3
Safe highway autonomy for heavy trucks remains an open and unsolved challenge: due to long braking distances, scene understanding of hundreds of meters is required for anticipatory…
Zero-Shot Depth from Defocus
Yiming Zuo, Hongyu Wen, Venkat Subramanian +5
Depth from Defocus (DfD) is the task of estimating a dense metric depth map from a focus stack. Unlike previous works overfitting to a certain dataset, this paper focuses on the ch…
UniLiPs: Unified LiDAR Pseudo-Labeling with Geometry-Grounded Dynamic Scene Decomposition
Filippo Ghilotti, Samuel Brucker, Nahku Saidy +3
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,…
LSD-3D: Large-Scale 3D Driving Scene Generation with Geometry Grounding
Julian Ost, Andrea Ramazzina, Amogh Joshi +3
Large-scale scene data is essential for training and testing in robot learning. Neural reconstruction methods have promised the capability of reconstructing large physically-ground…
SAMFusion: Sensor-Adaptive Multimodal Fusion for 3D Object Detection in Adverse Weather
Edoardo Palladin, Roland Dietze, Praveen Narayanan +2
Multimodal sensor fusion is an essential capability for autonomous robots, enabling object detection and decision-making in the presence of failing or uncertain inputs. While recen…
Self-Supervised Sparse Sensor Fusion for Long Range Perception
Edoardo Palladin, Samuel Brucker, Filippo Ghilotti +3
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 d…
Beyond Domain Randomization: Event-Inspired Perception for Visually Robust Adversarial Imitation from Videos
Andrea Ramazzina, Vittorio Giammarino, Matteo El-Hariry +1
Imitation from videos often fails when expert demonstrations and learner environments exhibit domain shifts, such as discrepancies in lighting, color, or texture. While visual rand…
Dual Exposure Stereo for Extended Dynamic Range 3D Imaging
Juhyung Choi, Jinnyeong Kim, Seokjun Choi +5
Achieving robust stereo 3D imaging under diverse illumination conditions is an important however challenging task, due to the limited dynamic ranges (DRs) of cameras, which are sig…
Polarization Wavefront Lidar: Learning Large Scene Reconstruction from Polarized Wavefronts
Dominik Scheuble, Chenyang Lei, Seung-Hwan Baek +2
Lidar has become a cornerstone sensing modality for 3D vision, especially for large outdoor scenarios and autonomous driving. Conventional lidar sensors are capable of providing ce…
Gated Fields: Learning Scene Reconstruction from Gated Videos
Andrea Ramazzina, Stefanie Walz, Pragyan Dahal +2
Reconstructing outdoor 3D scenes from temporal observations is a challenge that recent work on neural fields has offered a new avenue for. However, existing methods that recover sc…
HINT: Learning Complete Human Neural Representations from Limited Viewpoints
Alessandro Sanvito, Andrea Ramazzina, Stefanie Walz +2
No augmented application is possible without animated humanoid avatars. At the same time, generating human replicas from real-world monocular hand-held or robotic sensor setups is…
Real-Time Environment Condition Classification for Autonomous Vehicles
Marco Introvigne, Andrea Ramazzina, Stefanie Walz +2
Current autonomous driving technologies are being rolled out in geo-fenced areas with well-defined operation conditions such as time of operation, area, weather conditions and road…
Cross-spectral Gated-RGB Stereo Depth Estimation
Samuel Brucker, Stefanie Walz, Mario Bijelic +1
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-p…
Radar Fields: Frequency-Space Neural Scene Representations for FMCW Radar
David Borts, Erich Liang, Tim Brödermann +9
Neural fields have been broadly investigated as scene representations for the reproduction and novel generation of diverse outdoor scenes, including those autonomous vehicles and r…
Inverse Neural Rendering for Explainable Multi-Object Tracking
Julian Ost, Tanushree Banerjee, Mario Bijelic +1
Today, most methods for image understanding tasks rely on feed-forward neural networks. While this approach has allowed for empirical accuracy, efficiency, and task adaptation via…
Gated Stereo: Joint Depth Estimation from Gated and Wide-Baseline Active Stereo Cues
Stefanie Walz, Mario Bijelic, Andrea Ramazzina +3
We propose Gated Stereo, a high-resolution and long-range depth estimation technique that operates on active gated stereo images. Using active and high dynamic range passive captur…
ScatterNeRF: Seeing Through Fog with Physically-Based Inverse Neural Rendering
Andrea Ramazzina, Mario Bijelic, Stefanie Walz +3
Vision in adverse weather conditions, whether it be snow, rain, or fog is challenging. In these scenarios, scattering and attenuation severly degrades image quality. Handling such…
LiDAR Snowfall Simulation for Robust 3D Object Detection
Martin Hahner, Christos Sakaridis, Mario Bijelic +4
3D object detection is a central task for applications such as autonomous driving, in which the system needs to localize and classify surrounding traffic agents, even in the presen…
Gated2Gated: Self-Supervised Depth Estimation from Gated Images
Amanpreet Walia, Stefanie Walz, Mario Bijelic +5
Gated cameras hold promise as an alternative to scanning LiDAR sensors with high-resolution 3D depth that is robust to back-scatter in fog, snow, and rain. Instead of sequentially…
A Benchmark for Spray from Nearby Cutting Vehicles
Stefanie Walz, Mario Bijelic, Florian Kraus +3
Current driver assistance systems and autonomous driving stacks are limited to well-defined environment conditions and geo fenced areas. To increase driving safety in adverse weath…
ZeroScatter: Domain Transfer for Long Distance Imaging and Vision through Scattering Media
Zheng Shi, Ethan Tseng, Mario Bijelic +2
Adverse weather conditions, including snow, rain, and fog, pose a major challenge for both human and computer vision. Handling these environmental conditions is essential for safe…