Related papers: Predict-Optimize-Distill: A Self-Improving Cycle f…
Depth estimation and scene segmentation are two important tasks in intelligent transportation systems. A joint modeling of these two tasks will reduce the requirement for both the storage and training efforts. This work explores how the…
Obtaining accurate 3D object poses is vital for numerous computer vision applications, such as 3D reconstruction and scene understanding. However, annotating real-world objects is time-consuming and challenging. While synthetically…
Optimizing a deep neural network is a fundamental task in computer vision, yet direct training methods often suffer from over-fitting. Teacher-student optimization aims at providing complementary cues from a model trained previously, but…
Video understanding requires not only recognizing visual content but also performing temporally grounded, multi-step reasoning over long and noisy observations. We propose Process-of-Thought (PoT) Reasoning for Videos, a framework that…
Our work learns a unified model for single-view 3D reconstruction of objects from hundreds of semantic categories. As a scalable alternative to direct 3D supervision, our work relies on segmented image collections for learning 3D of generic…
Compact and efficient 6DoF object pose estimation is crucial in applications such as robotics, augmented reality, and space autonomous navigation systems, where lightweight models are critical for real-time accurate performance. This paper…
Out-of-distribution (OOD) detection is essential for ensuring the robustness of machine learning models by identifying samples that deviate from the training distribution. While traditional OOD detection has primarily focused on…
Distilling the structured information captured in feature maps has contributed to improved results for object detection tasks, but requires careful selection of baseline architectures and substantial pre-training. Self-distillation…
In this paper, we propose a simple and general framework for self-supervised point cloud representation learning. Human beings understand the 3D world by extracting two levels of information and establishing the relationship between them.…
In this paper, we introduce a novel single shot approach for 6D object pose estimation of rigid objects based on depth images. For this purpose, a fully convolutional neural network is employed, where the 3D input data is spatially…
Passive methods for object detection and segmentation treat images of the same scene as individual samples and do not exploit object permanence across multiple views. Generalization to novel or difficult viewpoints thus requires additional…
Prediction-based active perception has shown the potential to improve the navigation efficiency and safety of the robot by anticipating the uncertainty in the unknown environment. The existing works for 3D shape prediction make an implicit…
Phase retrieval (PR) reconstructs phase information from magnitude measurements, known as coded diffraction patterns (CDPs), whose quality depends on the number of snapshots captured using coded phase masks. High-quality phase estimation…
Estimating 3D human poses from a monocular video is still a challenging task. Many existing methods' performance drops when the target person is occluded by other objects, or the motion is too fast/slow relative to the scale and speed of…
Despite substantial progress in 3D object detection, advanced 3D detectors often suffer from heavy computation overheads. To this end, we explore the potential of knowledge distillation (KD) for developing efficient 3D object detectors,…
To accommodate rapid changes in the real world, the cognition system of humans is capable of continually learning concepts. On the contrary, conventional deep learning models lack this capability of preserving previously learned knowledge.…
Recent advances in automotive four-dimensional (4D) Radar have enabled access to raw 4D Radar Tensor (4DRT), offering richer spatial and Doppler information than conventional point clouds. While most existing methods rely on heavily…
RGB-D salient object detection (SOD) demonstrates its superiority on detecting in complex environments due to the additional depth information introduced in the data. Inevitably, an independent stream is introduced to extract features from…
Monocular depth estimation plays a fundamental role in computer vision. Due to the costly acquisition of depth ground truth, self-supervised methods that leverage adjacent frames to establish a supervisory signal have emerged as the most…
The modal decomposition techniques of proper orthogonal decomposition (POD) and dynamic mode decomposition (DMD) have become a common method for analysing the spatio-temporal coherence of dynamical systems. In particular, these techniques…