Stars
[ICLR 2026] Official repo for paper "Video-As-Prompt: Unified Semantic Control for Video Generation"
🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
Official implementation of ATI: Any Trajectory Instruction for Controllable Video Generation. https://arxiv.org/pdf/2505.22944
Official code base for the ICCV 2023 paper "3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation"
A General NeRF Acceleration Toolbox in PyTorch.
[NeurIPS 2021]: Are Transformers More Robust Than CNNs? (Pytorch implementation & checkpoints)
VoGE: A Differentiable Volume Renderer using Gaussian Ellipsoids for Analysis-by-Synthesis [ICLR 2023]
The official implementation of NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation [ICLR-2021]. https://arxiv.org/pdf/2101.12378.pdf
(ECCV 2022) Code for Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency
Pytorch implementation for A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose
This repository contains the code for the CVPR 2021 paper "GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields"
A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
(ECCV 2020) PyTorch implementation of paper "Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild"
StarMap for Category-Agnostic Keypoint and Viewpoint Estimation
The OccludedPASCAL3D+ is a dataset generated via superimposing occluder to PASCAL3D+ dataset for multiple computer vision tasks.
A python toolbox for bounding box operation