Related papers: SeeThrough3D: Occlusion Aware 3D Control in Text-t…
3D Gaussian Splatting can exploit frustum culling and level-of-detail strategies to accelerate rendering of scenes containing a large number of primitives. However, the semi-transparent nature of Gaussians prevents the application of…
Text- or image-to-3D generators and 3D scanners can now produce 3D assets with high-quality shapes and textures. These assets typically consist of a single, fused representation, like an implicit neural field, a Gaussian mixture, or a mesh,…
Generating immersive 3D scenes from texts is a core task in computer vision, crucial for applications in virtual reality and game development. Despite the promise of leveraging 2D diffusion priors, existing methods suffer from spatial…
Image matching is a fundamental and critical task in various visual applications, such as Simultaneous Localization and Mapping (SLAM) and image retrieval, which require accurate pose estimation. However, most existing methods ignore the…
Open-vocabulary 3D visual grounding and reasoning aim to localize objects in a scene based on implicit language descriptions, even when they are occluded. This ability is crucial for tasks such as vision-language navigation and autonomous…
Recently, deep learning-based 3D face reconstruction methods have demonstrated promising advancements in terms of quality and efficiency. Nevertheless, these techniques face challenges in effectively handling occluded scenes and fail to…
In autonomous driving, monocular sequences contain lots of information. Monocular depth estimation, camera ego-motion estimation and optical flow estimation in consecutive frames are high-profile concerns recently. By analyzing tasks above,…
Recent remarkable advances in large-scale text-to-image diffusion models have inspired a significant breakthrough in text-to-3D generation, pursuing 3D content creation solely from a given text prompt. However, existing text-to-3D…
We present a method that can recognize new objects and estimate their 3D pose in RGB images even under partial occlusions. Our method requires neither a training phase on these objects nor real images depicting them, only their CAD models.…
OCR-based image captioning is an important but under-explored task, aiming to generate descriptions containing visual objects and scene text. Recent studies have made encouraging progress, but they are still suffering from a lack of overall…
Our brain can effortlessly recognize objects even when partially hidden from view. Seeing the visible of the hidden is called amodal completion; however, this task remains a challenge for generative AI despite rapid progress. We propose to…
Despite rapid progress in Visual question answering (VQA), existing datasets and models mainly focus on testing reasoning in 2D. However, it is important that VQA models also understand the 3D structure of visual scenes, for example to…
A key challenge for LiDAR-based 3D object detection is to capture sufficient features from large scale 3D scenes especially for distant or/and occluded objects. Albeit recent efforts made by Transformers with the long sequence modeling…
The completion, extension, and generation of 3D semantic scenes are an interrelated set of capabilities that are useful for robotic navigation and exploration. Existing approaches seek to decouple these problems and solve them one-off.…
The presence of occlusions has provided substantial challenges to typically-powerful object recognition algorithms. Additional sources of information can be extremely valuable to reduce errors caused by occlusions. Scene context is known to…
Severe occlusions of objects pose a major challenge for computer vision. We show that two root causes are (1) the loss of visible information and (2) the distracting patterns caused by the occluders. Our approach addresses both causes at…
Generating complete 3D objects under partial occlusions (i.e., amodal scenarios) is a practically important yet challenging problem, as large portions of object geometry are unobserved in real-world scenarios. Existing approaches either…
3D understanding and rendering of moving humans from monocular videos is a challenging task. Despite recent progress, the task remains difficult in real-world scenarios, where obstacles may block the camera view and cause partial occlusions…
Camera-based 3D Semantic Scene Completion (SSC) is a critical task for autonomous driving and robotic scene understanding. It aims to infer a complete 3D volumetric representation of both semantics and geometry from a single image. Existing…
Current approaches to semantic image and scene understanding typically employ rather simple object representations such as 2D or 3D bounding boxes. While such coarse models are robust and allow for reliable object detection, they discard…