Related papers: GARNet: Global-Aware Multi-View 3D Reconstruction …
Models such as VGGT and $\pi^3$ have shown strong multi-view 3D performance, but their heavy reliance on global self-attention results in high computational cost. Existing sparse-attention variants offer partial speedups, yet lack a…
We present a novel end-to-end framework named as GSNet (Geometric and Scene-aware Network), which jointly estimates 6DoF poses and reconstructs detailed 3D car shapes from single urban street view. GSNet utilizes a unique four-way feature…
Feature fusion, the combination of features from different layers or branches, is an omnipresent part of modern network architectures. It is often implemented via simple operations, such as summation or concatenation, but this might not be…
Extensive research has been conducted on assessing grasp stability, a crucial prerequisite for achieving optimal grasping strategies, including the minimum force grasping policy. However, existing works employ basic feature-level fusion…
Multimodal learning has been lacking principled ways of combining information from different modalities and learning a low-dimensional manifold of meaningful representations. We study multimodal learning and sensor fusion from a latent…
Generalizable NeRF aims to synthesize novel views for unseen scenes. Common practices involve constructing variance-based cost volumes for geometry reconstruction and encoding 3D descriptors for decoding novel views. However, existing…
Infrared and visible image fusion aims at generating a fused image containing the intensity and detail information of source images, and the key issue is effectively measuring and integrating the complementary information of multi-modality…
How to learn long-range dependencies from 3D point clouds is a challenging problem in 3D point cloud analysis. Addressing this problem, we propose a global attention network for point cloud semantic segmentation, named as GA-Net, consisting…
Many visual phenomena suggest that humans use top-down generative or reconstructive processes to create visual percepts (e.g., imagery, object completion, pareidolia), but little is known about the role reconstruction plays in robust object…
Image fusion aims to combine information from multiple source images into a single one with more comprehensive informational content. Deep learning-based image fusion algorithms face significant challenges, including the lack of a…
We propose a learned image-guided rendering technique that combines the benefits of image-based rendering and GAN-based image synthesis. The goal of our method is to generate photo-realistic re-renderings of reconstructed objects for…
Geo-localization is a critical task in computer vision. In this work, we cast the geo-localization as a 2D image retrieval task. Current state-of-the-art methods for 2D geo-localization are not robust to locate a scene with drastic scale…
Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio. Machine perception models, in stark contrast, are typically modality-specific and optimised for…
Depth completion is a key task in autonomous driving, aiming to complete sparse LiDAR depth measurements into high-quality dense depth maps through image guidance. However, existing methods usually treat depth maps as an additional channel…
Unlike Object Detection, Visual Grounding task necessitates the detection of an object described by complex free-form language. To simultaneously model such complex semantic and visual representations, recent state-of-the-art studies adopt…
Advanced image fusion methods mostly prioritise high-level missions, where task interaction struggles with semantic gaps, requiring complex bridging mechanisms. In contrast, we propose to leverage low-level vision tasks from digital…
Recent advances in self-attention and pure multi-layer perceptrons (MLP) models for vision have shown great potential in achieving promising performance with fewer inductive biases. These models are generally based on learning interaction…
Infrared and visible image fusion targets to provide an informative image by combining complementary information from different sensors. Existing learning-based fusion approaches attempt to construct various loss functions to preserve…
Reconstruction of a 3D shape from a single 2D image is a classical computer vision problem, whose difficulty stems from the inherent ambiguity of recovering occluded or only partially observed surfaces. Recent methods address this challenge…
Augmentation-based self-supervised learning methods have shown remarkable success in self-supervised visual representation learning, excelling in learning invariant features but often neglecting equivariant ones. This limitation reduces the…