Related papers: FvOR: Robust Joint Shape and Pose Optimization for…

This paper is about reducing the cost of building good large-scale 3D reconstructions post-hoc. We render 2D views of an existing reconstruction and train a convolutional neural network (CNN) that refines inverse-depth to match a…

3D reconstruction aims to recover the dense 3D structure of a scene. It plays an essential role in various applications such as Augmented/Virtual Reality (AR/VR), autonomous driving and robotics. Leveraging multiple views of a scene…

We present FLARE, a feed-forward model designed to infer high-quality camera poses and 3D geometry from uncalibrated sparse-view images (i.e., as few as 2-8 inputs), which is a challenging yet practical setting in real-world applications.…

Reconstructing an intensity image from the events of a moving event camera is a challenging task that is typically approached with neural networks deployed on graphics processing units. This paper presents a much simpler, FIlter Based…

Robots and other smart devices need efficient object-based scene representations from their on-board vision systems to reason about contact, physics and occlusion. Recognized precise object models will play an important role alongside…

Neural implicit representations have revolutionized dense multi-view surface reconstruction, yet their performance significantly diminishes with sparse input views. A few pioneering works have sought to tackle the challenge of sparse-view…

We present an approach to recover absolute 3D human poses from multi-view images by incorporating multi-view geometric priors in our model. It consists of two separate steps: (1) estimating the 2D poses in multi-view images and (2)…

3D object pose estimation is a challenging task. Previous works always require thousands of object images with annotated poses for learning the 3D pose correspondence, which is laborious and time-consuming for labeling. In this paper, we…

With Fourier sensing, it is commonly the case that the field-of-view (FOV), the area of space to be imaged, is known prior to reconstruction. To date, reconstruction algorithms have focused on FOVs with simple geometries: a rectangle or a…

We introduce a simple yet effective algorithm that uses convolutional neural networks to directly estimate object poses from videos. Our approach leverages the temporal information from a video sequence, and is computationally efficient and…

Realtime 4D reconstruction for dynamic scenes remains a crucial challenge for autonomous driving perception. Most existing methods rely on depth estimation through self-supervision or multi-modality sensor fusion. In this paper, we propose…

Robots operating at night using conventional vision cameras face significant challenges in reconstruction due to noise-limited images. Previous work has demonstrated that burst-imaging techniques can be used to partially overcome this…

3D spatial perception is fundamental to generalizable robotic manipulation, yet obtaining reliable, high-quality 3D geometry remains challenging. Depth sensors suffer from noise and material sensitivity, while existing reconstruction models…

3D face reconstruction (3DFR) algorithms are based on specific assumptions tailored to distinct application scenarios. These assumptions limit their use when acquisition conditions, such as the subject's distance from the camera or the…

We present a learning framework that learns to recover the 3D shape, pose and texture from a single image, trained on an image collection without any ground truth 3D shape, multi-view, camera viewpoints or keypoint supervision. We approach…

Lidars and cameras are critical sensors that provide complementary information for 3D detection in autonomous driving. While prevalent multi-modal methods simply decorate raw lidar point clouds with camera features and feed them directly to…

Recent works on 6D object pose estimation focus on learning keypoint correspondences between images and object models, and then determine the object pose through RANSAC-based algorithms or by directly regressing the pose with end-to-end…

Neural rendering has advanced significantly in 3D reconstruction and novel view synthesis, and integrating physics into these frameworks opens new applications such as physically accurate digital twins for robotics and XR. However, the…

Camera pose estimation is a key step in standard 3D reconstruction pipelines that operate on a dense set of images of a single object or scene. However, methods for pose estimation often fail when only a few images are available because…

The challenging task of 3D planar reconstruction from images involves several sub-tasks including frame-wise plane detection, segmentation, parameter regression and possibly depth prediction, along with cross-frame plane correspondence and…