Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D (ECCV 2020)

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

Code for paper "PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify"

[ECCV'24] SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic

TrafficBots V1.5: TrafficBots + HPTR. 3rd place solution for Waymo Open Sim Agent Challenge 2024.

Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encoding. NeurIPS 2023.

基于图搜索构建云顶之弈S1版本最强阵容

[ICCV 2023] Multi3DRefer: Grounding Text Description to Multiple 3D Objects

Code for paper "MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping", ECCV 2024 (Oral)

Open-Sora: Democratizing Efficient Video Production for All

Policy Gradient algorithms (REINFORCE, NPG, TRPO, PPO)

Pytorch Implementation for First Order Constrained Optimization in Policy Space (FOCOPS).

code for Category-agnostic Skeletal Animal Reconstruction

A faster implementation of PointNet++ based on PyTorch.

3D Point Cloud registration using ICP

Convert any Triangle Mesh to Watertight Manifold

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

BERT score for text generation

Zeyuan Chen, Yangchao Wang, Yang Yang and Dong Liu. "PSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors". IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

A suite of GUI tools for extracting and modifying OVL and OVS archives, as well as editing the associated in-house file formats. Also includes a model plugin for Blender. For downloads, guides, and…

A Blender addon for generating synthetic ground truth data for Computer Vision applications