Related papers: IGGT: Instance-Grounded Geometry Transformer for S…

Given a single image of a target object, image-to-3D generation aims to reconstruct its texture and geometric shape. Recent methods often utilize intermediate media, such as multi-view images or videos, to bridge the gap between input image…

Understanding and localizing objects in complex 3D environments from natural language descriptions, known as 3D Visual Grounding (3DVG), is a foundational challenge in embodied AI, with broad implications for robotics, augmented reality,…

Generating accurate 3D models is a challenging problem that traditionally requires explicit learning from 3D datasets using supervised learning. Although recent advances have shown promise in learning 3D models from 2D images, these methods…

We introduce the Convolutional Set Transformer (CST), a novel neural architecture designed to process image sets of arbitrary cardinality that are visually heterogeneous yet share high-level semantics - such as a common category, scene, or…

We present a mapping system capable of constructing detailed instance-level semantic models of room-sized indoor environments by means of an RGB-D camera. In this work, we integrate deep-learning-based instance segmentation and…

Scene graph generation aims to capture detailed spatial and semantic relationships between objects in an image, which is challenging due to incomplete labelling, long-tailed relationship categories, and relational semantic overlap. Existing…

We present Inst4DGS, an instance-decomposed 4D Gaussian Splatting (4DGS) approach with long-horizon per-Gaussian trajectories. While dynamic 4DGS has advanced rapidly, instance-decomposed 4DGS remains underexplored, largely due to the…

Polygonal meshes have become the standard for discretely approximating 3D shapes, thanks to their efficiency and high flexibility in capturing non-uniform shapes. This non-uniformity, however, leads to irregularity in the mesh structure,…

The field of self-supervised 3D representation learning has emerged as a promising solution to alleviate the challenge presented by the scarcity of extensive, well-annotated datasets. However, it continues to be hindered by the lack of…

Unpaired Image-to-image Translation is a new rising and challenging vision problem that aims to learn a mapping between unaligned image pairs in diverse domains. Recent advances in this field like MUNIT and DRIT mainly focus on…

Self-supervised learning of point cloud aims to leverage unlabeled 3D data to learn meaningful representations without reliance on manual annotations. However, current approaches face challenges such as limited data diversity and inadequate…

As a pioneering work, PointContrast conducts unsupervised 3D representation learning via leveraging contrastive learning over raw RGB-D frames and proves its effectiveness on various downstream tasks. However, the trend of large-scale…

3D geometry is a very informative cue when interacting with and navigating an environment. This writing proposes a new approach to 3D reconstruction and scene understanding, which implicitly learns 3D geometry from depth maps pairing a deep…

3D semantic scene graphs (3DSSG) provide compact structured representations of environments by explicitly modeling objects, attributes, and relationships. While 3DSSGs have shown promise in robotics and embodied AI, many existing methods…

Joint estimation of surface normals and depth is essential for holistic 3D scene understanding, yet high-resolution prediction remains difficult due to the trade-off between preserving fine local detail and maintaining global consistency.…

Current multi-view indoor 3D object detectors rely on sensor geometry that is costly to obtain (i.e., precisely calibrated multi-view camera poses) to fuse multi-view information into a global scene representation, limiting deployment in…

General 3D foundation models have started to lead the trend of unifying diverse vision tasks, yet most assume RGB-only inputs and ignore readily available geometric cues (e.g., camera intrinsics, poses, and depth maps). To address this…

Modern 3D semantic instance segmentation approaches predominantly rely on specialized voting mechanisms followed by carefully designed geometric clustering techniques. Building on the successes of recent Transformer-based methods for object…

In this work, we present Fed3DGS, a scalable 3D reconstruction framework based on 3D Gaussian splatting (3DGS) with federated learning. Existing city-scale reconstruction methods typically adopt a centralized approach, which gathers all…

Encoding a driving scene into vector representations has been an essential task for autonomous driving that can benefit downstream tasks e.g. trajectory prediction. The driving scene often involves heterogeneous elements such as the…