Related papers: IGGT: Instance-Grounded Geometry Transformer for S…
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…
Panoramic imagery offers a full 360{\deg} field of view and is increasingly common in consumer devices. However, it introduces non-pinhole distortions that challenge joint pose estimation and 3D reconstruction. Existing feed-forward models,…
In this paper, we present a novel, scalable approach for constructing open set, instance-level 3D scene representations, advancing open world understanding of 3D environments. Existing methods require pre-constructed 3D scenes and face…
Accurate 3D instance segmentation is crucial for high-quality scene understanding in the 3D vision domain. However, 3D instance segmentation based on 2D-to-3D lifting approaches struggle to produce precise instance-level segmentation, due…
Semantic scene understanding from point clouds is particularly challenging as the points reflect only a sparse set of the underlying 3D geometry. Previous works often convert point cloud into regular grids (e.g. voxels or bird-eye view…
Despite significant progress in 3D object detection, point clouds remain challenging due to sparse data, incomplete structures, and limited semantic information. Capturing contextual relationships between distant objects presents additional…
Reconstructing dynamic driving scenes is essential for developing autonomous systems through sensor-realistic simulation. Although recent methods achieve high-fidelity reconstructions, they either rely on costly human annotations for object…
3D instance segmentation is fundamental to geometric understanding of the world around us. Existing methods for instance segmentation of 3D scenes rely on supervision from expensive, manual 3D annotations. We propose UnScene3D, the first…
Feed-forward 3D foundation models face a key challenge: the quadratic computational cost introduced by global attention, which severely limits scalability as input length increases. Concurrent acceleration methods, such as token merging,…
Scene understanding plays a critical role in enabling intelligence and autonomy in robotic systems. Traditional approaches often face challenges, including occlusions, ambiguous boundaries, and the inability to adapt attention based on…
Real-time immersive video communications, particularly high-fidelity 3D telepresence, necessitates a synergistic balance between instantaneous dynamic scene reconstruction and high-efficiency data transmission. While recent advancements in…
Semantic scene reconstruction from point cloud is an essential and challenging task for 3D scene understanding. This task requires not only to recognize each instance in the scene, but also to recover their geometries based on the partial…
In this study, we address the challenge of 3D scene structure recovery from monocular depth estimation. While traditional depth estimation methods leverage labeled datasets to directly predict absolute depth, recent advancements advocate…
We address the challenge of lifting 2D visual segmentation to 3D in Gaussian Splatting. Existing methods often suffer from inconsistent 2D masks across viewpoints and produce noisy segmentation boundaries as they neglect these semantic cues…
Recovering high-fidelity 3D hand geometry from images is a critical task in computer vision, holding significant value for domains such as robotics, animation and VR/AR. Crucially, scalable applications demand both accuracy and deployment…
Reasoning segmentation aims to segment target objects in complex scenes based on human intent and spatial reasoning. While recent multimodal large language models (MLLMs) have demonstrated impressive 2D image reasoning segmentation,…
Indoor scenes exhibit significant appearance variations due to myriad interactions between arbitrarily diverse object shapes, spatially-changing materials, and complex lighting. Shadows, highlights, and inter-reflections caused by visible…
Masked Modeling (MM) has demonstrated widespread success in various vision challenges, by reconstructing masked visual patches. Yet, applying MM for large-scale 3D scenes remains an open problem due to the data sparsity and scene…
Unsupervised learning for geometric perception (depth, optical flow, etc.) is of great interest to autonomous systems. Recent works on unsupervised learning have made considerable progress on perceiving geometry; however, they usually…
Unsupervised image-to-image translation has gained considerable attention due to the recent impressive progress based on generative adversarial networks (GANs). However, previous methods often fail in challenging cases, in particular, when…