arxiv:2609.11486
Published on Sep 10
· Submitted by
Alexander Yakovenko on Sep 11
Upvote
34
Authors:
,
,
Abstract
FreeFlow is a hierarchical transformer for optical flow that eliminates task-specific inductive biases and achieves state-of-the-art accuracy using window, shifted-window, and global attention.
Generated by thinkingmachines/Inkling-Small
Optical flow methods typically rely on task-specific inductive biases, such as correlation volumes, feature warping, and iterative refinement, among others, to reach high accuracy. While effective, such biases constrain the model to predefined heuristics, which can limit its expressivity and lead to more complex pipelines and additional computational cost. We present FreeFlow, a hierarchical transformer built without any flow-specific components, using instead a single feed-forward encoder--decoder. FreeFlow combines three attention variants: window attention for local processing, shifted-window attention for cross-window information exchange, and a global attention operating at a reduced resolution. The resulting architecture scales naturally with model capacity, enabling a consistent accuracy gain from small to large variants. Despite the absence of standard inductive biases, FreeFlow achieves state-of-the-art results on major benchmarks, including Sintel (0.68/1.48 EPE on Clean/Final), KITTI-2015 (3.23 Fl-all), and Spring (3.192 1px), while remaining memory efficient at 1080p inference.
View arXiv page View PDF Project pageGitHub 19 Add to collection
Community
Paper author Paper submitter 12 days ago
State-of-the-art optical flow method without any task-specific biases.
11 days ago
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
-
JEPADepth: Masked Predictive Representation Learning for Self-Supervised Monocular Depth Estimation (2026)
-
PhasorNet: Learning Structure from Frequency for Real-Time Stereo Matching (2026)
-
WAVE-Stereo: Warp-Aligned Volume Encoding for Stereo Matching (2026)
-
UDT: Reconciling U-Nets and Diffusion Transformers with Data-Adaptive Token Reduction (2026)
-
PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimation (2026)
-
PixRestore: Unified Image Restoration via Pixel Diffusion Transformer (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on HF Mirror checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
8 days ago
This is an automated message from the ResearchStudio team.
We created an interactive ResearchStudio Reel for this paper. It includes a visual poster, a video, and a blog, all available for download in editable formats.
Open the ResearchStudio Reel →
Download all files from HF Mirror
Please give this comment a thumbs up if you find the Reel helpful!
Want to explore or create Reels for more papers? Visit the ResearchStudio demo.
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
· Sign up or log in to comment
Upvote
34
Get this paper in your agent:
hf papers read 2609.11486
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 18
Browse 18 models citing this paper
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2609.11486 in a dataset README.md to link it from this page.