Single Frame Semantic Segmentation Using Multi-Modal Spherical Images

[ICCV 2025] Keypoint detection and description learned from image pairs only - no depth, no pose, no artificial augmentation required.

A portable version of LEGO Island (1997)

Minimal solvers for calibrated camera pose estimation

[CVPR'22] CrossLoc localization: a cross-modal visual representation learning method for absolute localization

Powerful, mature open-source cross-platform game engine for Python and C++, developed by Disney and CMU

[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

[CVPR 2024] Code release for "InstanceDiffusion: Instance-level Control for Image Generation"

Adaptive and Temporally Consistent Gaussian Surfels for Multi-view Dynamic Reconstruction

Code for "MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare", CoRL 2022.

[IROS Submission] "360FusionNeRF: Panoramic Neural Radiance Fields with Joint Guidance" by Shreyas Kulkarni, Peng Yin, Sebastian Scherer.

YOLOE: Real-Time Seeing Anything [ICCV 2025]

GRiT: A Generative Region-to-text Transformer for Object Understanding (ECCV2024)

Algorithms and Publications on 3D Object Tracking

Official implementation of the CVPR'24 paper [Adaptive Slot Attention: Object Discovery with Dynamic Slot Number]

This repository contains the official implementation of the research paper, "MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training" CVPR 2024

Repository for the paper "Integrating Visual and Textual Inputs for Searching Large-Scale Map Collections with CLIP"

Code Base for Anyhome

🏘️ Scaling Embodied AI by Procedurally Generating Interactive 3D Houses

Pytorch implementation of Pano2Room (SIGGRAPH Asia 2024)

[CVPR 2023] Official Pytorch code for PROB: Probabilistic Objectness for Open World Object Detection

Codebase for "VLMaterial: Procedural Material Generation with Large Vision-Language Models"