Related papers: SPAN: Spatial-Projection Alignment for Monocular 3…
Learning 3D generative models from a dataset of monocular images enables self-supervised 3D reasoning and controllable synthesis. State-of-the-art 3D generative models are GANs which use neural 3D volumetric representations for synthesis.…
Monocular Simultaneous Localization and Mapping (SLAM) aims to estimate a robot's pose while simultaneously reconstructing an unknown 3D scene using a single camera. While existing monocular SLAM systems generate detailed 3D geometry…
Multi-frame methods improve monocular depth estimation over single-frame approaches by aggregating spatial-temporal information via feature matching. However, the spatial-temporal feature leads to accuracy degradation in dynamic scenes. To…
We present Spann3R, a novel approach for dense 3D reconstruction from ordered or unordered image collections. Built on the DUSt3R paradigm, Spann3R uses a transformer-based architecture to directly regress pointmaps from images without any…
Deep learning-based dense object detectors have achieved great success in the past few years and have been applied to numerous multimedia applications such as video understanding. However, the current training pipeline for dense detectors…
Deep reinforcement learning (RL) is increasingly deployed in resource-constrained environments, yet the go-to function approximators - multilayer perceptrons (MLPs) - are often parameter-inefficient due to an imperfect inductive bias for…
Monocular 3D object detection is a fundamental but very important task to many applications including autonomous driving, robotic grasping and augmented reality. Existing leading methods tend to estimate the depth of the input image first,…
In this paper, we present a monocular Simultaneous Localization and Mapping (SLAM) algorithm using high-level object and plane landmarks. The built map is denser, more compact and semantic meaningful compared to feature point based SLAM. We…
Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection. While effective, existing DA methods suffer from a substantial drop in performance…
The spinal angle is an important indicator of body balance. It is important to restore the 3D shape of the human body and estimate the spine center line. Existing mul-ti-image-based body restoration methods require expensive equipment and…
Monocular simultaneous localization and mapping (SLAM) algorithms estimate drone poses and build a 3D map using a single camera. Current algorithms include sparse methods that lack detailed geometry, while learning-driven approaches produce…
In this paper, we introduce a novel unsupervised domain adaptation technique for the task of 3D keypoint prediction from a single depth scan or image. Our key idea is to utilize the fact that predictions from different views of the same or…
Directly learning multiple 3D objects motion from sequential images is difficult, while the geometric bundle adjustment lacks the ability to localize the invisible object centroid. To benefit from both the powerful object understanding…
Monocular 3D object tracking aims to estimate temporally consistent 3D object poses across video frames, enabling autonomous agents to reason about scene dynamics. However, existing state-of-the-art approaches are fully supervised and rely…
Inferring geometrically consistent dense 3D scenes across a tuple of temporally consecutive images remains challenging for self-supervised monocular depth prediction pipelines. This paper explores how the increasingly popular transformer…
We propose an efficient Stereographic Projection Neural Network (SPNet) for learning representations of 3D objects. We first transform a 3D input volume into a 2D planar image using stereographic projection. We then present a shallow 2D…
Articulation-centric 2D/3D pose supervision forms the core training objective in most existing 3D human pose estimation techniques. Except for synthetic source environments, acquiring such rich supervision for each real target domain at…
Single-view 3D shape retrieval is a fundamental yet challenging task that is increasingly important with the growth of available 3D data. Existing approaches largely fall into two categories: those using contrastive learning to map point…
3D object detection with a single image is an essential and challenging task for autonomous driving. Recently, keypoint-based monocular 3D object detection has made tremendous progress and achieved great speed-accuracy trade-off. However,…
Existing simultaneous localization and mapping (SLAM) algorithms are not robust in challenging low-texture environments because there are only few salient features. The resulting sparse or semi-dense map also conveys little information for…