Related papers: Complementary Bi-directional Feature Compression f…

Document image dewarping remains a challenging task in the deep learning era. While existing methods have improved by leveraging text line awareness, they typically focus only on a single horizontal dimension. In this paper, we propose a…

Reasoning segmentation enables open-set object segmentation via implicit text queries, therefore serving as a foundation for embodied agents that should operate autonomously in real-world environments. However, existing methods for…

Semantic segmentation in cataract surgery has a wide range of applications contributing to surgical outcome enhancement and clinical risk reduction. However, the varying issues in segmenting the different relevant structures in these…

One of the practical choices for making a lightweight semantic segmentation model is to combine a depth-wise separable convolution with a dilated convolution. However, the simple combination of these two methods results in an…

Pre-trained on extensive and diverse multi-modal datasets, 2D foundation models excel at addressing 2D tasks with little or no downstream supervision, owing to their robust representations. The emergence of 2D-to-3D distillation frameworks…

Semantic scene completion, also known as semantic occupancy prediction, can provide dense geometric and semantic information for autonomous vehicles, which attracts the increasing attention of both academia and industry. Unfortunately,…

Dataset distillation aims to synthesize a compact dataset from the original large-scale one, enabling highly efficient learning while preserving competitive model performance. However, traditional techniques primarily capture low-level…

In this paper, we address panoramic semantic segmentation which is under-explored due to two critical challenges: (1) image distortions and object deformations on panoramas; (2) lack of semantic annotations in the 360{\deg} imagery. To…

This work investigates learning pixel-wise semantic image segmentation in urban scenes without any manual annotation, just from the raw non-curated data collected by cars which, equipped with cameras and LiDAR sensors, drive around a city.…

We present a novel methodology that combines graph and dense segmentation techniques by jointly learning both point and pixel contour representations, thereby leveraging the benefits of each approach. This addresses deficiencies in typical…

Semantic segmentation necessitates approaches that learn high-level characteristics while dealing with enormous amounts of data. Convolutional neural networks (CNNs) can learn unique and adaptive features to achieve this aim. However, due…

This paper proposes a novel method for omnidirectional 360$\degree$ perception. Most common previous methods relied on equirectangular projection. This representation is easily applicable to 2D operation layers but introduces distortions…

Few-shot segmentation focuses on the generalization of models to segment unseen object with limited annotated samples. However, existing approaches still face two main challenges. First, huge feature distinction between support and query…

Multimodal Dataset Distillation (MDD) seeks to condense large-scale image-text datasets into compact surrogates while retaining their effectiveness for cross-modal learning. Despite recent progress, existing MDD approaches often suffer from…

It is challenging to disentangle an object into two orthogonal spaces of content and style since each can influence the visual observation differently and unpredictably. It is rare for one to have access to a large number of data to help…

3D shape completion from partial scans remains challenging for unseen categories and noisy real-world observations, where geometry alone is often insufficient for inferring missing structure. We present DinoComplete, a deterministic and…

360$^{\circ}$ panoramas are a rich medium, yet notoriously difficult to visualize in the 2D image plane. We explore how intelligent rotations of a spherical image may enable content-aware projection with fewer perceptible distortions.…

Learning to reliably perceive and understand the scene is an integral enabler for robots to operate in the real-world. This problem is inherently challenging due to the multitude of object types as well as appearance changes caused by…

Dataset distillation provides an effective approach to reduce memory and computational costs by optimizing a compact dataset that achieves performance comparable to the full original. However, for large-scale datasets and complex deep…

As a promising approach in model compression, knowledge distillation improves the performance of a compact model by transferring the knowledge from a cumbersome one. The kind of knowledge used to guide the training of the student is…