Related papers: Robust Bayesian Scene Reconstruction with Retrieva…
Recent 3D-based manipulation methods either directly predict the grasp pose using 3D neural networks, or solve the grasp pose using similar objects retrieved from shape databases. However, the former faces generalizability challenges when…
We present the first real-time system capable of tracking and reconstructing, individually, every visible object in a given scene, without any form of prior on the rigidness of the objects, texture existence, or object category. In contrast…
Humans excel in grasping and manipulating objects because of their life-long experience and knowledge about the 3D shape and weight distribution of objects. However, the lack of such intuition in robots makes robotic grasping an…
In computer graphics and vision, recovering easily modifiable scene appearance from image data is crucial for applications such as content creation. We introduce a novel method that integrates 3D Gaussian Splatting with an implicit surface…
Implicit neural representation has demonstrated promising results in 3D reconstruction on various scenes. However, existing approaches either struggle to model fast-moving objects or are incapable of handling large-scale camera ego-motions…
Consider scene understanding problems such as predicting where a person is probably reaching, or inferring the pose of 3D objects from depth images, or inferring the probable street crossings of pedestrians at a busy intersection. This…
We propose R3GS, a robust reconstruction and relocalization framework tailored for unconstrained datasets. Our method uses a hybrid representation during training. Each anchor combines a global feature from a convolutional neural network…
We present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing radiance field reconstruction approaches rely on accurate…
The data consistency for the physical forward model is crucial in inverse problems, especially in MR imaging reconstruction. The standard way is to unroll an iterative algorithm into a neural network with a forward model embedded. The…
As generative models become increasingly capable of producing high-fidelity visual content, the demand for efficient, interpretable, and editable image representations has grown substantially. Recent advances in 2D Gaussian Splatting (2DGS)…
Robotic grasping is a cornerstone capability of embodied systems. Many methods directly output grasps from partial information without modeling the geometry of the scene, leading to suboptimal motion and even collisions. To address these…
Feed-forward 3D reconstruction from sparse, low-resolution (LR) images is a crucial capability for real-world applications, such as autonomous driving and embodied AI. However, existing methods often fail to recover fine texture details.…
Implicit neural representation has paved the way for new approaches to dynamic scene reconstruction and rendering. Nonetheless, cutting-edge dynamic neural rendering methods rely heavily on these implicit representations, which frequently…
Robust 3D representation learning forms the perceptual foundation of spatial intelligence, enabling downstream tasks in scene understanding and embodied AI. However, learning such representations directly from unposed multi-view images…
We present a framework that enables fast reconstruction and real-time rendering of urban-scale scenes while maintaining robustness against appearance variations across multi-view captures. Our approach begins with scene partitioning for…
Pose estimation of 3D objects in monocular images is a fundamental and long-standing problem in computer vision. Existing deep learning approaches for 6D pose estimation typically rely on the assumption of availability of 3D object models…
The presence of occlusions has provided substantial challenges to typically-powerful object recognition algorithms. Additional sources of information can be extremely valuable to reduce errors caused by occlusions. Scene context is known to…
Implicit neural 3D representation has achieved impressive results in surface or scene reconstruction and novel view synthesis, which typically uses the coordinate-based multi-layer perceptrons (MLPs) to learn a continuous scene…
The introduction of the neural implicit representation has notably propelled the advancement of online dense reconstruction techniques. Compared to traditional explicit representations, such as TSDF, it improves the mapping completeness and…
3D Gaussian Splatting (3DGS) has gained significant attention for its real-time, photo-realistic rendering in novel-view synthesis and 3D modeling. However, existing methods struggle with accurately modeling scenes affected by transient…