874 citations · 947 across the 7 of their papers we have counts for
7 papers
Closing the Visual Sim-to-Real Gap with Object-Composable NeRFs
Nikhil Mishra, Maximilian Sieb, Pieter Abbeel +1
Deep learning methods for perception are the cornerstone of many robotic systems. Despite their potential for impressive performance, obtaining real-world training data is expensiv…
Convolutional Occupancy Models for Dense Packing of Complex, Novel Objects
Nikhil Mishra, Pieter Abbeel, Xi Chen +1
Dense packing in pick-and-place systems is an important feature in many warehouse and logistics applications. Prior work in this space has largely focused on planning algorithms in…
Distributional Instance Segmentation: Modeling Uncertainty and High Confidence Predictions with Latent-MaskRCNN
YuXuan Liu, Nikhil Mishra, Pieter Abbeel +1
Object recognition and instance segmentation are fundamental skills in any robotic or autonomous system. Existing state-of-the-art methods are often unable to capture meaningful un…
Autoregressive Uncertainty Modeling for 3D Bounding Box Prediction
YuXuan Liu, Nikhil Mishra, Maximilian Sieb +3
3D bounding boxes are a widespread intermediate representation in many computer vision applications. However, predicting them is a challenging task, largely due to partial observab…
PixelSNAIL: An Improved Autoregressive Generative Model
Xi Chen, Nikhil Mishra, Mostafa Rohaninejad +1
Autoregressive generative models consistently achieve the best results in density estimation tasks involving high dimensional data, such as images or audio. They pose density estim…
A Simple Neural Attentive Meta-Learner
Nikhil Mishra, Mostafa Rohaninejad, Xi Chen +1
Deep neural networks excel in regimes with large amounts of data, but tend to struggle when data is scarce or when they need to adapt quickly to changes in the task. In response, r…
Prediction and Control with Temporal Segment Models
Nikhil Mishra, Pieter Abbeel, Igor Mordatch
We introduce a method for learning the dynamics of complex nonlinear systems based on deep generative models over temporal segments of states and actions. Unlike dynamics models th…