An archive of working notes on 3D vision, sparse tensors, and the math underneath.
I'm a Senior Research Scientist at NVIDIA. This site is the long-form companion to my papers — derivations I had to write out before they made sense, drafts I keep returning to, and tutorials for tools I wish had existed when I was figuring them out.
Featured Research
SpaCeFormer: Real-Time Open-Vocabulary 3D Instance Segmentation Without Proposals
→
Why SVD Should Only Appear at Inference: A Gradient Analysis of Rotation Representations
→
Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation
→PeRFception: Perception using Radiance Fields
→
Deep Global Registration
We present Deep Global Registration, a differentiable framework for pairwise registration of real-world 3D scans. Deep global registration is based on three modules: a 6-dimens...
→
High dimensional Convolutional Neural Networks for 3D Perception
→
Fully Convolutional Geometric Features
→
4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks
In many robotics and VR/AR applications, 3D-videos are readily-available sources of input (a continuous sequence of depth images, or LIDAR scans). However, those 3D-videos are p...
→Recent
All posts →CuTe DSL Basics: A Practical Introduction
CuTe DSL Basics — From Hello to Tiled Kernels This tutorial turns the CuTe DSL script snippets into a connected story: we start with a first GPU kernel, learn how dynamic printing and data types w...
CUDA Memory Load/Store Performance: A Comprehensive Benchmark Analysis
CUDA Memory Load/Store Performance: A Comprehensive Benchmark Analysis GPU memory performance is often the bottleneck in high-performance computing applications. Understanding the nuances of diffe...
Fast Monocular Scene Reconstruction with Global-Sparse Local-Dense Grids
Authors Wei Dong, Christopher Choy, Charles Loop, Or Litany, Yuke Zhu, Anima Anandkumar IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023 Abstract Indoor scene reconstruct...
ACID: Action-Conditional Implicit Visual Dynamics for Deformable Object Manipulation
Authors Yufei Wang, Zhou Xian, Feng Chen, Tsun-Hsuan Wang, Yian Wang, Katerina Fragkiadaki, Christopher Choy, Zackory Erickson, David Held RSS, 2022 Abstract Manipulating volumetric deformabl...
DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
Authors Shiyi Lan, Zhiding Yu, Christopher Choy, Subhashree Radhakrishnan, Guilin Liu, Yuke Zhu, Larry S. Davis, Anima Anandkumar IEEE International Conference on Computer Vision (ICCV), 2021 Ab...
Self-Calibrating Neural Radiance Fields
Authors Yoonwoo Jeong, Seokjun Ahn, Christopher Choy, Animashree Anandkumar, Minsu Cho, Jaesik Park ICCV, 2021 Abstract In this work, we propose a camera self-calibration algorithm for generic ...
Ghost of 3D Perception: Permutation Invariance Matters? Convolutions are Permutation Invariant!
Are you familiar with the python dictionary class? Let me give you a quick test to check your level of knowledge. a = dict() a[1.1] = 1 a[2.1] = 2 b = dict() b[2.1] = 2 b[1.1] = 1 Do you think t...
Faster Neural Radiance Fields Inference
The Neural Radiance Fields (NeRF) proposed an interesting way to represent a 3D scene using an implicit network for high fidelity volumetric rendering. Compared with traditional methods to generate...
Setting Class Attributes in Python
Setting class attributes in python can be tedious. In this post, I want to summarize a trick that I’ve been using to simplify this process. Class Attributes in init In many cases, we have to save...
