Related papers: CountFormer: Multi-View Crowd Counting Transformer
This paper presents Volumetric Transformer Pose estimator (VTP), the first 3D volumetric transformer framework for multi-view multi-person 3D human pose estimation. VTP aggregates features from 2D keypoints in all camera views and directly…
Recent advances in 3D foundation models have led to growing interest in reconstructing humans and their surrounding environments. However, most existing approaches focus on monocular inputs, and extending them to multi-view settings…
Current object detectors typically have a feature pyramid (FP) module for multi-level feature fusion (MFF) which aims to mitigate the gap between features from different levels and form a comprehensive object representation to achieve…
GigaMVS presents several challenges to existing Multi-View Stereo (MVS) algorithms for its large scale, complex occlusions, and gigapixel images. To address these problems, we first apply one of the state-of-the-art learning-based MVS…
Recognizing target objects using an event-based camera draws more and more attention in recent years. Existing works usually represent the event streams into point-cloud, voxel, image, etc, and learn the feature representations using…
We present XFormer, a novel human mesh and motion capture method that achieves real-time performance on consumer CPUs given only monocular images as input. The proposed network architecture contains two branches: a keypoint branch that…
Local feature matching is a computationally intensive task at the subpixel level. While detector-based methods coupled with feature descriptors struggle in low-texture scenes, CNN-based methods with a sequential extract-to-match pipeline,…
Video captioning is an advanced multi-modal task which aims to describe a video clip using a natural language sentence. The encoder-decoder framework is the most popular paradigm for this task in recent years. However, there exist some…
Crowd counting is a challenging yet critical task in computer vision with applications ranging from public safety to urban planning. Recent advances using Convolutional Neural Networks (CNNs) that estimate density maps have shown…
Visual segmentation seeks to partition images, video frames, or point clouds into multiple segments or groups. This technique has numerous real-world applications, such as autonomous driving, image editing, robot sensing, and medical…
We propose DeepMultiCap, a novel method for multi-person performance capture using sparse multi-view cameras. Our method can capture time varying surface details without the need of using pre-scanned template models. To tackle with the…
Point clouds are a very efficient way to represent volumetric data in medical imaging. First, they do not occupy resources for empty spaces and therefore can avoid trade-offs between resolution and field-of-view for voxel-based 3D…
This paper aims to address the problem of supervised monocular depth estimation. We start with a meticulous pilot study to demonstrate that the long-range correlation is essential for accurate depth estimation. Therefore, we propose to…
Crowd counting models in highly congested areas confront two main challenges: weak localization ability and difficulty in differentiating between foreground and background, leading to inaccurate estimations. The reason is that objects in…
Moving object detection and segmentation from a single moving camera is a challenging task, requiring an understanding of recognition, motion and 3D geometry. Combining both recognition and reconstruction boils down to a fusion problem,…
Novel view synthesis (NVS) boosts immersive experiences in computer vision and graphics. Existing techniques, though progressed, rely on dense multi-view observations, restricting their application. This work takes on the challenge of…
Image captioning is shown to be able to achieve a better performance by using scene graphs to represent the relations of objects in the image. The current captioning encoders generally use a Graph Convolutional Net (GCN) to represent the…
Monocular depth estimation (MDE) has attracted increasing interest in the past few years, owing to its important role in 3D vision. MDE is the estimation of a depth map from a monocular image/video to represent the 3D structure of a scene,…
Unsupervised learning of object-centric representations in dynamic visual scenes is challenging. Unlike most previous approaches that learn to decompose 2D images, we present DynaVol, a 3D scene generative model that unifies geometric…
Numerous studies have investigated the pivotal role of reliable 3D volume representation in scene perception tasks, such as multi-view stereo (MVS) and semantic scene completion (SSC). They typically construct 3D probability volumes…