David Charatan

pixelsplat. [CVPR 2024 Oral, Best Paper Runner-Up] Code for "pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction" by David Charatan, Sizhe Lester Li, Andrea Tagliasacchi, and Vincent Sitzmann

flowmap. [3DV 2025] Code for "FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent" by Cameron Smith*, David Charatan*, Ayush Tewari, and Vincent Sitzmann

millivid. Official implementation of "MilliVid: Adaptive Latents for Long-Range Consistency in Video Generation"

diff-gaussian-rasterization-modified. Cuda

point2mesh-reimplementation. A reimplementation of Hanocka et al.'s paper Point2Mesh: A Self-Prior for Deformable Meshes for CSCI 1470: Deep Learning at Brown University.

real_estate_10k_tools. Python

meshtryoshka. Code for "Meshtryoshka: Differentiable Rendering of Real-World Scenes via Mesh Rasterization"

jax_template. Python

fused_sample_ops. Cuda

nerf2d. Python

shape-assembly-parser. A parser for the ShapeAssembly domain-specific language.

dcr-reimplementation. A reimplementation of 6D Dynamic Camera Relocalization from Single Reference Image by Feng et al. (CVPR 2016) for ENGN 2560: Computer Vision at Brown University

torchdraw. Python

tensorbox. Python

loopcraft-datagen. Data generation code for "MilliVid: Adaptive Latents for Long-Range Consistency in Video Generation"

torchdraw_cuda. Cuda

neural-style. An implementation of "Perceptual Losses for Real-Time Style Transfer and Super-Resolution" by Johonson et al. for CSCI 1290: Computational Photography at Brown University.

gmflow. [CVPR'22 Oral] GMFlow: Learning Optical Flow via Global Matching

shape-assembly-tool. A command line tool for ShapeAssembly.