Related papers: LiftProj: Space Lifting and Projection-Based Panor…

Open-world 3D generation has recently attracted considerable attention. While many single-image-to-3D methods have yielded visually appealing outcomes, they often lack sufficient controllability and tend to produce hallucinated regions that…

Volumetric video relighting is essential for bringing captured performances into virtual worlds, but current approaches struggle to deliver temporally stable, production-ready results. Diffusion-based intrinsic decomposition methods show…

We propose R3GS, a robust reconstruction and relocalization framework tailored for unconstrained datasets. Our method uses a hybrid representation during training. Each anchor combines a global feature from a convolutional neural network…

Sparse-view 3D reconstruction is essential for applications in which dense image acquisition is impractical, such as robotics, augmented/virtual reality (AR/VR), and autonomous systems. In these settings, minimal image overlap prevents…

We address the problems of measuring geometric similarity between 3D scenes, represented through point clouds or range data frames, and associating them. Our approach leverages macro-scale 3D structural geometry - the relative configuration…

Ghost projection is the reversed process of computational classical ghost imaging that allows any desired image to be synthesized using a linear combination of illuminating patterns. Typically, physical attenuating masks are used to produce…

We introduce the task of mixed-view panorama synthesis, where the goal is to synthesize a novel panorama given a small set of input panoramas and a satellite image of the area. This contrasts with previous work which only uses input…

Panoptic segmentation of 3D scenes, involving the segmentation and classification of object instances in a dense 3D reconstruction of a scene, is a challenging problem, especially when relying solely on unposed 2D images. Existing…

Image generation technology can synthesize condition-specific images to supplement real-world industrial anomaly data and enhance anomaly detection model performance. Existing generation techniques rarely account for the pose and…

3D geometric information is essential for manipulation tasks, as robots need to perceive the 3D environment, reason about spatial relationships, and interact with intricate spatial configurations. Recent research has increasingly focused on…

Region-based methods have become increasingly popular for model-based, monocular 3D tracking of texture-less objects in cluttered scenes. However, while they achieve state-of-the-art results, most methods are computationally expensive,…

We present uLayout, a unified model for estimating room layout geometries from both perspective and panoramic images, whereas traditional solutions require different model designs for each image type. The key idea of our solution is to…

Visual relocalization is a fundamental task in the field of 3D computer vision, estimating a camera's pose when it revisits a previously known scene. While point-based hierarchical relocalization methods have shown strong scalability and…

3D Gaussian Splatting SLAM has emerged as a widely used technique for high-fidelity mapping in spatial intelligence. However, existing methods often rely on a single representation scheme, which limits their performance in large-scale…

Single-view indoor scene generation plays a crucial role in a range of real-world applications. However, generating a complete 360{\deg} scene from a single image remains a highly ill-posed and challenging problem. Recent approaches have…

Generating ground-level views and coherent 3D site models from aerial-only imagery is challenging due to extreme viewpoint changes, missing intermediate observations, and large scale variations. Existing methods either refine renderings…

3D Gaussian Splatting (GS) enables fast and high-quality scene reconstruction, but it lacks an object-consistent and semantically aware structure. We propose Split&Splat, a framework for panoptic scene reconstruction using 3DGS. Our…

Articulation-centric 2D/3D pose supervision forms the core training objective in most existing 3D human pose estimation techniques. Except for synthetic source environments, acquiring such rich supervision for each real target domain at…

Data augmentation is crucial for improving the robustness of face detection systems, especially under challenging conditions such as occlusion, illumination variation, and complex environments. Traditional copy paste augmentation often…

Due to the current lack of large-scale datasets at the million-scale level, tasks involving panoramic images predominantly rely on existing two-dimensional pre-trained image benchmark models as backbone networks. However, these networks are…