Understanding objects in 3D from a single image is a cornerstone of spatial intelligence. A key step toward this goal is monocular 3D object detection--recovering the extent, location, and orientation of objects from an input RGB image. To be practical in the open world, such a detector must generalize beyond closed-set categories, support diverse prompt modalities, and leverage geometric cues when available. Progress is hampered by two bottlenecks: existing methods are designed for a single prompt type and lack a mechanism to incorporate additional geometric cues, and current 3D datasets cover only narrow categories in controlled environments, limiting open-world transfer. In this work we address both gaps. First, we introduce WildDet3D, a unified geometry-aware architecture that natively accepts text, point, and box prompts and can incorporate auxiliary depth signals at inference time. Second, we present WildDet3D-Data, the largest open 3D detection dataset to date, constructed by generating candidate 3D boxes from existing 2D annotations and retaining only human-verified ones, yielding over 1M images across 13.5K categories in diverse real-world scenes. WildDet3D establishes a new state-of-the-art across multiple benchmarks and settings. In the open-world setting, it achieves 22.6/24.8 AP3D on our newly introduced WildDet3D-Bench with text and box prompts. On Omni3D, it reaches 34.2/36.4 AP3D with text and box prompts, respectively. In zero-shot evaluation, it achieves 40.3/48.9 ODS on Argoverse 2 and ScanNet. Notably, incorporating depth cues at inference time yields substantial additional gains (+20.7 AP on average across settings).
HyperSAM: A Promptable Foundation Model for Hyperspectral Remote Sensing
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；Helmholtz-Zentrum Dresden-Rossendorf（亥姆霍兹德累斯顿罗森多夫研究中心）；University of Iceland（冰岛大学）；Griffith University（格里菲斯大学）
Taming SAM3 in the Wild: A Concept Bank for Open-Vocabulary Segmentation
Department of Electrical and Computer Engineering, Sungkyunkwan University（Sungkyunkwan 大学电气与计算机工程系）；School of Computing and Artificial Intelligence, Southwest Jiaotong University（西南交通大学计算机与人工智能学院）；School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；School of Computer Science and Engineering, University of Electronic Science and Technology of China（中国电子科技大学计算机科学与工程学院）
SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild
University of Cambridge（剑桥大学）；Southern University of Science and Technology（南方科技大学）；Tsinghua University（清华大学）；IMATI-CNR, Milan, Italy（意大利米兰IMATI-CNR研究所）
本文提出SAM 3D Animal，首个可提示的多动物3D重建框架，基于SMAL+参数化动物模型，通过关键点和掩码提示实现拥挤和遮挡场景的可靠重建，利用Herd3D数据集在多个数据集上取得最优结果。
Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shanghai AI Laboratory（上海人工智能实验室）；The Hong Kong Polytechnic University（香港理工大学）；ARC Lab, Tencent PCG（腾讯平台与内容事业群ARC实验室）；The Chinese University of Hong Kong（香港中文大学）
TransCAB: Transferable Clean-Annotation Backdoor to Object Detection with Natural Trigger in Real-World
The University of Adelaide（阿德莱德大学）；Data61, CSIRO（澳大利亚联邦科学与工业研究组织Data61）；Nanjing University of Science and Technology（南京理工大学）；The University of Western Australia（西澳大学）
OpenCVL: An Open, Diverse, and Large-Scale Dataset for Fine-Grained Cross-View Localization
École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；Southern University of Science and Technology (SUSTech)（南方科技大学）；Delft University of Technology（代尔夫特理工大学）；Zenseact（Zenseact公司）
Real-world face recognition applications often deal with suboptimal image quality or resolution due to different capturing conditions such as various subject-to-camera distances, poor camera settings, or motion blur. This characteristic has an unignorable effect on performance. Recent cross-resolution face recognition approaches used simple, arbitrary, and unrealistic down- and up-scaling techniques to measure robustness against real-world edge-cases in image quality. Thus, we propose a new standardized benchmark dataset and evaluation protocol derived from the famous Labeled Faces in the Wild…
Diffusion Models are Efficient Data Generators for Human Mesh Recovery
The University of Adelaide（阿德莱德大学）；Zhejiang University（浙江大学）；Zhejiang University of Technology（浙江工业大学）；The University of Hong Kong（香港大学）；SenseTime（秒针科技）
In this work, we focus on the task of learning and representing dense correspondences in deformable object categories. While this problem has been considered before, solutions so far have been rather ad-hoc for specific object types (i.e., humans), often with significant manual work involved. However, scaling the geometry understanding to all objects in nature requires more automated approaches that can also express correspondences between related, but geometrically different objects. To this end, we propose a new, learnable image-based representation of dense correspondences. Our model predic…
A central goal of visual recognition is to understand objects and scenes from a single image. 2D recognition has witnessed tremendous progress thanks to large-scale learning and general-purpose representations. Comparatively, 3D poses new challenges stemming from occlusions not depicted in the image. Prior works try to overcome these by inferring from multiple views or rely on scarce CAD models and category-specific priors which hinder scaling to novel settings. In this work, we explore single-view 3D reconstruction by learning generalizable representations inspired by advances in self-supervi…
College of Information Science and Engineering, Northeastern University（东北大学信息科学与工程学院）；Ant Group（蚂蚁集团）；Shanghai Jiao Tong University（上海交通大学）；Alibaba Group（阿里巴巴集团）；HKUST（香港科技大学）
In this work, we explore self-supervised visual pre-training on images from diverse, in-the-wild videos for real-world robotic tasks. Like prior work, our visual representations are pre-trained via a masked autoencoder (MAE), frozen, and then passed into a learnable control module. Unlike prior work, we show that the pre-trained representations are effective across a range of real-world robotic tasks and embodiments. We find that our encoder consistently outperforms CLIP (up to 75%), supervised ImageNet pre-training (up to 81%), and training from scratch (up to 81%). Finally, we train a 307M p…
