Princeton Vision & Learning Lab ORG

Infinite Photorealistic Worlds using Procedural Generation

No description.

No description.

No description.

No description.

No description.

Deep Patch Visual Odometry/SLAM

No description.

No description.

[ECCV2024 - Oral, Best Paper Award Candidate] SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow

Training and experimentation code used for "Stacked Hourglass Networks for Human Pose Estimation"

Pytorch implementation of the ECCV 2016 paper "Stacked Hourglass Networks for Human Pose Estimation"

A Learning Environment for Theorem Proving with the Coq proof assistant

Training code for "Associative Embedding: End-to-End Learning for Joint Detection and Grouping"

Code to test and use the model from "Stacked Hourglass Networks for Human Pose Estimation"

No description.

[ICLR2026 - Oral] WAFT: Warping-Alone Field Transforms for Optical Flow

Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"

Training code for "Pixels to Graphs by Associative Embedding"

No description.

Code for the NIPS 2016 paper

No description.

[ICCV 25] Official code for "OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration"

No description.

Code for the CVPR 2019 paper "Learning Single-Image Depth from Videos using Quality Assessment Networks"

No description.

[ECCV 2026] WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching

No description.

Official code for View Synthesis with Sculpted Neural Points

An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition

Code for Decorrelated Batch Normalization

[ECCV24] official code for "OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations"

Code for the CVPR 2020 paper "OASIS: A Large-Scale Dataset for Single Image 3D in the Wild"

Code for reproducing experiments in "How Useful is Self-Supervised Pretraining for Visual Tasks?"

Code for reproducing results in ICML 2020 paper "PackIt: A Virtual Environment for Geometric Planning"

Official code for Zero-Shot Depth from Defocus (https://arxiv.org/abs/2603.26658)

Unofficial sample code for Distilled 3D Networks (D3D) in Tensorflow.

[ECCV 2024] LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flow

Official code for ICCV 2023 paper "Convolutional Networks with Oriented 1D Kernels"

Variable-resolution mesh extraction from SDFs/occupancy using Octree marching cubes

No description.

[ICCV 25] Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimation

Code for the paper "Strongly Incremental Constituency Parsing with Graph Neural Networks"

No description.

Official code for NeurRIPS 2020 paper "Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D"

Code for the paper "Learning to Prove Theorems by Learning to Generate Theorems"

Code for the ICCV 2017 paper "Surface Normals in the Wild"

Code for FormulaNet in NIPS 2017

No description.

Code to generate datasets used in "How Useful is Self-Supervised Pretraining for Visual Tasks?"

No description.

[3DV25] Official code for "Towards Foundation Models for 3D Vision: How Close Are We?"

No description.

Code for "Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations"

[CVPR 2026 Oral] SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Grouping

No description.

No description.

No description.

Code for ACL 2018 paper 'Think Visually: Question Answering through Virtual Imagery'

We propose a temporally coherent method for extracting meshes suitable for long-range camera trajectories in unbounded scenes represented by an occupancy function. The key idea is to perform 4D mesh extraction using a new spacetime tree structure called the binary-octree, from which 3D meshes are sliced.

Learning Symbolic Rules for Reasoning in Quasi-Natural Language: https://arxiv.org/abs/2111.12038

codes for ECCV 2016

No description.

No description.

A tool to reorganize and compress your computer vision datasets, including RGB / Depth / Flow / SurfaceNormal framesets or videos.

Code for rendering images for NeurRIPS 2020 paper "Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D"

Code for generating data in ICML 2020 paper "PackIt: A Virtual Environment for Geometric Planning"

No description.

No description.

No description.

No description.

The Infinigen repository used during BinocMesher development, along with the necessary modifications.

No description.

Evaluating multimodal memory beyond long context measurements

No description.

Project Website for AnyBody: A Benchmark Suite for Cross-Embodiment Generalization

No description.

Infinite Photorealistic Worlds using Procedural Generation