Related papers: ShapeGen: Robotic Data Generation for Category-Lev…

Acquiring and annotating surgical data is often resource-intensive, ethical constraining, and requiring significant expert involvement. While generative AI models like text-to-image can alleviate data scarcity, incorporating spatial…

This article investigates, within the field of neuropsychology of artificial intelligence, the process of categorical segmentation performed by language models. This process involves, across different neural layers, the creation of new…

Training a deep network policy for robot manipulation is notoriously costly and time consuming as it depends on collecting a significant amount of real world data. To work well in the real world, the policy needs to see many instances of…

This paper presents MuGen, a data-driven framework for learning and deploying multi-skill locomotion on humanoid robots. MuGen enables a robot to perform expressive motions like humans under the guidance of example motion sequences. To…

The development of high-dimensional generative models has recently gained a great surge of interest with the introduction of variational auto-encoders and generative adversarial neural networks. Different variants have been proposed where…

Large Vision Models trained on internet-scale data have demonstrated strong capabilities in segmenting and semantically understanding object parts, even in cluttered, crowded scenes. However, while these models can direct a robot toward the…

We present PhysGen, a novel image-to-video generation method that converts a single image and an input condition (e.g., force and torque applied to an object in the image) to produce a realistic, physically plausible, and temporally…

Character animation in real-world scenarios necessitates a variety of constraints, such as trajectories, key-frames, interactions, etc. Existing methodologies typically treat single or a finite set of these constraint(s) as separate control…

Existing single-view 3D generative models typically adopt multiview diffusion priors to reconstruct object surfaces, yet they remain prone to inter-view inconsistencies and are unable to faithfully represent complex internal structure or…

The Boundary representation (B-rep) format is the de-facto shape representation in computer-aided design (CAD) to model solid and sheet objects. Recent approaches to generating CAD models have focused on learning sketch-and-extrude modeling…

Existing 3D semantic segmentation methods rely on point-wise or voxel-wise feature descriptors to output segmentation predictions. However, these descriptors are often supervised at point or voxel level, leading to segmentation models that…

Instance segmentation is data-hungry, and as model capacity increases, data scale becomes crucial for improving the accuracy. Most instance segmentation datasets today require costly manual annotation, limiting their data scale. Models…

We present ScaleMoGen, a scale-wise autoregressive framework for text-driven human motion generation. Unlike conventional autoregressive approaches that rely on standard next-token prediction, ScaleMoGen frames motion generation as a…

Utilization of classification latent space information for downstream reconstruction and generation is an intriguing and a relatively unexplored area. In general, discriminative representations are rich in class-specific features but are…

In this paper, we explore generalizable, perception-to-action robotic manipulation for precise, contact-rich tasks. In particular, we contribute a framework for closed-loop robotic manipulation that automatically handles a category of…

Recent deep generative models are able to provide photo-realistic images as well as visual or textual content embeddings useful to address various tasks of computer vision and natural language processing. Their usefulness is nevertheless…

This survey provides a comprehensive review on recent advancements of generative learning models in robotic manipulation, addressing key challenges in the field. Robotic manipulation faces critical bottlenecks, including significant…

Human anatomy, morphology, and associated diseases can be studied using medical imaging data. However, access to medical imaging data is restricted by governance and privacy concerns, data ownership, and the cost of acquisition, thus…

Biological systems can form complex three-dimensional structures through the collective behavior of agents that share a common update rule and operate without central control. How such distributed control gives rise to precise global…

Acquiring and annotating sufficient labeled data is crucial in developing accurate and robust learning-based models, but obtaining such data can be challenging in many medical image segmentation tasks. One promising solution is to…