Related papers: GeomPrompt: Geometric Prompt Learning for RGB-D Se…

Multimodal Large Language Models (MLLMs) demonstrate exceptional semantic reasoning but struggle with 3D spatial perception when restricted to pure RGB inputs. Despite leveraging implicit geometric priors from 3D reconstruction models,…

Although deep neural networks have provided impressive gains in performance, these improvements often come at the cost of increased computational complexity and expense. In many cases, such as 3D volume or video classification tasks, not…

We rethink the segment anything model (SAM) and propose a novel multiprompt network called COMPrompter for camouflaged object detection (COD). SAM has zero-shot generalization ability beyond other models and can provide an ideal framework…

Geometric Problem Solving (GPS) poses a unique challenge for Multimodal Large Language Models (MLLMs), requiring not only the joint interpretation of text and diagrams but also iterative visuospatial reasoning. While existing approaches…

Image restoration has always been a cutting-edge topic in the academic and industrial fields of computer vision. Since degradation signals are often random and diverse, "all-in-one" models that can do blind image restoration have been…

The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and predict'' paradigm through prompt learning to induce…

Visible-modal object tracking gives rise to a series of downstream multi-modal tracking tributaries. To inherit the powerful representations of the foundation model, a natural modus operandi for multi-modal tracking is full fine-tuning on…

Multimodal semantic communication has gained widespread attention due to its ability to enhance downstream task performance. A key challenge in such systems is the effective fusion of features from different modalities, which requires the…

While most current RGB-D-based category-level object pose estimation methods achieve strong performance, they face significant challenges in scenes lacking depth information. In this paper, we propose a novel category-level object pose…

Monocular depth inference is a fundamental problem for scene perception of robots. Specific robots may be equipped with a camera plus an optional depth sensor of any type and located in various scenes of different scales, whereas recent…

The problem of detecting changes in a scene and segmenting the foreground from background is still challenging, despite previous work. Moreover, new RGBD capturing devices include depth cues, which could be incorporated to improve…

Prompt-driven image analysis converts a single natural-language instruction into multiple steps: locate, segment, edit, and describe. We present a practical case study of a unified pipeline that combines open-vocabulary detection,…

Video depth estimation extends monocular prediction into the temporal domain to ensure coherence. However, existing methods often suffer from spatial blurring in fine-detail regions and temporal inconsistencies. We argue that current…

Objects may appear at arbitrary scales in perspective images of a scene, posing a challenge for recognition systems that process images at a fixed resolution. We propose a depth-aware gating module that adaptively selects the pooling field…

Monocular omnidirectional depth estimation is receiving considerable research attention due to its broad applications for sensing 360{\deg} surroundings. Existing approaches in this field suffer from limitations in recovering small object…

Cryo-electron microscopy (cryo-EM) remains pivotal in structural biology, yet the task of protein particle picking, integral for 3D protein structure construction, is laden with manual inefficiencies. While recent AI tools such as Topaz and…

The Segment Anything Model (SAM) has demonstrated its effectiveness in segmenting any part of 2D RGB images. However, SAM exhibits a stronger emphasis on texture information while paying less attention to geometry information when…

In recent years, soft prompt learning methods have been proposed to fine-tune large-scale vision-language pre-trained models for various downstream tasks. These methods typically combine learnable textual tokens with class tokens as input…

The primary challenge of cross-domain few-shot segmentation (CD-FSS) is the domain disparity between the training and inference phases, which can exist in either the input data or the target classes. Previous models struggle to learn…

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…