multi-view, end2end, 3D Reconstruction

[CVPR 2026 Oral] Official implementation for ChordEdit: One-Step Low-Energy Transport for Image Editing

[ CVPR 2023 Award Candidate ] OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation

Point-Focused Attention Meets Context-Scan State Space: Robust Biological Visual Perception for Point Cloud Representation

[ICML 2026] WorldMirror: Fast and Universal 3D reconstruction model for versatile tasks

An agentic skills framework & software development methodology that works.

[NeurIPS 2025] PointMAC: Meta-learned Adaptation for Robust Test-time Point Cloud Completion

[ICML 2026 Spotlight] Official PyTorch implementation of “SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion”.

[CVPR 2026] Hyper-PCN: Hypergraph-Based Point Cloud Completion via High-Order Correlation Modeling

TartanAir dataset tools and samples

[CVPR 2025] SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization

[AAAI 2026 Oral] SplatSSC: Decoupled Depth-Guided Gaussian Splatting for Semantic Scene Completion

This repository contains PyTorch implementation for Collaborative Completion and Segmentation for Partial Point Clouds with Outliers (TVCG 2023).

Official repository for the paper "MGPC: Multimodal Network for Generalizable Point Cloud Completion With Modality Dropout and Progressive Decoding"

Reference PyTorch implementation and models for DINOv3

[IEEE TPAMI 2026] Flexible-weighted Chamfer Distance: Enhanced Objective Function for Point Cloud Completion

[CVPR 2026] LaS-Comp: Zero-shot 3D Completion with Latent–Spatial Consistency

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

[AAAI 2026 Poster] TOSC: Task-Oriented Shape Completion for Open-World Dexterous Grasp Generation from Partial Point Clouds

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

Native and Compact Structured Latents for 3D Generation

[ICCV'25 Oral] The official implementation of Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion

[CVPR'24] Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion

The official implementation of Diffusion Distillation With Direct Preference Optimization For Efficient 3D LiDAR Scene Completion [AAAI'26]

Tracking acceptance rates at global CS/AI conferences. This repository contains metadata for building the OpenAccept main site.

We have summarised all 3D anomaly detection methods and datasets (still updating). 多模态，点云和姿势无关异常检测的综述仓库（持续更新）

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer