Related papers: Physics-Guided VLM Priors for All-Cloud Removal

Surface reconstruction from point clouds is vital for 3D computer vision. State-of-the-art methods leverage large datasets to first learn local context priors that are represented as neural network-based signed distance functions (SDFs)…

Vision-language models (VLMs) have shown significant promise in remote sensing applications, particularly for land-use and land-cover (LULC) mapping via zero-shot classification and retrieval. However, current approaches face several key…

Cloud removal is an essential task in remote sensing data analysis. As the image sensors are distant from the earth ground, it is likely that part of the area of interests is covered by cloud. Moreover, the atmosphere in between creates a…

Semantic segmentation of remote sensing imagery is fundamental to Earth observation. Achieving accurate results requires integrating not only optical images but also physical variables such as the Digital Elevation Model (DEM), Synthetic…

3D reconstruction from single view images is an ill-posed problem. Inferring the hidden regions from self-occluded images is both challenging and ambiguous. We propose a two-pronged approach to address these issues. To better incorporate…

We address the problem of removing undesirable reflections from a single image captured through a glass surface, which is an ill-posed, challenging but practically important problem for photo enhancement. Inspired by iterative structure…

About half of all optical observations collected via spaceborne satellites are affected by haze or clouds. Consequently, cloud coverage affects the remote sensing practitioner's capabilities of a continuous and seamless monitoring of our…

Vision Language Model (VLM) typically assume complete modality input during inference. However, their effectiveness drops sharply when certain modalities are unavailable or incomplete. Current research on missing modality primarily faces…

Although large vision-language models (LVLMs) have demonstrated impressive capabilities in multi-modal understanding and reasoning, their practical applications are still limited by massive model parameters and high computational costs.…

Despite their impressive capabilities, multimodal large language models (MLLMs) are prone to hallucinations, i.e., the generated content that is nonsensical or unfaithful to input sources. Unlike in LLMs, hallucinations in MLLMs often stem…

Large Language Models (LLMs) have succeeded in a variety of natural language processing tasks [Zha+25]. However, they have notable limitations. LLMs tend to generate hallucinations, a seemingly plausible yet factually unsupported output…

We propose a fast and accurate surface reconstruction algorithm for unorganized point clouds using an implicit representation. Recent learning methods are either single-object representations with small neural models that allow for high…

Multimodal language models (MLLMs) require large parameter capacity to align high-dimensional visual features with linguistic representations, making them computationally heavy and difficult to deploy efficiently. We introduce a progressive…

The generation of factually incorrect objects, commonly known as object hallucination, remains a persistent challenge in Large Vision-Language Models (LVLMs). Current approaches to address this issue - ranging from expensive data-driven…

Large vision-language contrastive models (VLCMs), such as CLIP, have become foundational, demonstrating remarkable success across a variety of downstream tasks. Despite their advantages, these models, akin to other foundational systems,…

Image downscaling and upscaling are two basic rescaling operations. Once the image is downscaled, it is difficult to be reconstructed via upscaling due to the loss of information. To make these two processes more compatible and improve the…

Video Large Language Models (Video LLMs) have shown impressive performance across a wide range of video-language tasks. However, they often fail in scenarios requiring a deeper understanding of physical dynamics. This limitation primarily…

The interpretation of multi-temporal remote sensing imagery is critical for monitoring Earth's dynamic processes-yet previous change detection methods, which produce binary or semantic masks, fall short of providing human-readable insights…

Most current neural networks for reconstructing surfaces from point clouds ignore sensor poses and only operate on raw point locations. Sensor visibility, however, holds meaningful information regarding space occupancy and surface…

Object reconstruction from 3D point clouds has been a long-standing research problem in computer vision and computer graphics, and achieved impressive progress. However, reconstruction from time-varying point clouds (a.k.a. 4D point clouds)…