Related papers: NAIMA: Semantics Aware RGB Guided Depth Super-Reso…

Face representation learning solutions have recently achieved great success for various applications such as verification and identification. However, face recognition approaches that are based purely on RGB images rely solely on intensity…

The recent Segment Anything Model (SAM) demonstrates strong instance segmentation performance across various downstream tasks. However, SAM is trained solely on RGB data, limiting its direct applicability to RGB-thermal (RGB-T) semantic…

In this paper, we aim to solve the problem of consistent depth prediction in complex scenes under various illumination conditions. The existing indoor datasets based on RGB-D sensors or virtual rendering have two critical limitations -…

Existing convolutional neural networks (CNN) based image super-resolution (SR) methods have achieved impressive performance on bicubic kernel, which is not valid to handle unknown degradations in real-world applications. Recent blind SR…

With the increasing availability of depth sensors, multimodal frameworks that combine color information with depth data are gaining interest. However, ground truth data for semantic segmentation is burdensome to provide, thus making domain…

The 3D scene understanding is mainly considered as a crucial requirement in computer vision and robotics applications. One of the high-level tasks in 3D scene understanding is semantic segmentation of RGB-Depth images. With the availability…

The introduction of generative models has significantly advanced image super-resolution (SR) in handling real-world degradations. However, they often incur fidelity-related issues, particularly distorting textual structures. In this paper,…

Infrared small target detection remains challenging due to limited feature representation and severe background interference, resulting in sub-optimal performance. While recent CLIP-inspired methods attempt to leverage textual guidance for…

Disentangled representation is a powerful technique to tackle domain shift problem in medical image analysis in unsupervised domain adaptation setting.However, previous methods only focus on exacting domain-invariant feature and ignore…

Recent Reference-Based image super-resolution (RefSR) has improved SOTA deep methods introducing attention mechanisms to enhance low-resolution images by transferring high-resolution textures from a reference high-resolution image. The main…

Image Super-Resolution (SR) aims to reconstruct high-resolution images from degraded low-resolution inputs. While diffusion-based SR methods offer powerful generative capabilities, their performance heavily depends on how semantic priors…

Generalized metric depth understanding is critical for precise vision-guided robotics, which current state-of-the-art (SOTA) vision-encoders do not support. To address this, we propose Vanishing Depth, a self-supervised training approach…

Majority of the perception methods in robotics require depth information provided by RGB-D cameras. However, standard 3D sensors fail to capture depth of transparent objects due to refraction and absorption of light. In this paper, we…

Scene Text Image Super-Resolution (STISR) aims to enhance the resolution and legibility of text within low-resolution (LR) images, consequently elevating recognition accuracy in Scene Text Recognition (STR). Previous methods predominantly…

Recent RGB-D semantic segmentation has motivated research interest thanks to the accessibility of complementary modalities from the input side. Existing works often adopt a two-stream architecture that processes photometric and geometric…

VLA models encode visual observations as 2D patch tokens with no intrinsic geometric structure. We introduce GST-VLA with two contributions. First, the Gaussian Spatial Tokenizer (GST) converts frozen dense depth and frozen semantic patch…

3D perception ability is crucial for generalizable robotic manipulation. While recent foundation models have made significant strides in perception and decision-making with RGB-based input, their lack of 3D perception limits their…

Semantic segmentation is an important task for numerous applications but it is still quite challenging to achieve advanced performance with limited computational costs. In this paper, we present CGRSeg, an efficient yet competitive…

Diffusion-based image super-resolution (SR) methods have demonstrated remarkable performance. Recent advancements have introduced deterministic sampling processes that reduce inference from 15 iterative steps to a single step, thereby…

Despite impressive advancements in Visual-Language Models (VLMs) for multi-modal tasks, their reliance on RGB inputs limits precise spatial understanding. Existing methods for integrating spatial cues, such as point clouds or depth, either…