Ensuring safety in autonomous driving requires scalable generation of realistic, controllable driving scenes beyond what real-world testing provides. Yet existing instruction guided image editors, trained on object-centric or artistic data, struggle with dense, safety-critical driving layouts. We propose HorizonWeaver, which tackles three fundamental challenges in driving scene editing: (1) multi-level granularity, requiring coherent object- and scene-level edits in dense environments; (2) rich high-level semantics, preserving diverse objects while following detailed instructions; and (3) ubiquitous domain shifts, handling changes in climate, layout, and traffic across unseen environments. The core of HorizonWeaver is a set of complementary contributions across data, model, and training: (1) Data: Large-scale dataset generation, where we build a paired real/synthetic dataset from Boreas, nuScenes, and Argoverse2 to improve generalization; (2) Model: Language-Guided Masks for fine-grained editing, where semantics-enriched masks and prompts enable precise, language-guided edits; and (3) Training: Content preservation and instruction alignment, where joint losses enforce scene consistency and instruction fidelity. Together, HorizonWeaver provides a scalable framework for photorealistic, instruction-driven editing of complex driving scenes, collecting 255K images across 13 editing categories and outperforming prior methods in L1, CLIP, and DINO metrics, achieving +46.4% user preference and improving BEV segmentation IoU by +33%. Project page: https://msoroco.github.io/horizonweaver/
In Vision-and-Language Navigation (VLN), an agent needs to navigate through the environment based on natural language instructions. Due to limited available data for agent training and finite diversity in navigation environments, it is challenging for the agent to generalize to new, unseen environments. To address this problem, we propose EnvEdit, a data augmentation method that creates new environments by editing existing environments, which are used to train a more generalizable agent. Our augmented environments can differ from the seen environments in three diverse aspects: style, object ap…
RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models
Southern University of Science and Technology（南方科技大学）；StepFun；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shenzhen University of Advanced Technology（深圳理工大学）
DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving
The Hong Kong University of Science & Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science & Technology（香港科技大学）；University of California, Berkeley（加州大学伯克利分校）；PhiGent Robotics（菲境机器人）
StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation
The University of British Columbia（不列颠哥伦比亚大学）；ETH Zürich（苏黎世联邦理工学院）；McMaster University（麦马斯特大学）；Vector Institute（向量研究所）；Canada CIFAR AI Chair（加拿大 CIFAR 人工智能主席）
Stanford University（斯坦福大学）；Adobe Research（Adobe研究院）；University College London（伦敦大学学院）
Neural representations are popular for representing shapes, as they can be learned form sensor data and used for data cleanup, model completion, shape editing, and shape synthesis. Current neural representations can be categorized as either overfitting to a single object instance, or representing a collection of objects. However, neither allows accurate editing of neural scene representations: on the one hand, methods that overfit objects achieve highly accurate reconstructions, but do not generalize to unseen object configurations and thus cannot support editing; on the other hand, methods th…
School of Cyber Science and Engineering（网络安全科学与工程学院）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；State Key Laboratory of Cyberspace Security Defense（网络空间安全防御国家重点实验室）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）
GenMix: Effective Data Augmentation with Generative Diffusion Model Image Editing
School of Computing and Information Systems, The University of Melbourne, Australia（墨尔本大学计算与信息系统学院）；Mohamed bin Zayed University of Artificial Intelligence, UAE（人工智能 Mohamed bin Zayed 大学）；Information Technology University, Punjab, Pakistan（巴基斯坦旁遮普信息科技大学）
Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation
Shanghai Jiao Tong University（上海交通大学）；Ningbo Institute of Digital Twin, Eastern Institute of Technology（东方理工大学宁波数字孪生研究院）；University of Science and Technology of China（中国科学技术大学）；The University of Hong Kong（香港大学）
Where Detectors Fail: Probing Generative Space for Generalizable AI-Generated Image Detection
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China（中山大学计算机科学与工程学院）；Australian National University, Canberra, Australia（澳大利亚国立大学）；Peng Cheng Laboratory, Shenzhen, China（鹏城实验室）；Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China（清华大学深圳国际研究生学院）
RoadGIE: Towards A Global-Scale Aerial Benchmark for Generalizable Interactive Road Extraction
NKIARI, Shenzhen Futian（深圳福田NKIARI）；VCIP, CS, Nankai University（南开大学VCIP研究所）；AAIS, Nankai University（南开大学AAIS）；College of Electronic Engineering, National University of Defense Technology, Changsha, China（国防科技大学电子工程学院，长沙，中国）
AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editing
Sydney AI Centre, The University of Sydney（悉尼人工智能中心，悉尼大学）；University of Technology Sydney（技术大学悉尼）；University of Melbourne（墨尔本大学）；Hong Kong Baptist University（香港 Baptist 大学）；Mohamed bin Zayed University of Artificial Intelligence（Mohamed bin Zayed 人工智能大学）
Generalizable Face Landmarking Guided by Conditional Face Warping
School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Key Laboratory of Artificial Intelligence, Ministry of Education, Shanghai（上海 教育部人工智能重点实验室）
3D generative models of objects enable photorealistic image synthesis with 3D control. Existing methods model the scene as a global scene representation, ignoring the compositional aspect of the scene. Compositional reasoning can enable a wide variety of editing applications, in addition to enabling generalizable 3D reasoning. In this paper, we present a compositional generative model, where each semantic part of the object is represented as an independent 3D representation learned from only in-the-wild 2D data. We start with a global generative model (GAN) and learn to decompose it into diffe…
VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction
Peking University（北京大学）；Tencent（腾讯）；The Chinese University of Hong Kong（香港中文大学）；Shanghai AI Lab（上海人工智能实验室）；NTU Singapore（新加坡国立大学）；Zhongguancun Academy（中关村学院）；Beijing Key Lab of Data Intel. & Security (PKU)（北京数据智能与安全实验室（北京大学））
