FreeFlow: A Bias-free Hierarchical Transformer for Optical Flow Estimation
Updated 2 h ago · first seen 11 Sept 2026
paper_01M294H24VPKWYWZY3AD088WJ1
- Published
- 11 Sept 2026
- T1 · 4 h ago
- arXiv
- 2609.11486
- T1 · 4 h ago
- Category
- cs.CV
- T1 · 4 h ago
Abstract
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.
Authors 4
Vladislav Bargatin, Alexander Yakovenko, Khaled Abud, Dmitriy Vatolin
Specification
- Official page
Source:arXiv (Atom API + RSS)T1observed 4 h agohigh
- Arxiv announce type
- new
Source:arXiv (Atom API + RSS)T1observed 4 h agohigh
- arXiv id
- 2609.11486
Source:arXiv (Atom API + RSS)T1observed 4 h agohigh
- Categories
- cs.CV
Source:arXiv (Atom API + RSS)T1observed 4 h agohigh
- DOI
- 10.1007/978-3-032-37132-4_11
Source:arXiv (Atom API + RSS)T1observed 4 h agohigh
- Github repo
- msu-video-group/freeflow
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- Hf paper url
- https://huggingface.co/papers/2609.11486
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- Github stars
- 8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Hf comments
- 1
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Upvotes
- 5
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Source:arXiv (Atom API + RSS)T1observed 4 h agohigh
- Primary category
- cs.CV
Source:arXiv (Atom API + RSS)T1observed 4 h agohigh
- Published
- 11 Sept 2026
Source:arXiv (Atom API + RSS)T1observed 4 h agohigh
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
15
Source tiers
T1T210 / 5
Freshest observation
2 h ago
Conflicts
3 flagged
No models linked to this paper yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Abstract
Abstractabstract1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 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. | → current | current | arXiv (Atom API + RSS)T1 | high | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
New paper: FreeFlow: A Bias-free Hierarchical Transformer for Optical Flow Estimation
arxiv
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| arXiv (Atom API + RSS) | rss.arxiv.org/rss/cs.CV | feed | T1· Official | 2 h ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/papers | listing | T2· Quality secondary | 2 h ago | 3 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.