Related papers: DeS3: Adaptive Attention-driven Self and Soft Shad…
Instance shadow detection is a brand new problem, aiming to find shadow instances paired with object instances. To approach it, we first prepare a new dataset called SOBA, named after Shadow-OBject Association, with 3,623 pairs of shadow…
We present a diffusion-based portrait shadow removal approach that can robustly produce high-fidelity results. Unlike previous methods, we cast shadow removal as diffusion-based inpainting. To this end, we first train a shadow-independent…
Monocular 3D object detection (M3OD) is a significant yet inherently challenging task in autonomous driving due to absence of explicit depth cues in a single RGB image. In this paper, we strive to boost currently underperforming monocular…
This study addresses the challenge of performing visual localization in demanding conditions such as night-time scenarios, adverse weather, and seasonal changes. While many prior studies have focused on improving image-matching performance…
Realtime 4D reconstruction for dynamic scenes remains a crucial challenge for autonomous driving perception. Most existing methods rely on depth estimation through self-supervision or multi-modality sensor fusion. In this paper, we propose…
A Vision Transformer (ViT) is a simple neural architecture amenable to serve several computer vision tasks. It has limited built-in architectural priors, in contrast to more recent architectures that incorporate priors either about the…
Non-line-of-sight (NLOS) imaging of objects not visible to either the camera or illumination source is a challenging task with vital applications including surveillance and robotics. Recent NLOS reconstruction advances have been achieved…
Visual attention helps achieve robust perception under noise, corruption, and distribution shifts in human vision, which are areas where modern neural networks still fall short. We present VARS, Visual Attention from Recurrent Sparse…
Self-supervised monocular depth estimation (MDE) models universally suffer from the notorious edge-fattening issue. Triplet loss, as a widespread metric learning strategy, has largely succeeded in many computer vision applications. In this…
Vision Transformers (ViTs) often degrade under distribution shifts because they rely on spurious correlations, such as background cues, rather than semantically meaningful features. Existing regularization methods, typically relying on…
Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling (MIM), there is no significant difference in essence, that is, how to design proper pretext tasks for vision…
In recent years, various shadow detection methods from a single image have been proposed and used in vision systems; however, most of them are not appropriate for the robotic applications due to the expensive time complexity. This paper…
Although the recent image-based 3D object detection methods using Pseudo-LiDAR representation have shown great capabilities, a notable gap in efficiency and accuracy still exist compared with LiDAR-based methods. Besides, over-reliance on…
Existing portrait relighting methods struggle with precise control over facial shadows, particularly when faced with challenges such as handling hard shadows from directional light sources or adjusting shadows while remaining in harmony…
Face anti-spoofing (FAS) or presentation attack detection is an essential component of face recognition systems deployed in security-critical applications. Existing FAS methods have poor generalizability to unseen spoof types, camera…
We introduce a variational method for multi-view shape-from-shading under natural illumination. The key idea is to couple PDE-based solutions for single-image based shape-from-shading problems across multiple images and multiple color…
Removing objects from images is a challenging problem that is important for many applications, including mixed reality. For believable results, the shadows that the object casts should also be removed. Current inpainting-based methods only…
In this paper we present S3R-Net, the Self-Supervised Shadow Removal Network. The two-branch WGAN model achieves self-supervision relying on the unify-and-adaptphenomenon - it unifies the style of the output data and infers its…
With a wide range of shadows in many collected images, shadow removal has aroused increasing attention since uncontaminated images are of vital importance for many downstream multimedia tasks. Current methods consider the same convolution…
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…