Related papers: Pose Optimization for Autonomous Driving Datasets …
Neural implicit representations such as NeRF have revolutionized 3D scene representation with photo-realistic quality. However, existing methods for visual localization within NeRF representations suffer from inefficiency and scalability…
Accurate 3D object pose estimation is key to enabling many robotic applications that involve challenging object interactions. In this work, we show that the density field created by a state-of-the-art efficient radiance field reconstruction…
Autonomous mobile robots (AMRs) equipped with high-quality cameras have revolutionized the field of inspections by providing efficient and cost-effective means of conducting surveys. The use of autonomous inspection is becoming more…
Accurate camera localization is crucial for modern retail environments, enabling enhanced customer experiences, streamlined inventory management, and autonomous operations. While Absolute Pose Regression (APR) from a single image offers a…
Spacecraft pose estimation networks require tens of thousands of CAD-rendered images to be trained. This reliance on synthetic CAD data (i) limits applicability to targets with reliable geometry prior, excluding uncooperative or poorly…
Driving scenes are extremely diverse and complicated that it is impossible to collect all cases with human effort alone. While data augmentation is an effective technique to enrich the training data, existing methods for camera data in…
Autonomous vehicles such as the Mars rovers currently lead the vanguard of surface exploration on extraterrestrial planets and moons. In order to accelerate the pace of exploration and science objectives, it is critical to plan safe and…
Reconstructing from multi-view images is a longstanding problem in 3D vision, where neural radiance fields (NeRFs) have shown great potential and get realistic rendered images of novel views. Currently, most NeRF methods either require…
Neural radiance fields (NeRFs) have emerged as a prominent pre-training paradigm for vision-centric autonomous driving, which enhances 3D geometry and appearance understanding in a fully self-supervised manner. To apply NeRF-based…
We present the first method capable of photorealistically reconstructing deformable scenes using photos/videos captured casually from mobile phones. Our approach augments neural radiance fields (NeRF) by optimizing an additional continuous…
Consistent motion estimation is fundamental for all mobile autonomous systems. While this sounds like an easy task, often, it is not the case because of changing environmental conditions affecting odometry obtained from vision, Lidar, or…
Precise camera localization is a critical task in XR applications and robotics. Using only the camera captures as input to a system is an inexpensive option that enables localization in large indoor and outdoor environments, but it presents…
Autonomous vehicles rely extensively on perception systems to navigate and interpret their surroundings. Despite significant advancements in these systems recently, challenges persist under conditions like occlusion, extreme lighting, or in…
Neural Radiance Fields (NeRF) is an emerging technique to synthesize 3D objects from 2D images with a wide range of potential applications. However, rendering existing NeRF models is extremely computation intensive, making it challenging to…
Neural Radiance Fields (NeRF) show impressive performance for the photorealistic free-view rendering of scenes. However, NeRFs require dense sampling of images in the given scene, and their performance degrades significantly when only a…
Neural surface reconstruction relies heavily on accurate camera poses as input. Despite utilizing advanced pose estimators like COLMAP or ARKit, camera poses can still be noisy. Existing pose-NeRF joint optimization methods handle poses…
Depth estimation is a fundamental component of spatial perception for autonomous driving and other unmanned systems operating in open urban environments. Existing depth datasets such as KITTI, nuScenes, and DDAD have advanced the field but…
While deep learning reshaped the classical motion capture pipeline with feed-forward networks, generative models are required to recover fine alignment via iterative refinement. Unfortunately, the existing models are usually hand-crafted or…
Most state-of-the-art works in trajectory forecasting for automotive target predicting the pose and orientation of the agents in the scene. This represents a particularly useful problem, for instance in autonomous driving, but it does not…
Autonomous driving simulation system plays a crucial role in enhancing self-driving data and simulating complex and rare traffic scenarios, ensuring navigation safety. However, traditional simulation systems, which often heavily rely on…