Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignment
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）理工学院）；Shanghai Ai Lab（上海人工智能实验室）；Faculty of Geosciences and Engineering, Southwest Jiaotong University（西南交通大学地球科学与工程学院）
Cloud removal (CR) is essential for optical remote sensing, serving as a prerequisite for reliable downstream interpretation, such as semantic segmentation and change detection. However, existing CR approaches often prioritize visual realism while overlooking their impact on subsequent analytical tasks, leading to semantic drift and degraded downstream performance. To address this issue, we propose Geo-Anchored Cloud Removal (GACR), a unified framework that jointly ensures faithful reconstruction and robust interpretability. At its core, GACR incorporates Observation-Anchored Residual Flow (OAR-Flow), which reformulates CR as a physically grounded residual inversion process. By anchoring the generative trajectory to the cloudy observation rather than pure noise, OAR-Flow enables fast, stable, and faithful reconstruction. To further preserve semantic structures critical for downstream interpretation, GACR integrates Geo-Contextual Prior Alignment (GCPA) to constrain the reconstruction within a semantic manifold induced by a Vision Foundation Model (VFM). Consequently, GACR strictly maintains the spatial-semantic integrity of complex landscapes. Extensive experiments across six CR datasets and twelve downstream tasks demonstrate that GACR produces superior reconstruction quality while consistently improving downstream task accuracy. The code is available at https://github.com/wzy6055/GACR.
We address the problem of detecting and erasing furniture from a wide angle photograph of a room. Inpainting large regions of an indoor scene often results in geometric inconsistencies of background elements within the inpaint mask. To address this problem, we utilize perceptual information (e.g. instance segmentation, and room layout) to produce a geometrically consistent empty version of a room. We share important details to make this system viable, such as per-plane inpainting, automatic rectification, and texture refinement. We provide detailed ablation along with qualitative examples, jus…
Dynamic objects have a significant impact on the robot's perception of the environment which degrades the performance of essential tasks such as localization and mapping. In this work, we address this problem by synthesizing plausible color, texture and geometry in regions occluded by dynamic objects. We propose the novel geometry-aware DynaFill architecture that follows a coarse-to-fine topology and incorporates our gated recurrent feedback mechanism to adaptively fuse information from previous timesteps. We optimize our architecture using adversarial training to synthesize fine realistic tex…
GeoFF3D: Coordinate-Anchored Feed-Forward Reconstruction for Large-Scale UAV Mapping
Central South University（中南大学）；Hunan Engineering Research Center of 3D Real Scene Construction and Application Technology（湖南省3D真实场景构建与应用技术工程研究中心）；National University of Defense Technology（国防科技大学）
DAMA: Disentangled Body-Anchored Gaussians for Controllable Multi-Layered Avatars
University of Tübingen（图宾根大学）；Tübingen AI Center（图宾根人工智能中心）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Max Planck Institute for Informatics（马克斯·普朗克信息研究所）；Zuse School ELIZA（祖斯学校ELIZA）
MSVS-VAE: Multi-Scale Anchored VecSet for High-Fidelity 3D Reconstruction
The Hong Kong University of Science and Technology（香港科技大学）；Peking University（北京大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Lightspeed Studios（光速工作室）
Australian National University（澳大利亚国立大学）；Beijing Institute of Technology（北京理工大学）；Tencent（腾讯）
Images captured in snowy days suffer from noticeable degradation of scene visibility, which degenerates the performance of current vision-based intelligent systems. Removing snow from images thus is an important topic in computer vision. In this paper, we propose a Deep Dense Multi-Scale Network (\textbf{DDMSNet}) for snow removal by exploiting semantic and geometric priors. As images captured in outdoor often share similar scenes and their visibility varies with depth from camera, such semantic and geometric information provides a strong prior for snowy image restoration. We incorporate the s…
GRAR: Glass-induced Reflection Artifact Removal in LiDAR Point Clouds
College of Computer Science and Electronic Engineering, Hunan University（湖南大学计算机科学与电子工程学院）；School of Design, Hunan University（湖南大学设计学院）；School of Finance and Statistics, Hunan University（湖南大学金融与统计学院）
FrameTwin: Curve-Anchored Gaussian Alignment from Sparse Views for Adaptive Wireframe 3D Printing
Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong（香港中文大学机械与自动化工程系）；Centre of Perceptual and Interactive Intelligence, Hong Kong（香港感知与交互智能中心）；University of Manchester（曼彻斯特大学）；Department of Mechanical and Aerospace Engineering, The University of Manchester, United Kingdom（曼彻斯特大学机械与航空航天工程系）
Inception Institute of Artificial Intelligence（人工智能初学者研究所）；ReLER, University of Technology Sydney（悉尼科技大学ReLER）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
While single-view 3D reconstruction has made significant progress benefiting from deep shape representations in recent years, garment reconstruction is still not solved well due to open surfaces, diverse topologies and complex geometric details. In this paper, we propose a novel learnable Anchored Unsigned Distance Function (AnchorUDF) representation for 3D garment reconstruction from a single image. AnchorUDF represents 3D shapes by predicting unsigned distance fields (UDFs) to enable open garment surface modeling at arbitrary resolution. To capture diverse garment topologies, AnchorUDF not o…
CoGeo-GS: Concept-Driven and Geometry-Aware Multi-Object Removal in 3D Scenes
Southern University of Science and Technology（南方科技大学）；ByteDance（字节跳动）；Zhejiang University（浙江大学）；Fudan University（复旦大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
HiSfM: Disambiguating Structure-from-Motion via Scaffold-Anchored Hierarchical Reconstruction
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Language as an Anchor: Preserving Relative Visual Geometry for Domain Incremental Learning
School of Computer Science and Engineering, Southeast University, China（东南大学计算机科学与工程学院）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Ministry of Education, China（教育部新一代人工智能技术及其交叉应用重点实验室）；Nanjing University of Science and Technology, China（南京理工大学）
University of Science and Technology of China（中国科学技术大学）
Geometry-based point cloud compression (G-PCC) can achieve remarkable compression efficiency for point clouds. However, it still leads to serious attribute compression artifacts, especially under low bitrate scenarios. In this paper, we propose a Multi-Scale Graph Attention Network (MS-GAT) to remove the artifacts of point cloud attributes compressed by G-PCC. We first construct a graph based on point cloud geometry coordinates and then use the Chebyshev graph convolutions to extract features of point cloud attributes. Considering that one point may be correlated with points both near and far …
Optical remote sensing imagery has been widely used in many fields due to its high resolution and stable geometric properties. However, remote sensing imagery is inevitably affected by climate, especially clouds. Removing the cloud in the high-resolution remote sensing satellite image is an indispensable pre-processing step before analyzing it. For the sake of large-scale training data, neural networks have been successful in many image processing tasks, but the use of neural networks to remove cloud in remote sensing imagery is still relatively small. We adopt generative adversarial network t…
Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）；Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院（KAIST））
Conebeam CT using a circular trajectory is quite often used for various applications due to its relative simple geometry. For conebeam geometry, Feldkamp, Davis and Kress algorithm is regarded as the standard reconstruction method, but this algorithm suffers from so-called conebeam artifacts as the cone angle increases. Various model-based iterative reconstruction methods have been developed to reduce the cone-beam artifacts, but these algorithms usually require multiple applications of computational expensive forward and backprojections. In this paper, we develop a novel deep learning approac…
Machine Unlearning in Hyperbolic vs. Euclidean Multimodal Contrastive Learning: Adapting Alignment Calibration to MERU
Aalborg University（奥尔堡大学）；University of Barcelona（巴塞罗那大学）；Computer Vision Center（计算机视觉中心）；Milestone Systems（里程碑系统公司）；Pioneer Center for Artificial Intelligence（先锋人工智能中心）
