3D visual grounding is the task of localizing the object in a 3D scene w...
Adaptation of semantic segmentation networks to different visual conditi...
We present a simple and practical framework for anomaly segmentation cal...
Recently, indiscernible scene understanding has attracted a lot of atten...
Concealed scene understanding (CSU) is a hot computer vision topic aimin...
Monocular depth estimation is fundamental for 3D scene understanding and...
The burgeoning field of camouflaged object detection (COD) seeks to iden...
Semantic segmentation is a fundamental task in visual scene understandin...
Lidar is a vital sensor for estimating the depth of a scene. Typical spi...
Standard unsupervised domain adaptation methods adapt models from a sour...
The performance of video frame interpolation is inherently correlated wi...
We present a masked vision-language transformer (MVLT) for fashion-speci...
Learning neural fields has been an active topic in deep learning researc...
Due to the scarcity of dense pixel-level semantic annotations for images...
Despite significant academic and corporate efforts, autonomous driving u...
Besides standard cameras, autonomous vehicles typically include multiple...
Monocular depth estimation is vital for scene understanding and downstre...
3D object detection is a central task for applications such as autonomou...
Traditional frame-based cameras inevitably suffer from motion blur due t...
This work addresses the challenging task of LiDAR-based 3D object detect...
Level 5 autonomy for self-driving cars requires a robust visual percepti...
We address the problem of semantic nighttime image segmentation and impr...
This work addresses the problem of semantic scene understanding under fo...
This work addresses the problem of semantic segmentation of nighttime im...
This work addresses the problem of semantic scene understanding under fo...
This work addresses the problem of semantic scene understanding under de...
Object detection typically assumes that training and test data are drawn...
This work addresses the problem of semantic foggy scene understanding (S...
Active contour models based on partial differential equations have prove...