Zhelun Shen

rayder. Python

SemanticVLA_Offcial. Python

vggt-omega. [CVPR 2026 Oral] VGGT Omega

SVSM. Scalable View Synthesis Model [CVPR 2026]

RnG. [CVPR26 Highlight] RnG: A Unified Transformer for Complete 3D Modeling from Partial Observations

GenHOI. this is the official repo of GenHOI

history-llms. Information hub for our project training the largest possible historical LLMs.

DiffusionAsShader. [SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

NumCLIP. [ECCV 2024] Teach CLIP to Develop a Number Sense for Ordinal Regression

Open-Sora. Open-Sora: Democratizing Efficient Video Production for All

HunyuanDiT. Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

MiDaS. Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

Marigold. [CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

DKT-Stereo. [CVPR'24] Robust Synthetic-to-Real Transfer for Stereo Matching

BalancedMSE. [CVPR 2022 Oral] Balanced MSE for Imbalanced Visual Regression https://arxiv.org/abs/2203.16427

diffuseMix. Official PyTorch implementation of DiffuseMix : Label-Preserving Data Augmentation with Diffusion Models (CVPR'2024)

xformers. Hackable and optimized Transformers building blocks, supporting a composable construction.

Uni-ControlNet. [NeurIPS 2023] Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Tune-A-Video. [ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation

Grounded-Segment-Anything. Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

FollowYourPose. [AAAI 2024] Follow-Your-Pose: This repo is the official implementation of "Follow-Your-Pose : Pose-Guided Text-to-Video Generation using Pose-Free Videos"

UniControl. Unified Controllable Visual Generation Model

outdoor-nerf-depth. [ACM MM 2023] Digging into Depth Priors for Outdoor Neural Radiance Fields

UCFNet. TPAMI2023 UCFNet:Digging Into Uncertainty-based Pseudo-label for Robust Stereo Matching

mars. MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving

PCWNet. Python

color_transfer. Performs color transfer between two images. Loosely based on the "Color Transfer between Images" paper by Reinhard et al., 2001.

CompletionFormer. [CVPR2023] CompletionFormer: Depth Completion with Convolutions and Vision Transformers

NeRF-Supervised-Deep-Stereo. A novel paradigm for collecting and generating stereo training data using neural rendering

Palette-Image-to-Image-Diffusion-Models. Unofficial implementation of Palette: Image-to-Image Diffusion Models by Pytorch

bts. From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation

Graft-PSMNet. Python

ITSA. ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networks (CVPR 2022)

PENet_ICRA2021. ICRA 2021 "Towards Precise and Efficient Image Guided Depth Completion"

nerf-factory. An awesome PyTorch NeRF library

PaddleDepth. Python

CFNet. CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching（CVPR2021）

OnlinePruductRetrieval. Python

PaddleDetection. Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

NerfingMVS. [ICCV 2021 Oral] NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo

UniMVSNet. [CVPR 2022] Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation

GwcNet. Group-wise Correlation Stereo Network, CVPR 2019

LapDepth-release. Monocular Depth Estimation Using Laplacian Pyramid-Based Depth Residuals

EANet. External Attention Network

AutoShape. ICCV2021 Paper: AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection

SMD-Nets. SMD-Nets: Stereo Mixture Density Networks