transparent-objects

🎉 Official code release of "TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priors" (ACM MM 2025).

Instant NeRF for depth/3d shape estimation of transparent objects

SIGGRAPH Asia 2020: Differentiable Refraction-Tracing for Mesh Reconstruction of Transparent Objects

[SIGGRAPH'25 (ACM TOG)] TransparentGS: Fast Inverse Rendering of Transparent Objects with Gaussians

Real-time, open-source simulation of transparent objects for deep learning applications

StereOBJ-1M: Large-scale Stereo Image Dataset for 6D Object Pose Estimation (ICCV 2021)

Official implementation of "TransNormal: Dense Visual Semantics for Diffusion-based Transparent Object Normal Estimation" (ICML 2026). Single-step diffusion model for accurate surface normal prediction of transparent objects.

[ICRA'25] NeuGrasp: Generalizable Neural Surface Reconstruction with Background Priors for Material-Agnostic Object Grasp Detection

Detection and Reconstruction of Transparent Objects with Infrared Projection-based RGB-D Cameras

Official implementation of "TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation". Single-step surface normal estimation for general scenes and transparent objects. Code and model weights will be released progressively.

This repository comprises glass segmentation algorithms and corresponding dockerfiles.

MSc AI Thesis work - Depth Estimation for transparent objects

Dataset for depth estimation for transparent objects

A simple class that wraps your renderer and provide basic oit rendering for your opaque and transparent objects.

contained is a crate working to provide macros, primitives, and other utilities useful for working with transparent wrapper types in Rust.

Determining the three-dimensional shape and position of transparent objects for robotic manipulation purposes.

Detect, repair, and govern LLM hallucinations via a proved topological invariant, with no ground truth needed.