Pinned Repositories
dreamitate
Dreamitate: Real-World Visuomotor Policy Learning via Video Generation (CoRL 2024)
drrobot
Code for "Differentiable Robot Rendering" (CoRL 2024)
expert
Code for Learning to Learn Language from Narrated Video
hyperfuture
Code for the paper Learning the Predictability of the Future (CVPR 2021)
oops
Code for Oops! Predicting Unintentional Action in Video
pix2gestalt
Code for the paper "pix2gestalt: Amodal Segmentation by Synthesizing Wholes" (CVPR 2024)
SelfSupDefense
viper
Code for the paper "ViperGPT: Visual Inference via Python Execution for Reasoning"
zero123
Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)
ZSRobust4FoundationModel
Computer Vision Lab at Columbia University's Repositories
cvlab-columbia/zero123
Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)
cvlab-columbia/viper
Code for the paper "ViperGPT: Visual Inference via Python Execution for Reasoning"
cvlab-columbia/hyperfuture
Code for the paper Learning the Predictability of the Future (CVPR 2021)
cvlab-columbia/pix2gestalt
Code for the paper "pix2gestalt: Amodal Segmentation by Synthesizing Wholes" (CVPR 2024)
cvlab-columbia/drrobot
Code for "Differentiable Robot Rendering" (CoRL 2024)
cvlab-columbia/oops
Code for Oops! Predicting Unintentional Action in Video
cvlab-columbia/dreamitate
Dreamitate: Real-World Visuomotor Policy Learning via Video Generation (CoRL 2024)
cvlab-columbia/ZSRobust4FoundationModel
cvlab-columbia/expert
Code for Learning to Learn Language from Narrated Video
cvlab-columbia/SelfSupDefense
cvlab-columbia/voicecamo
Code for the paper Real-Time Neural Voice Camouflage
cvlab-columbia/DoubleRight
cvlab-columbia/globetrotter
Code for the Globetrotter project
cvlab-columbia/CT4Recognition
cvlab-columbia/GenInt
cvlab-columbia/RaidarLLMDetect
cvlab-columbia/aquabot
cvlab-columbia/paperbot
PaperBot: Learning to Design Real-World Tools Using Paper
cvlab-columbia/trajectories
Code for the paper "Representing Spatial Trajectories as Distributions"
cvlab-columbia/aha
Code for Video Representations of Goals Emerge from Watching Failure
cvlab-columbia/surfsup
Code for the paper- SURFSUP: Learning Fluid Simulation for Novel Surfaces
cvlab-columbia/CATER
CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning
cvlab-columbia/Equi4Rob