Related papers: Enhancing High-Resolution 3D Generation through Pi…

Large-scale scene data is essential for training and testing in robot learning. Neural reconstruction methods have promised the capability of reconstructing large physically-grounded outdoor scenes from captured sensor data. However, these…

3D scene generation has long been dominated by 2D multi-view or video diffusion models. This is due not only to the lack of scene-level 3D latent representation, but also to the fact that most scene-level 3D visual data exists in the form…

Recently, the text-to-3D task has developed rapidly due to the appearance of the SDS method. However, the SDS method always generates 3D objects with poor quality due to the over-smooth issue. This issue is attributed to two factors: 1) the…

3D scene reconstruction is fundamental for spatial intelligence applications such as AR, robotics, and digital twins. Traditional multi-view stereo struggles with sparse viewpoints or low-texture regions, while neural rendering approaches,…

While recent generative models for 2D images achieve impressive visual results, they clearly lack the ability to perform 3D reasoning. This heavily restricts the degree of control over generated objects as well as the possible applications…

Along with the breakthrough of convolutional neural networks, learning-based segmentation has emerged in many research works. Most of them are based on supervised learning, requiring plenty of annotated data; however, to support…

High-resolution video generation has emerged as a crucial task in computer vision, with wide-ranging applications in entertainment, simulation, and data augmentation. However, generating temporally coherent and visually realistic videos…

Fine-tuning over large pretrained language models (PLMs) has established many state-of-the-art results. Despite its superior performance, such fine-tuning can be unstable, resulting in significant variance in performance and potential risks…

Vision-based grasp estimation is an essential part of robotic manipulation tasks in the real world. Existing planar grasp estimation algorithms have been demonstrated to work well in relatively simple scenes. But when it comes to complex…

3D content creation has achieved significant progress in terms of both quality and speed. Although current feed-forward models can produce 3D objects in seconds, their resolution is constrained by the intensive computation required during…

3D Gaussian Splatting (3DGS) has emerged as a novel explicit representation for 3D scenes, offering both high-fidelity reconstruction and efficient rendering. However, 3DGS lacks 3D segmentation ability, which limits its applicability in…

Time varying sequences of 3D point clouds, or 4D point clouds, are now being acquired at an increasing pace in several applications (e.g., LiDAR in autonomous or assisted driving). In many cases, such volume of data is transmitted, thus…

3D-aware generative models have shown that the introduction of 3D information can lead to more controllable image generation. In particular, the current state-of-the-art model GIRAFFE can control each object's rotation, translation, scale,…

Score-based generative models (SGMs) have recently emerged as a promising class of generative models. The key idea is to produce high-quality images by recurrently adding Gaussian noises and gradients to a Gaussian sample until converging…

Image-based 3D generation has vast applications in robotics and gaming, where high-quality, diverse outputs and consistent 3D representations are crucial. However, existing methods have limitations: 3D diffusion models are limited by…

In recent years, autonomous driving has significantly in creased the demand for high-quality data to train 2D and 3D perception models for safety-critical scenarios. Real world datasets struggle to meet this demand as require ments…

Score distillation sampling (SDS), the methodology in which the score from pretrained 2D diffusion models is distilled into 3D representation, has recently brought significant advancements in text-to-3D generation task. However, this…

Recent works on text-to-3d generation show that using only 2D diffusion supervision for 3D generation tends to produce results with inconsistent appearances (e.g., faces on the back view) and inaccurate shapes (e.g., animals with extra…

Generative models, particularly diffusion models, have made significant success in data synthesis across various modalities, including images, videos, and 3D assets. However, current diffusion models are computationally intensive, often…

RGB-D semantic segmentation can be advanced with convolutional neural networks due to the availability of Depth data. Although objects cannot be easily discriminated by just the 2D appearance, with the local pixel difference and geometric…