Related papers: UFO: Unifying Feed-Forward and Optimization-based …
Automatic reconstruction of 3D models from images using multi-view Structure-from-Motion methods has been one of the most fruitful outcomes of computer vision. These advances combined with the growing popularity of Micro Aerial Vehicles as…
The advent of deep learning has led to significant progress in monocular human reconstruction. However, existing representations, such as parametric models, voxel grids, meshes and implicit neural representations, have difficulties…
Driven by the ever-increasing requirements of autonomous vehicles, such as traffic monitoring and driving assistant, deep learning-based object detection (DL-OD) has been increasingly attractive in intelligent transportation systems.…
In this paper, we propose a single UniFied transfOrmer (UFO), which is capable of processing either unimodal inputs (e.g., image or language) or multimodal inputs (e.g., the concatenation of the image and the question), for vision-language…
Unmanned Aerial Vehicles (UAVs) have great potential in urban traffic monitoring due to their rapid speed, cost-effectiveness, and extensive field-of-view, while being unconstrained by traffic congestion. However, their limited flight…
Scaling RL for LLMs is computationally expensive, largely due to multi-sampling for policy optimization and evaluation, making efficient data selection crucial. Inspired by the Zone of Proximal Development (ZPD) theory, we hypothesize LLMs…
We introduce UniCon3R, a unified feed-forward framework for online human-scene 4D reconstruction from monocular video. Current feed-forward human-scene reconstruction methods suffer from artifacts, where bodies float above the ground or…
Reconstructing dynamic assets from video data is central to many in computer vision and graphics tasks. Existing 4D reconstruction approaches are limited by category-specific models or slow optimization-based methods. Inspired by the recent…
In this study, we introduce BirdNeRF, an adaptation of Neural Radiance Fields (NeRF) designed specifically for reconstructing large-scale scenes using aerial imagery. Unlike previous research focused on small-scale and object-centric NeRF…
Urban scene reconstruction is crucial for real-world autonomous driving simulators. Although existing methods have achieved photorealistic reconstruction, they mostly focus on pinhole cameras and neglect fisheye cameras. In fact, how to…
Implicit neural representations have shown promising potential for the 3D scene reconstruction. Recent work applies it to autonomous 3D reconstruction by learning information gain for view path planning. Effective as it is, the computation…
Existing methods for reconstructing objects and humans from a monocular image suffer from severe mesh collisions and performance limitations for interacting occluding objects. This paper introduces a method to obtain a globally consistent…
We propose a feed-forward Gaussian Splatting model that unifies 3D scene and semantic field reconstruction. Combining 3D scenes with semantic fields facilitates the perception and understanding of the surrounding environment. However, key…
We introduce the first approach to solve the challenging problem of unsupervised 4D visual scene understanding for complex dynamic scenes with multiple interacting people from multi-view video. Our approach simultaneously estimates a…
Reconstructing large-scale dynamic driving scenes remains challenging due to the coexistence of static environments with extreme depth variation and diverse dynamic actors exhibiting complex motions. Existing Gaussian Splatting based…
Autonomous driving holds great promise in addressing traffic safety concerns by leveraging artificial intelligence and sensor technology. Multi-Object Tracking plays a critical role in ensuring safer and more efficient navigation through…
Recent advances in implicit scene representation enable high-fidelity street view novel view synthesis. However, existing methods optimize a neural radiance field for each scene, relying heavily on dense training images and extensive…
Achieving safe, high-speed autonomous flight in complex environments with static, dynamic, or mixed obstacles remains challenging, as a single perception modality is incomplete. Depth cameras are effective for static objects but suffer from…
Closed-loop simulation and scalable pre-training for autonomous driving require synthesizing free-viewpoint driving scenes. However, existing datasets and generative pipelines rarely provide consistent off-trajectory observations, limiting…
High-fidelity street scene reconstruction is pivotal for end-to-end autonomous driving simulation, where novel-view synthesis (NVS) and time-varying information modeling are two fundamental capabilities to facilitate closed-loop training.…