mworchel/differentiable-shadow-mapping
Differentiable Shadow Mapping for Efficient Inverse Graphics (CVPR 2023)
This tool helps computer graphics researchers and 3D vision developers create realistic shadows in virtual scenes. It takes 3D object models and light source positions as input, then calculates and renders highly accurate shadows. The output is improved shadow maps and scene visibility, crucial for applications like inverse graphics where you infer 3D properties from 2D images.
No commits in the last 6 months.
Use this if you are building a custom differentiable renderer and need to efficiently incorporate realistic shadow mapping with anti-aliasing.
Not ideal if you are a designer using off-the-shelf rendering software and not developing custom graphics algorithms.
Stars
57
Forks
4
Language
Python
License
BSD-3-Clause
Category
Last pushed
Sep 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/mworchel/differentiable-shadow-mapping"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
rundiwu/DeepCAD
code for our ICCV 2021 paper "DeepCAD: A Deep Generative Network for Computer-Aided Design Models"
XingangPan/GAN2Shape
Code for GAN2Shape (ICLR2021 oral)
ayaanzhaque/instruct-nerf2nerf
Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions (ICCV 2023)
compphoto/Intrinsic
Repo for the papers "Intrinsic Image Decomposition via Ordinal Shading" (TOG 2023) and "Colorful...
cgtuebingen/SIGNeRF
SIGNeRF: Scene Integrated Generation for Neural Radiance Fields