13 accepted papers
Multi-modal large language models (MLLMs) have rapidly advanced in visual tasks, yet their spatial understanding remains limited to single images, leaving them ill-suited for physical-world applications that require multi-frame reasoning. In this paper, we propose a framework to equip MLLMs with mul
We present SAM 3D, a generative model for visually grounded 3D object reconstruction, predicting geometry, texture, and layout from a single image. SAM 3D excels in natural images, where occlusion and scene clutter are common and visual recognition cues from context play a larger role. We achieve th
We introduce HOIGPT, a token-based generative method that unifies 3D hand-object interactions (HOI) perception and generation, offering the first comprehensive solution for captioning and generating high-quality 3D HOI sequences from a diverse range of conditional signals (e.g. text, objects, partia…
To address the challenge of short-term object pose tracking in dynamic environments with monocular RGB input, we introduce a large-scale synthetic dataset Omni-Pose6D, crafted to mirror the diversity of real-world conditions. We additionally present a benchmarking framework for a comprehensive compa
"Goal-oriented planning, or anticipating a series of actions that transition an agent from its current state to a predefined objective, is crucial for developing intelligent assistants aiding users in daily procedural tasks. The problem presents significant challenges due to the need for comprehensi…
We present Ego-Exo4D a diverse large-scale multimodal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric and exocentric video of skilled human activities (e.g. sports music dance bike repair). 740 participants from 13 cities worldwide perform…
Egocentric videos are often available in the form of uninterrupted, uncurated long videos capturing the camera wearers' daily life activities.Understanding these videos requires models to be able to reason about activities, objects, and their interactions. However, current video benchmarks study the…
This letter investigates the addition of keypoint detections to a deep network affordance segmentation pipeline. The intent is to better interpret the functionality of object parts from a manipulation perspective. While affordance segmentation does provide label information about the potential use o
A segmentation-based architecture is proposed to decompose objects into multiple primitive shapes from monocular depth input for robotic manipulation. The backbone deep network is trained on synthetic data with 6 classes of primitive shapes generated by a simulation engine. Each primitive shape is d…
This letter presents a deep learning framework to predict the affordances of object parts for robotic manipulation. The framework segments affordance maps by jointly detecting and localizing candidate regions within an image. Rather than requiring annotated real-world images, the framework learns fr
This letter presents a framework to detect and rank affordances of novel objects to assist with robotic manipulation tasks. The framework segments the affordance map of unseen objects using region-based affordance segmentation. Detected affordances define an initial state from which to generate acti
A human-in-the-loop system is proposed to enable hands-free collaborative manipulation for people with physical disabilities. Studies show that the cognitive burden of interfacing with a robotic assistant decreases with increased robot autonomy. Incorporating modern advances in perception with augme…
A deep learning architecture is proposed to predict graspable locations for robotic manipulation. It considers situations where no, one, or multiple object(s) are seen. By defining the learning problem to be classified with null hypothesis competition instead of regression, the deep neural network w