Related papers: ADOP: Approximate Differentiable One-Pixel Point R…

Despite considerable progress being achieved in point cloud geometry compression, there still remains a challenge in effectively compressing large-scale scenes with sparse surfaces. Another key challenge lies in reducing decoding latency, a…

Point cloud processing has become a cornerstone technology in many 3D vision tasks. However, arbitrary rotations introduce variations in point cloud orientations, posing a long-standing challenge for effective representation learning. The…

Point cloud analysis is an area of increasing interest due to the development of 3D sensors that are able to rapidly measure the depth of scenes accurately. Unfortunately, applying deep learning techniques to perform point cloud analysis is…

Differentiable rendering is a technique used in an important emerging class of visual computing applications that involves representing a 3D scene as a model that is trained from 2D images using gradient descent. Recent works (e.g. 3D…

Implicit Neural Point Cloud (INPC) is a recent hybrid representation that combines the expressiveness of neural fields with the efficiency of point-based rendering, achieving state-of-the-art image quality in novel view synthesis. However,…

Monocular 3D object detection aims to locate objects in different scenes with just a single image. Due to the absence of depth information, several monocular 3D detection techniques have emerged that rely on auxiliary depth maps from the…

In this paper, we present a novel algorithm for point cloud registration for range sensors capable of measuring per-return instantaneous radial velocity: Doppler ICP. Existing variants of ICP that solely rely on geometry or other features…

Classifier guidance -- using the gradients of an image classifier to steer the generations of a diffusion model -- has the potential to dramatically expand the creative control over image generation and editing. However, currently…

Rendering is the process of generating 2D images from 3D assets, simulated in a virtual environment, typically with a graphics pipeline. By inverting such renderer, one can think of a learning approach to predict a 3D shape from an input…

The primary challenge in accelerating image super-resolution lies in reducing computation while maintaining performance and adaptability. Motivated by the observation that high-frequency regions (e.g., edges and textures) are most critical…

This work considers identifying parameters characterizing a physical system's dynamic motion directly from a video whose rendering configurations are inaccessible. Existing solutions require massive training data or lack generalizability to…

Deep learning has shown remarkable performance in medical image segmentation. However, despite its promise, deep learning has many challenges in practice due to its inability to effectively transition to unseen domains, caused by the…

While commodity GPUs provide a continuously growing range of features and sophisticated methods for accelerating compute jobs, many state-of-the-art solutions for point cloud rendering still rely on the provided point primitives (GL_POINTS,…

In the booming video era, video segmentation attracts increasing research attention in the multimedia community. Semi-supervised video object segmentation (VOS) aims at segmenting objects in all target frames of a video, given annotated…

Autonomous driving in complex urban scenarios requires 3D perception to be both comprehensive and precise. Traditional 3D perception methods focus on object detection, resulting in sparse representations that lack environmental detail.…

We propose a real-time dynamic LiDAR odometry pipeline for mobile robots in Urban Search and Rescue (USAR) scenarios. Existing approaches to dynamic object detection often rely on pretrained learned networks or computationally expensive…

We present Adaptive Instance Selection network architecture for class-agnostic instance segmentation. Given an input image and a point $(x, y)$, it generates a mask for the object located at $(x, y)$. The network adapts to the input point…

Three-dimensional (3D) object recognition is crucial for intelligent autonomous agents such as autonomous vehicles and robots alike to operate effectively in unstructured environments. Most state-of-art approaches rely on relatively dense…

Highly distributed training of Deep Neural Networks (DNNs) on future compute platforms (offering 100 of TeraOps/s of computational capacity) is expected to be severely communication constrained. To overcome this limitation, new gradient…

Abnormalities in pupillary light reflex can indicate optic nerve disorders that may lead to permanent visual loss if not diagnosed in an early stage. In this study, we focus on relative afferent pupillary defect (RAPD), which is based on…