Related papers: NOVA: Next-step Open-Vocabulary Autoregression for…
Referring Multi-Object Tracking (RMOT) aims to achieve precise object detection and tracking through natural language instructions, representing a fundamental capability for intelligent robotic systems. However, current RMOT research…
Zero-shot object navigation has advanced rapidly with open-vocabulary detectors, image--text models, and language-guided exploration. However, even after current methods detect a plausible target hypothesis, the agent may still oscillate…
Closed-set 3D perception models trained on only a pre-defined set of object categories can be inadequate for safety critical applications such as autonomous driving where new object types can be encountered after deployment. In this paper,…
The development of Neural Radiance Fields (NeRFs) has provided a potent representation for encapsulating the geometric and appearance characteristics of 3D scenes. Enhancing the capabilities of NeRFs in open-vocabulary 3D semantic…
Recent studies have explored leveraging the world knowledge and cognitive capabilities of Vision-Language Models (VLMs) to address the long-tail problem in end-to-end autonomous driving. However, existing methods typically formulate…
The transformer neural network architecture allows for autoregressive sequence-to-sequence modeling through the use of attention layers. It was originally created with the application of machine translation but has revolutionized natural…
The goal of this work is to establish a scalable pipeline for expanding an object detector towards novel/unseen categories, using zero manual annotations. To achieve that, we make the following four contributions: (i) in pursuit of…
3D multi-object tracking is an important component in robotic perception systems such as self-driving vehicles. Recent work follows a tracking-by-detection pipeline, which aims to match past tracklets with detections in the current frame.…
Open-Vocabulary Multi-Object Tracking (OV-MOT) aims to enable approaches to track objects without being limited to a predefined set of categories. Current OV-MOT methods typically rely primarily on instance-level detection and association,…
Reliable detection of various objects and road users in the surrounding environment is crucial for the safe operation of automated driving systems (ADS). Despite recent progresses in developing highly accurate object detectors based on Deep…
Tracking objects that move within dynamic environments is a core challenge in robotics. Recent research has advanced this topic significantly; however, many existing approaches remain inefficient due to their reliance on heavy foundation…
Omnimodal understanding entails a massive, highly redundant search space of cross-modal interactions, demanding focused and deliberative reasoning. Current reasoning paradigms rely on either sequential step-by-step generation or parallel…
3D semantic occupancy and flow prediction are fundamental to spatiotemporal scene understanding. This paper proposes a vision-based framework with three targeted improvements. First, we introduce an occlusion-aware adaptive lifting…
Generalizing open-vocabulary 3D instance segmentation (OV-3DIS) to diverse, unstructured, and mesh-free environments is crucial for robotics and AR/VR, yet remains a significant challenge. We attribute this to two key limitations of…
Large vision-language models (VLMs) have shown promising capabilities in scene understanding, enhancing the explainability of driving behaviors and interactivity with users. Existing methods primarily fine-tune VLMs on on-board multi-view…
Learning-based perception and prediction modules in modern autonomous driving systems typically rely on expensive human annotation and are designed to perceive only a handful of predefined object categories. This closed-set paradigm is…
Vision-Language Models (VLM) exhibit strong reasoning capabilities, showing promise for end-to-end autonomous driving systems. Chain-of-Thought (CoT), as VLM's widely used reasoning strategy, is facing critical challenges. Existing textual…
Autonomous navigation under natural language instructions represents a crucial step toward embodied intelligence, enabling complex task execution in environments ranging from industrial facilities to domestic spaces. However,…
Reference Audio-Visual Segmentation (Ref-AVS) aims to provide a pixel-wise scene understanding in Language-aided Audio-Visual Scenes (LAVS). This task requires the model to continuously segment objects referred to by text and audio from a…
This paper targets on learning-based novel view synthesis from a single or limited 2D images without the pose supervision. In the viewer-centered coordinates, we construct an end-to-end trainable conditional variational framework to…