Related papers: TrajVG: 3D Trajectory-Coupled Visual Geometry Lear…
Real-world applications like video gaming and virtual reality often demand the ability to model 3D scenes that users can explore along custom camera trajectories. While significant progress has been made in generating 3D objects from text…
We introduce a novel task of 3D visual grounding in monocular RGB images using language descriptions with both appearance and geometry information. Specifically, we build a large-scale dataset, Mono3DRefer, which contains 3D object targets…
Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving. However, there still lacks a driving-targeted dense geometry perception model that can adapt to different scenarios and camera…
Most model-free visual object tracking methods formulate the tracking task as object location estimation given by a 2D segmentation or a bounding box in each video frame. We argue that this representation is limited and instead propose to…
Multi-object tracking (MOT) in monocular videos is fundamentally challenged by occlusions and depth ambiguity, issues that conventional tracking-by-detection (TBD) methods struggle to resolve owing to a lack of geometric awareness. To…
Despite the significant improvement in the performance of monocular pose estimation approaches and their ability to generalize to unseen environments, multi-view (MV) approaches are often lagging behind in terms of accuracy and are specific…
We present a technique for a complete 3D reconstruction of small objects moving in front of a textured background. It is a particular variation of multibody structure from motion, which specializes to two objects only. The scene is captured…
We present a convolutional neural network for joint 3D shape prediction and viewpoint estimation from a single input image. During training, our network gets the learning signal from a silhouette of an object in the input image - a form of…
Visual-based perception is the key module for autonomous driving. Among those visual perception tasks, video object detection is a primary yet challenging one because of feature degradation caused by fast motion or multiple poses. Current…
Cross-view geo-localization aims at localizing a ground-level query image by matching it to its corresponding geo-referenced aerial view. In real-world scenarios, the task requires accommodating diverse ground images captured by users with…
Being able to generate realistic trajectory options is at the core of increasing the degree of automation of road vehicles. While model-driven, rule-based, and classical learning-based methods are widely used to tackle these tasks at…
Reconstructing dynamic objects from monocular videos is a severely underconstrained and challenging problem, and recent work has approached it in various directions. However, owing to the ill-posed nature of this problem, there has been no…
Existing multi-view image compression methods often rely on 2D projection-based similarities between views to estimate disparities. While effective for small disparities, such as those in stereo images, these methods struggle with the more…
Recent generative models can produce high-fidelity videos, yet they often exhibit 3D spatial geometric inconsistencies. Existing evaluation methods fail to accurately characterize these inconsistencies: fidelity-centric metrics like FVD are…
Recent text-to-image models, such as Stable Diffusion, have achieved impressive visual quality, yet they often suffer from geometric inconsistencies that undermine the structural realism of generated scenes. One prominent issue is vanishing…
Image-based 3D reconstruction or 3D photogrammetry of small-scale objects including insects and biological specimens is challenging due to the use of high magnification lens with inherent limited depth of field, and the object's fine…
The field of multiple view geometry has seen tremendous progress in reconstruction and calibration due to methods for extracting reliable point features and key developments in projective geometry. Point features, however, are not available…
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 fine-tuning, it also comes with fundamental disadvantages.…
3D multi-object tracking (MOT) is vital for many applications including autonomous driving vehicles and service robots. With the commonly used tracking-by-detection paradigm, 3D MOT has made important progress in recent years. However,…
Recent advances in 3D Gaussian Splatting (3DGS) have enabled RGB-only SLAM systems to achieve high-fidelity scene representation. However, the heavy reliance of existing systems on photometric rendering loss for camera tracking undermines…