Related papers: UniISP: A Unified ISP Framework for Both Human and…

While traditional methods relies on depth sensors, the current trend leans towards utilizing cost-effective RGB images, despite their absence of depth cues. This paper introduces an interesting approach to detect grasping pose from a single…

Most existing super-resolution methods do not perform well in real scenarios due to lack of realistic training data and information loss of the model input. To solve the first problem, we propose a new pipeline to generate realistic…

Perceiving and reconstructing objects from images are critical for real-to-sim transfer tasks, which are widely used in the robotics community. Existing methods rely on multiple submodules such as detection, segmentation, shape…

Tractable models of human perception have proved to be challenging to build. Hand-designed models such as MS-SSIM remain popular predictors of human image quality judgements due to their simplicity and speed. Recent modern deep learning…

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…

RGB-IR(RGB-Infrared) image pairs are frequently applied simultaneously in various applications like intelligent surveillance. However, as the number of modalities increases, the required data storage and transmission costs also double.…

Cameras currently allow access to two image states: (i) a minimally processed linear raw-RGB image state (i.e., raw sensor data) or (ii) a highly-processed nonlinear image state (e.g., sRGB). There are many computer vision tasks that work…

Lightweight vision networks have witnessed remarkable progress in recent years, yet achieving a satisfactory balance among parameter scale, computational overhead, and task performance remains difficult. Although many existing lightweight…

Existing infrared and visible image fusion methods often face the dilemma of balancing modal information. Generative fusion methods reconstruct fused images by learning from data distributions, but their generative capabilities remain…

Hyperspectral images super-resolution aims to improve the spatial resolution, yet its performance is often limited at high-resolution ratios. The recent adoption of high-resolution reference images for super-resolution is driven by the poor…

Graph neural networks have emerged as a promising paradigm for image processing, yet their performance in image classification tasks is hindered by a limited consideration of the underlying structure and relationships among visual entities.…

In this work, we focus on Interactive Human Parsing (IHP), which aims to segment a human image into multiple human body parts with guidance from users' interactions. This new task inherits the class-aware property of human parsing, which…

One of the main challenges in building a large scale publish-subscribe infrastructure in an enterprise network, is to provide the subscribers with the required information, while minimizing the consumed host and network resources.…

We present UniModel, a unified generative model that jointly supports visual understanding and visual generation within a single pixel-to-pixel diffusion framework. Our goal is to achieve unification along three axes: the model, the tasks,…

Robotic manipulation requires accurate perception of the environment, which poses a significant challenge due to its inherent complexity and constantly changing nature. In this context, RGB image and point-cloud observations are two…

Infrared and visible image fusion aims to generate synthetic images simultaneously containing salient features and rich texture details, which can be used to boost downstream tasks. However, existing fusion methods are suffering from the…

In order to function in unstructured environments, robots need the ability to recognize unseen novel objects. We take a step in this direction by tackling the problem of segmenting unseen object instances in tabletop environments. However,…

Low-light images suffer from severe noise and low illumination. Current deep learning models that are trained with real-world images have excellent noise reduction, but a ratio parameter must be chosen manually to complete the enhancement…

In order to operate autonomously, a robot should explore the environment and build a model of each of the surrounding objects. A common approach is to carefully scan the whole workspace. This is time-consuming. It is also often impossible…

We propose In-Context Translation (ICT), a general learning framework to unify visual recognition (e.g., semantic segmentation), low-level image processing (e.g., denoising), and conditional image generation (e.g., edge-to-image synthesis).…