Vision-based 3D semantic occupancy prediction is essential for autonomous driving, yet dense voxel representations waste computation on largely empty space, while BEV and TPV projections compromise fine-grained 3D structure. Fully sparse representations offer an attractive alternative, but existing methods, including SparseOcc, entangle scene completion with semantic prediction by indiscriminately propagating high-dimensional features into empty regions and applying voxel-wise classification. This creates excessive activations, computational overhead, and geometric ambiguity. We present SparseOcc++, a geometry-aware sparse framework that explicitly decouples scene completion from semantic segmentation. SparseOcc++ reformulates completion as signed-distance regression on sparse anchor voxels through a scene completion field (SCF). To model complex outdoor geometry robustly, it combines orthogonal decomposition with discretized distance learning. A geometry-guided propagation module then converts the SCF into a complete volumetric scene and restricts semantic segmentation to geometrically verified regions. Experiments establish new state of the art: SparseOcc++ improves IoU by 2.3 points and is 3.9x faster than SparseOcc on nuScenes, while achieving a 5.9x speedup over OccFormer on SemanticKITTI.
FSF-Net: Enhance 4D Occupancy Forecasting with Coarse BEV Scene Flow for Autonomous Driving
School of Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）；School of Electrical and Information Engineering, Tianjin University（天津大学电气自动化与信息工程学院）
OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene Generation
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University（电子信息与电气工程学院，上海交通大学）；Ningbo Institute of Digital Twin, Eastern Institute of Technology（宁波数字孪生研究所，东部技术研究所）；PhiGent Robotics, Beijing, China（PhiGent Robotics，北京，中国）
GTAD: Global Temporal Aggregation Denoising Learning for 3D Semantic Occupancy Prediction
Department of Computer and Technology, Fudan University（复旦大学计算机与技术系）；School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）；Shanghai Film Academy of Shanghai University（上海大学上海电影学院）
Autonomous driving requires efficient reasoning about the location and appearance of the different agents in the scene, which aids in downstream tasks such as object detection, object tracking, and path planning. The past few years have witnessed a surge in approaches that combine the different taskbased modules of the classic self-driving stack into an End-toEnd(E2E) trainable learning system. These approaches replace perception, prediction, and sensor fusion modules with a single contiguous module with shared latent space embedding, from which one extracts a human-interpretable representatio…
DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving
School of Computer Science, Peking University（北京大学计算机学院）；Defense Innovation Institute（国防创新研究院）；China Telecom Institute of AI & NPU（中国电信人工智能与NPU研究院）；HKUST（香港科技大学）；GigaAI（极佳科技）；BUPT（北京邮电大学）；Ant Group（蚂蚁集团）；SYSU（中山大学）；THU（清华大学）；BJTU（北京交通大学）
Autonomous driving requires efficient reasoning about the Spatio-temporal nature of the semantics of the scene. Recent approaches have successfully amalgamated the traditional modular architecture of an autonomous driving stack comprising perception, prediction, and planning in an end-to-end trainable system. Such a system calls for a shared latent space embedding with interpretable intermediate trainable projected representation. One such successfully deployed representation is the Bird's-Eye View(BEV) representation of the scene in ego-frame. However, a fundamental assumption for an undistor…
In this report, we introduce our solution to the Occupancy and Flow Prediction challenge in the Waymo Open Dataset Challenges at CVPR 2022, which ranks 1st on the leaderboard. We have developed a novel hierarchical spatial-temporal network featured with spatial-temporal encoders, a multi-scale aggregator enriched with latent variables, and a recursive hierarchical 3D decoder. We use multiple losses including focal loss and modified flow trace loss to efficiently guide the training process. Our method achieves a Flow-Grounded Occupancy AUC of 0.8389 and outperforms all the other teams on the le…
We present Hand ArticuLated Occupancy (HALO), a novel representation of articulated hands that bridges the advantages of 3D keypoints and neural implicit surfaces and can be used in end-to-end trainable architectures. Unlike existing statistical parametric hand models (e.g.~MANO), HALO directly leverages 3D joint skeleton as input and produces a neural occupancy volume representing the posed hand surface. The key benefits of HALO are (1) it is driven by 3D key points, which have benefits in terms of accuracy and are easier to learn for neural networks than the latent hand-model parameters; (2)…
FetchBot: Learning Generalizable Object Fetching in Cluttered Scenes via Zero-Shot Sim2Real
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；CFCS, School of Computer Science, Peking University（计算机科学系，北京大学）；Galbot；Beijing Academy of Artificial Intelligence（北京人工智能研究院）
OSCAR: Occupancy-based Shape Completion via Acoustic Neural Implicit Representations
Chair for Computer Aided Medical Procedures (CAMP) Technical University of Munich（慕尼黑工业大学计算机辅助医疗程序教席（CAMP））；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心（MCML））；Konrad Zuse School of Excellence in Reliable AI (relAI)（康拉德·楚泽可靠人工智能卓越学校（relAI））
ShanghaiTech University（上海科技大学）；University of California San Diego（加州大学圣地亚哥分校）
Recently, Generative Adversarial Networks (GANs)} have been widely used for portrait image generation. However, in the latent space learned by GANs, different attributes, such as pose, shape, and texture style, are generally entangled, making the explicit control of specific attributes difficult. To address this issue, we propose a SofGAN image generator to decouple the latent space of portraits into two subspaces: a geometry space and a texture space. The latent codes sampled from the two subspaces are fed to two network branches separately, one to generate the 3D geometry of portraits with c…
This paper introduces Attentive Implicit Representation Networks (AIR-Nets), a simple, but highly effective architecture for 3D reconstruction from point clouds. Since representing 3D shapes in a local and modular fashion increases generalization and reconstruction quality, AIR-Nets encode an input point cloud into a set of local latent vectors anchored in 3D space, which locally describe the object's geometry, as well as a global latent description, enforcing global consistency. Our model is the first grid-free, encoder-based approach that locally describes an implicit function. The vector at…
