facebookresearch / segment_this_thingLinks
Segment This Thing is an efficient image segmentation models that uses a biologically-inspired foveated tokenization to reduce inference costs.
☆53Updated 5 months ago
Alternatives and similar repositories for segment_this_thing
Users that are interested in segment_this_thing are comparing it to the libraries listed below
Sorting:
- Code for QuantVGGT: Quantized Visual Geometry Grounded Transformer☆79Updated 3 weeks ago
- EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory☆49Updated last month
- Implementation of Zero-Shot Video Semantic Segmentation [CVPR 2025]☆54Updated 8 months ago
- Scene-Centric Unsupervised Panoptic Segmentation (CVPR 2025 Highlight)☆73Updated 2 months ago
- [NeurIPS 2025] Official code for JAFAR: Jack up Any Feature at Any Resolution☆200Updated last month
- [CVPR 2025 highlight] Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision☆30Updated 3 weeks ago
- Official implementation of the WACV 2025 paper "3D Part Segmentation via Geometric Aggregation of 2D Visual Features"☆25Updated 5 months ago
- ☆24Updated 7 months ago
- [NeurIPS 2025] Official Implementation of DINO-Foresight: Looking into the Future with DINO☆120Updated last month
- [NeurIPS2023] 3D-OWIS is capable of detecting unknown instances in inference, and progressively learning novel classes in the process of …☆67Updated last year
- [ICRA 2024] Official Implementation of the paper "Parameter-efficient Prompt Learning for 3D Point Cloud Understanding"☆28Updated 8 months ago
- ☆35Updated 6 months ago
- [ICLR 25'] InstantSplamp: Fast and Generalizable Stenography Framework for Generative Gaussian Splatting☆21Updated 7 months ago
- [ECCV 2024] Official Implementation of "Appearance-Based Refinement for Object-Centric Motion Segmentation" Junyu Xie, Weidi Xie, Andrew …☆14Updated last year
- [CVPR'2025] EntitySAM: Segment Everything in Video☆52Updated 4 months ago
- Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion (ICCV 2025)☆71Updated 2 months ago
- [CVPR 2025] RelationField: Relate Anything in Radiance Fields☆84Updated 8 months ago
- Open-Vocabulary Panoptic Segmentation☆27Updated 5 months ago
- [ECCV 2024] Pytorch code for our ECCV'24 paper NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Ra…☆104Updated 8 months ago
- Official PyTorch implementation of Self-Supervised Any-Point Tracking by Contrastive Random Walks, ECCV 2024.☆54Updated last year
- [ECCV 2024] Decomposition Betters Tracking Everything Everywhere☆112Updated last year
- Implementation for DIY-SC paper.☆21Updated 4 months ago
- Scaling Properties of Diffusion Models For Perceptual Tasks (CVPR 2025)☆44Updated 6 months ago
- [AAAI 2025] GFlow: Recovering 4D World from Monocular Video☆55Updated 6 months ago
- [CVPR 2025] CRISP: Object Pose and Shape Estimation with Test-Time Adaptation☆80Updated 7 months ago
- Official repository for paper "Scene-agnostic Pose Regression for Visual Localization" (SPR), CVPR 2025☆30Updated 7 months ago
- Code for the paper "AMEGO: Active Memory from long EGOcentric videos" published at ECCV 2024☆42Updated 11 months ago
- FlowFeat: Pixel-Dense Embedding of Motion Profiles (NeurIPS 2025 Spotlight)☆32Updated last week
- Code implementation of the paper "World-in-World: World Models in a Closed-Loop World"☆84Updated last week
- ☆73Updated 7 months ago