Related papers: ViBA: Implicit Bundle Adjustment with Geometric an…

This work reports a novel multi-frame Bundle Adjustment (BA) framework called RKHS-BA. It uses continuous landmark representations that encode RGB-D/LiDAR and semantic observations in a Reproducing Kernel Hilbert Space (RKHS). With a…

Recent advances in image editing have been driven by the development of denoising diffusion models, marking a significant leap forward in this field. Despite these advances, the generalization capabilities of recent image editing approaches…

Recent advances in Video Large Language Models (Video-LLMs) have greatly expanded multimodal reasoning capabilities. However, the massive number of visual tokens extracted from long video sequences incurs prohibitive computational costs,…

Visual localization has traditionally been formulated as a pair-wise pose regression problem. Existing approaches mainly estimate relative poses between two images and employ a late-fusion strategy to obtain absolute pose estimates.…

Video-based pretraining offers immense potential for learning strong visual representations on an unprecedented scale. Recently, masked video modeling methods have shown promising scalability, yet fall short in capturing higher-level…

Transformer-based video diffusion models rely on 3D attention over spatial and temporal tokens, which incurs quadratic time and memory complexity and makes end-to-end training for ultra-high-resolution videos prohibitively expensive. To…

Videos captured in low-light and underwater conditions often suffer from distortions such as noise, low contrast, color imbalance, and blur. These issues not only limit visibility but also degrade automatic tasks like detection.…

Infrared and visible image fusion aim to integrate modality strengths for visually enhanced, informative images. Visible imaging in real-world scenarios is susceptible to dynamic environmental brightness fluctuations, leading to texture…

Recently, methods leveraging diffusion model priors to assist monocular geometric estimation (e.g., depth and normal) have gained significant attention due to their strong generalization ability. However, most existing works focus on…

End-to-end reinforcement learning on images showed significant progress in the recent years. Data-based approach leverage data augmentation and domain randomization while representation learning methods use auxiliary losses to learn…

VVI-ReID is a critical technique for all-day surveillance, where temporal information provides additional cues beyond static images. However, existing approaches rely heavily on fully supervised learning with expensive cross-modality…

WiFi-based human pose estimation has emerged as a promising non-visual alternative approaches due to its pene-trability and privacy advantages. This paper presents VST-Pose, a novel deep learning framework for accurate and continuous pose…

The explosive growth of image data facilitates the fast development of image processing and computer vision methods for emerging visual applications, meanwhile introducing novel distortions to the processed images. This poses a grand…

Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level perception with sparse, embodiment-specific action supervision. Since these models typically rely…

Vision-Language-Action (VLA) models often fail to generalize to unseen camera viewpoints, a limitation stemming from their difficulty in inferring robust 3D geometry from 2D images. We introduce GeoAware-VLA, a simple yet effective approach…

Heatmap regression based face alignment has achieved prominent performance on static images. However, the stability and accuracy are remarkably discounted when applying the existing methods on dynamic videos. We attribute the degradation to…

An enormous and ever-growing volume of data is nowadays becoming available in a sequential fashion in various real-world applications. Learning in nonstationary environments constitutes a major challenge, and this problem becomes orders of…

This paper introduces a novel approach to Visual Forced Alignment (VFA), aiming to accurately synchronize utterances with corresponding lip movements, without relying on audio cues. We propose a novel VFA approach that integrates a local…

Multi-view depth estimation has achieved impressive performance over various benchmarks. However, almost all current multi-view systems rely on given ideal camera poses, which are unavailable in many real-world scenarios, such as autonomous…

Recent advancements in keypoint detection and descriptor extraction have shown impressive performance in local feature learning tasks. However, existing methods generally exhibit suboptimal performance under extreme conditions such as…