Related papers: Z3D: Zero-Shot 3D Visual Grounding from Images
Modern 3D object detection datasets are constrained by narrow class taxonomies and costly manual annotations, limiting their ability to scale to open-world settings. In contrast, 2D vision-language models trained on web-scale image-text…
Aligning ground-level imagery with geo-registered satellite maps is crucial for mapping, navigation, and situational awareness, yet remains challenging under large viewpoint gaps or when GPS is unreliable. We introduce Wrivinder, a…
Visual Grounding, also known as Referring Expression Comprehension and Phrase Grounding, aims to ground the specific region(s) within the image(s) based on the given expression text. This task simulates the common referential relationships…
We investigate transductive zero-shot point cloud semantic segmentation, where the network is trained on seen objects and able to segment unseen objects. The 3D geometric elements are essential cues to imply a novel 3D object type. However,…
Humans can infer the three-dimensional structure of objects from two-dimensional visual inputs. Modeling this ability has been a longstanding goal for the science and engineering of visual intelligence, yet decades of computational methods…
Dynamic Gaussian splatting has led to impressive scene reconstruction and image synthesis advances in novel views. Existing methods, however, heavily rely on pre-computed poses and Gaussian initialization by Structure from Motion (SfM)…
Feed-forward multi-frame 3D reconstruction models often degrade on videos with object motion. Global-reference becomes ambiguous under multiple motions, while the local pointmap relies heavily on estimated relative poses and can drift,…
Open-vocabulary 3D object detection aims to localize and recognize objects beyond a fixed training taxonomy. In multi-view RGB settings, recent approaches often decouple geometry-based instance construction from semantic labeling,…
Monocular 3D object detection is well-known to be a challenging vision task due to the loss of depth information; attempts to recover depth using separate image-only approaches lead to unstable and noisy depth estimates, harming 3D…
Generating a coherent 3D scene representation from multi-view images is a fundamental yet challenging task. Existing methods often struggle with multi-view fusion, leading to fragmented 3D representations and sub-optimal performance. To…
In recent years, there has been an explosion of 2D vision models for numerous tasks such as semantic segmentation, style transfer or scene editing, enabled by large-scale 2D image datasets. At the same time, there has been renewed interest…
Scene representation is a crucial design choice in robotic manipulation systems. An ideal representation is expected to be 3D, dynamic, and semantic to meet the demands of diverse manipulation tasks. However, previous works often lack all…
Open-vocabulary 3D object detection (OV-3DDet) aims to localize and recognize both seen and previously unseen object categories within any new 3D scene. While language and vision foundation models have achieved success in handling various…
Visual localization is the problem of estimating the camera pose of a given query image within a known scene. Most state-of-the-art localization approaches follow the structure-based paradigm and use 2D-3D matches between pixels in a query…
We present LoD-Loc v3, a novel method for generalized aerial visual localization in dense urban environments. While prior work LoD-Loc v2 achieves localization through semantic building silhouette alignment with low-detail city models, it…
Visual-semantic embedding is an interesting research topic because it is useful for various tasks, such as visual question answering (VQA), image-text retrieval, image captioning, and scene graph generation. In this paper, we focus on…
Current Visual-Language Navigation (VLN) methodologies face a trade-off between semantic understanding and control precision. While Multimodal Large Language Models (MLLMs) offer superior reasoning, deploying them as low-level controllers…
While video generation models excel at producing high-quality monocular videos, generating 3D stereoscopic and spatial videos for immersive applications remains an underexplored challenge. We present a pose-free and training-free method…
With the explosive 3D data growth, the urgency of utilizing zero-shot learning to facilitate data labeling becomes evident. Recently, methods transferring language or language-image pre-training models like Contrastive Language-Image…
Spatio-temporal video grounding (STVG) aims at localizing the spatio-temporal tube of a video, as specified by the input text query. In this paper, we utilize multimodal large language models (MLLMs) to explore a zero-shot solution in STVG.…