Related papers: ESCAPE: Equivariant Shape Completion via Anchor Po…

Boundary representation (B-rep) is the industry standard for computer-aided design (CAD). While deep learning shows promise in processing B-rep models, existing methods suffer from a representation gap: continuous approaches offer…

In this paper we introduce EfficientPose, a new approach for 6D object pose estimation. Our method is highly accurate, efficient and scalable over a wide range of computational resources. Moreover, it can detect the 2D bounding box of…

Finding correspondences between images or 3D scans is at the heart of many computer vision and image retrieval applications and is often enabled by matching local keypoint descriptors. Various learning approaches have been applied in the…

Estimating 3D from 2D is one of the central tasks in computer vision. In this work, we consider the monocular setting, i.e. single-view input, for 3D human pose estimation (HPE). Here, the task is to predict a 3D point set of human skeletal…

Visual place recognition methods struggle with occlusions and partial visual overlaps. We propose a novel visual place recognition approach based on overlap prediction, called VOP, shifting from traditional reliance on global image…

Given a single scene image, this paper proposes a method of Category-level 6D Object Pose and Size Estimation (COPSE) from the point cloud of the target object, without external real pose-annotated training data. Specifically, beyond the…

Directly regressing all 6 degrees-of-freedom (6DoF) for the object pose (e.g. the 3D rotation and translation) in a cluttered environment from a single RGB image is a challenging problem. While end-to-end methods have recently demonstrated…

The task of crafting procedural programs capable of generating structurally valid 3D shapes easily and intuitively remains an elusive goal in computer vision and graphics. Within the graphics community, generating procedural 3D models has…

This letter presents KGpose, a novel end-to-end framework for 6D pose estimation of multiple objects. Our approach combines keypoint-based method with learnable pose regression through `keypoint-graph', which is a graph representation of…

The unpaired point cloud completion task aims to complete a partial point cloud by using models trained with no ground truth. Existing unpaired point cloud completion methods are class-aware, i.e., a separate model is needed for each object…

Transformer-based end-to-end speech recognition models have received considerable attention in recent years due to their high training speed and ability to model a long-range global context. Position embedding in the transformer…

It is at times important to detect human presence automatically in secure environments. This needs a shape recognition algorithm that is robust, fast and has low error rates. The algorithm needs to process camera images quickly to detect…

Worldwide Geo-localization aims to pinpoint the precise location of images taken anywhere on Earth. This task has considerable challenges due to immense variation in geographic landscapes. The image-to-image retrieval-based approaches fail…

Vision Transformers have demonstrated remarkable success in computer vision tasks, yet their reliance on learnable one-dimensional positional embeddings fundamentally disrupts the inherent two-dimensional spatial structure of images through…

Autonomous driving scenes range from empty highways to dense intersections with dozens of interacting road users, yet current 3D detection models apply a fixed computation budget to every frame, wasting resources on simple scenes while…

Transformers have demonstrated outstanding performance in many applications of deep learning. When applied to time series data, transformers require effective position encoding to capture the ordering of the time series data. The efficacy…

Human pose estimation (HPE) usually requires large-scale training data to reach high performance. However, it is rather time-consuming to collect high-quality and fine-grained annotations for human body. To alleviate this issue, we revisit…

360{\deg} images are widely available over the last few years. This paper proposes a new technique for single 360{\deg} image depth prediction under open environments. Depth prediction from a 360{\deg} single image is not easy for two…

For robot manipulation, a complete and accurate object shape is desirable. Here, we present a method that combines visual and haptic reconstruction in a closed-loop pipeline. From an initial viewpoint, the object shape is reconstructed…

State-of-the-art object pose estimation handles multiple instances in a test image by using multi-model formulations: detection as a first stage and then separately trained networks per object for 2D-3D geometric correspondence prediction…