Related papers: EvidMTL: Evidential Multi-Task Learning for Uncert…
Recent advances in scene understanding benefit a lot from depth maps because of the 3D geometry information, especially in complex conditions (e.g., low light and overexposed). Existing approaches encode depth maps along with RGB images and…
Decoding visual information from time-resolved brain recordings, such as EEG and MEG, plays a pivotal role in real-time brain-computer interfaces. However, existing approaches primarily focus on direct brain-image feature alignment and are…
Conventional visual simultaneous localization and mapping (SLAM) algorithms often fail under rapid motion, low illumination, or abrupt lighting transitions due to motion blur and limited dynamic range. Event cameras mitigate these issues…
This paper proposes a new principled multi-task representation learning framework (InfoMTL) to extract noise-invariant sufficient representations for all tasks. It ensures sufficiency of shared representations for all tasks and mitigates…
Image-based depth estimation has gained significant attention in recent research on computer vision for autonomous vehicles in intelligent transportation systems. This focus stems from its cost-effectiveness and wide range of potential…
Estimating a depth map from a single RGB image has been investigated widely for localization, mapping, and 3-dimensional object detection. Recent studies on a single-view depth estimation are mostly based on deep Convolutional neural…
Monocular depth estimation is challenging due to its inherent ambiguity and ill-posed nature, yet it is quite important to many applications. While recent works achieve limited accuracy by designing increasingly complicated networks to…
Multi-view multi-label classification (MvMLC) is indispensable for modern web applications aggregating information from diverse sources. However, real-world web-scale settings are rife with missing views and continuously emerging classes,…
Reliable scene understanding is indispensable for modern autonomous systems. Current learning-based methods typically try to maximize their performance based on segmentation metrics that only consider the quality of the segmentation.…
Monocular Depth Estimation (MDE) is a fundamental computer vision task with important applications in 3D vision. The current mainstream MDE methods employ an encoder-decoder architecture with multi-level/scale feature processing. However,…
Cross-modal knowledge transfer enhances point cloud representation learning in LiDAR semantic segmentation. Despite its potential, the \textit{weak teacher challenge} arises due to repetitive and non-diverse car camera images and sparse,…
Omnidirectional depth estimation enables efficient 3D perception over a full 360-degree range. However, in real-world applications such as autonomous driving and robotics, achieving real-time performance and robust cross-scene…
Spatial reasoning from monocular images is essential for autonomous driving, yet current Vision-Language Models (VLMs) still struggle with fine-grained geometric perception, particularly under large scale variation and ambiguous object…
Depth information is the foundation of perception, essential for autonomous driving, robotics, and other source-constrained applications. Promptly obtaining accurate and efficient depth information allows for a rapid response in dynamic…
Monocular depth prediction plays a crucial role in understanding 3D scene geometry. Although recent methods have achieved impressive progress in terms of evaluation metrics such as the pixel-wise relative error, most methods neglect the…
Event cameras offer distinct advantages over conventional frame-based sensors, including microsecond-level temporal resolution, high dynamic range, and low bandwidth. In this paper, we predict per-pixel depth distributions from monocular…
Robot navigation in unstructured environments requires multimodal perception systems that can support safe navigation. Multimodality enables the integration of complementary information collected by different sensors. However, this…
In recent years, the parameters of backbones of Video Understanding tasks continue to increase and even reach billion-level. Whether fine-tuning a specific task on the Video Foundation Model or pre-training the model designed for the…
Simultaneous multi-index quantification, segmentation, and uncertainty estimation of liver tumors on multi-modality non-contrast magnetic resonance imaging (NCMRI) are crucial for accurate diagnosis. However, existing methods lack an…
Self-supervised monocular depth estimation has been widely studied, owing to its practical importance and recent promising improvements. However, most works suffer from limited supervision of photometric consistency, especially in weak…