Official implementation of Think Global, Act Local: Dual-scale GraphTransformer for Vision-and-Language Navigation (CVPR'22 Oral).

NerF computer vision dataset

code release of paper "Compositional Human-Scene Interaction Synthesis with Semantic Control"

Trilinear sampler with smoothstep and double backpropagation

Rendering Point Clouds with Compute Shaders

Official Implementation of "LiteDepth: Digging into Fast and Accurate Depth Estimation on Mobile Devices"

[ECCV 2022] StyleLight: HDR Panorama Generation for Lighting Estimation and Editing

Self-supervised monocular depth estimation with a vision transformer

open neural graphics primitive

Code release for NeRFReN: Neural Radiance Fields with Reflections (CVPR 2022).

🔥DM-NeRF in PyTorch (ICLR 2023)

[ECCV 2022] PlaneFormers: From Sparse View Planes to 3D Reconstruction

Independent PyTorch implementation of Scene Representation Transformer

(WIP) Official implementation of the NeurIPS 2021 paper "Panoptic 3D Scene Reconstruction from a Single RGB Image"

A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF

DFNet: Enhance Absolute Pose Regression with Direct Feature Matching (ECCV 2022)

SIGGRAPH 2022 Labs Demo for "Learning Smooth Neural Functions via Lipschitz Regularization"

Artistic Radiance Fields

[NeurIPS2022] Official implementation of PeRFception: Perception using Radiance Fields.

Transformers as Meta-Learners for Implicit Neural Representations, in ECCV 2022

This project is the non-official PyTorch implementation of Block-NeRF.

PixTrack is a Computer Vision method for Object Tracking which uses NeRF templates and feature-metric alignment to robustly track the 6DoF pose of a known object.

Different embedding methods and gpu support for depth-supervised NeRF.

NVIDIA Kaolin Wisp is a PyTorch library powered by NVIDIA Kaolin Core to work with neural fields (including NeRFs, NGLOD, instant-ngp and VQAD).

The code of 'Towards Domain-agnostic depth completion'

[ECCV2022] Neural Density-Distance Fields (NeDDF)