Related papers: OccScene: Semantic Occupancy-based Cross-task Mutu…

This paper presents a novel generative approach that outputs 3D indoor environments solely from a textual description of the scene. Current methods often treat scene synthesis as a mere layout prediction task, leading to rooms with…

Generating high-fidelity 3D indoor scenes remains a significant challenge due to data scarcity and the complexity of modeling intricate spatial relations. Current methods often struggle to scale beyond training distribution to dense scenes…

Generating explorable 3D scenes from a single image is a highly challenging problem in 3D vision. Existing methods struggle to support free exploration, often producing severe geometric distortions and noisy artifacts when the viewpoint…

World models are critical for autonomous driving to simulate environmental dynamics and generate synthetic data. Existing methods struggle to disentangle ego-vehicle motion (perspective shifts) from scene evolvement (agent interactions),…

3D semantic occupancy prediction aims to obtain 3D fine-grained geometry and semantics of the surrounding scene and is an important task for the robustness of vision-centric autonomous driving. Most existing methods employ dense grids such…

The 3D occupancy estimation task has become an important challenge in the area of vision-based autonomous driving recently. However, most existing camera-based methods rely on costly 3D voxel labels or LiDAR scans for training, limiting…

3D scene flow estimation is a vital tool in perceiving our environment given depth or range sensors. Unlike optical flow, the data is usually sparse and in most cases partially occluded in between two temporal samplings. Here we propose a…

Vision-based 3D semantic occupancy prediction is vital for autonomous driving, enabling unified modeling of static infrastructure and dynamic agents. Global occupancy maps serve as long-term memory priors, providing valuable historical…

In this paper we propose USegScene, a framework for semantically guided unsupervised learning of depth, optical flow and ego-motion estimation for stereo camera images using convolutional neural networks. Our framework leverages semantic…

Learning-based 3D Scanning plays a crucial role in enabling efficient and accurate scanning of target objects. However, recent reinforcement learning-based methods often require large-scale training data and still struggle to generalize to…

Modern learning-based approaches to 3D-aware image synthesis achieve high photorealism and 3D-consistent viewpoint changes for the generated images. Existing approaches represent instances in a shared canonical space. However, for…

Designing 3D scenes is traditionally a challenging task that demands both artistic expertise and proficiency with complex software. Recent advances in text-to-3D generation have greatly simplified this process by letting users create scenes…

While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model which addresses both families of tasks simultaneously. We…

This paper focuses on semantic scene completion, a task for producing a complete 3D voxel representation of volumetric occupancy and semantic labels for a scene from a single-view depth map observation. Previous work has considered scene…

Robust perception in automated driving requires reliable performance under adverse conditions, where sensors may be affected by partial failures or environmental occlusions. Although existing autonomous driving datasets inherently contain…

Image fusion is a crucial technique in the field of computer vision, and its goal is to generate high-quality fused images and improve the performance of downstream tasks. However, existing fusion methods struggle to balance these two…

Diffusion models has emerged as a powerful framework for tasks like image controllable generation and dense prediction. However, existing models often struggle to capture underlying semantics (e.g., edges, textures, shapes) and effectively…

3D occupancy prediction holds significant promise in the fields of robot perception and autonomous driving, which quantifies 3D scenes into grid cells with semantic labels. Recent works mainly utilize complete occupancy labels in 3D voxel…

Humans possess the cognitive ability to comprehend scenes in a compositional manner. To empower AI systems with similar capabilities, object-centric learning aims to acquire representations of individual objects from visual scenes without…

The Class Incremental Semantic Segmentation (CISS) extends the traditional segmentation task by incrementally learning newly added classes. Previous work has introduced generative replay, which involves replaying old class samples generated…